Index
A
- accuracy measures
- accuracy score, Accuracy Measures for Classification Models, Accuracy Measures for Classification Models, Classifying Passengers Who Sailed on the Titanic
- activation functions, Understanding Neural Networks
- Adam optimizer, Building Neural Networks with Keras and TensorFlow
- adaptive learning rate algorithms, Training Neural Networks
- additive modeling, Gradient-Boosting Machines
- additive smoothing, Naive Bayes
- agglomerative clustering, Segmenting Customers Using More Than Two Dimensions
- AlexNet, Image Classification with Convolutional Neural Networks
- algorithm, Machine Learning
- AlphaGo, Machine Learning Versus Artificial Intelligence
- analyze_image_in_stream method, The Computer Vision Service
- analyze_sentiment, Calling Azure Cognitive Services APIs
- anchors and anchor boxes, R-CNNs
- annotate_image function, Mask R-CNN
- anomaly detection, Anomaly Detection-Multivariate Anomaly Detection
- Anomaly Detector, Introducing Azure Cognitive Services
- anonymizing data, Anonymizing Data-Anonymizing Data
- ArcFace, ArcFace, Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- arctic wildlife recognition, Accuracy Measures for Classification Models, Training a CNN to Recognize Arctic Wildlife-Training a CNN to Recognize Arctic Wildlife, Using Transfer Learning to Identify Arctic Wildlife-Using Transfer Learning to Identify Arctic Wildlife, Applying Image Augmentation to Arctic Wildlife-Applying Image Augmentation to Arctic Wildlife
- area under the curve (AUC), Accuracy Measures for Classification Models
- argmax function, Multiclass Classification with Neural Networks
- artificial intelligence (AI)
- attention mechanisms, Transformer Encoder-Decoders-Transformer Encoder-Decoders
- AUC (area under the curve), Accuracy Measures for Classification Models
- audio classification with CNNs, Audio Classification with CNNs-Audio Classification with CNNs
- AudioConfig object, The Speech Service
- augmentation layers, Image Augmentation with Augmentation Layers
- average pooling layer, Understanding CNNs
- AWS AI Services, Azure Cognitive Services
- Azure Cognitive Services APIs, Custom Object Detection, Azure Cognitive Services-Summary
- calling APIs, Calling Azure Cognitive Services APIs-Calling Azure Cognitive Services APIs
- Computer Vision service, Image Classification with Convolutional Neural Networks, Introducing Azure Cognitive Services, The Computer Vision Service-The Computer Vision Service
- containers, Azure Cognitive Services Containers-Azure Cognitive Services Containers
- Contoso Travel exercise, Putting It All Together: Contoso Travel-Putting It All Together: Contoso Travel
- Decision services, Introducing Azure Cognitive Services
- keys and endpoints, Keys and Endpoints-Keys and Endpoints
- Language service, Introducing Azure Cognitive Services, The Language Service-The Language Service
- SDKs available, Calling Azure Cognitive Services APIs-Calling Azure Cognitive Services APIs
- Speech service, Introducing Azure Cognitive Services, The Speech Service-The Speech Service
- subscription setup, Training a Custom Object Detection Model with the Custom Vision Service-Training a Custom Object Detection Model with the Custom Vision Service
- Translator service, The Translator Service-The Translator Service
- Azure Portal, Keys and Endpoints
- AzureError, Calling Azure Cognitive Services APIs
B
- backpropagation, Training Neural Networks-Training Neural Networks, Building Neural Networks with Keras and TensorFlow, Dropout
- bag of words, Text Classification
- batch normalization, Pretrained CNNs
- Bayes’ theorem, Naive Bayes
- bearing failure prediction, anomaly detection, Using PCA to Predict Bearing Failure-Using PCA to Predict Bearing Failure
- BERT (bidirectional encoder representations from transformers), Bidirectional Encoder Representations from Transformers (BERT)-Fine-Tuning BERT to Perform Sentiment Analysis
- biases, neural networks, Understanding Neural Networks, Understanding Neural Networks, Using a Neural Network to Predict Taxi Fares
- bidirectional encoder representations from transformers (BERT), Bidirectional Encoder Representations from Transformers (BERT)-Fine-Tuning BERT to Perform Sentiment Analysis
- bilingual evaluation understudy (BLEU) scores, Building a Transformer-Based NMT Model
- binary classification models, Binary Classification-Detecting Credit Card Fraud
- binary classifiers, in Viola-Jones face detection, Face Detection with Viola-Jones
- binary trees, Decision Trees
- binary_crossentropy function, Binary Classification with Neural Networks
- BLEU (bilingual evaluation understudy) scores, Building a Transformer-Based NMT Model
- Boltzmann machines, Machine Learning Versus Artificial Intelligence
- boosting, Gradient-Boosting Machines-Gradient-Boosting Machines
- bottleneck layers, Understanding CNNs, Understanding CNNs, Using Keras and TensorFlow to Build CNNs, Transfer Learning-Transfer Learning
- bottom Sobel kernel, Understanding CNNs
- bounding boxes, object detection, R-CNNs
- breast cancer dataset, Data Normalization, Anonymizing Data
C
- C parameter, SVMs, How Support Vector Machines Work, Hyperparameter Tuning-Hyperparameter Tuning
- C#
- California Housing Prices dataset, Accuracy Measures for Regression Models
- Callback class, Keras Callbacks
- callbacks, Keras, Keras Callbacks-Keras Callbacks
- CART (Classification and Regression Tree) algorithm, Decision Trees
- cascade classifiers, Face Detection with Viola-Jones-Using the OpenCV Implementation of Viola-Jones
- CascadeClassifier class, Using the OpenCV Implementation of Viola-Jones-Using the OpenCV Implementation of Viola-Jones
- categorical data, Categorical Data-Categorical Data
- categorical values, Categorical Data
- categorical_crossentropy function, Multiclass Classification with Neural Networks
- centroid, cluster, Unsupervised Learning with k-Means Clustering
- Classification and Regression Tree (CART) algorithm, Decision Trees
- classification boundary, Supervised Learning
- classification models, Supervised Learning-Supervised Learning, Classification Models-Summary
- accuracy measures for, Classification Models, Accuracy Measures for Classification Models-Accuracy Measures for Classification Models
- audio classification, Audio Classification with CNNs-Audio Classification with CNNs
- binary classifiers, Binary Classification-Detecting Credit Card Fraud, Binary Classification with Neural Networks-Training a Neural Network to Detect Credit Card Fraud
- CNNs, Understanding CNNs, Understanding CNNs, Transfer Learning-Transfer Learning
- digit recognition model, Building a Digit Recognition Model-Building a Digit Recognition Model
- GBMs, Gradient-Boosting Machines-Gradient-Boosting Machines
- image (see images, classifying and generating)
- and k-nearest neighbors, k-Nearest Neighbors, Using k-Nearest Neighbors to Classify Flowers-Using k-Nearest Neighbors to Classify Flowers
- logistic regression (see logistic regression)
- MLPs for, Understanding CNNs
- multiclass, Supervised Learning, Using k-Nearest Neighbors to Classify Flowers-Using k-Nearest Neighbors to Classify Flowers, Classification Models, Multiclass Classification-Multiclass Classification, Multiclass Classification with Neural Networks-Multiclass Classification with Neural Networks
- multilabel, Classification Models
- SVMs (see support vector machines)
- text (see text classification and processing)
- cleaning of text for vectorization, Preparing Text for Classification
- closed-set versus open-set classification, Handling Unknown Faces: Closed-Set Versus Open-Set Classification-Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- clustering algorithms, Unsupervised Learning with k-Means Clustering
- CNNs (see convolutional neural networks)
- COCO dataset, Mask R-CNN, YOLOv3 and Keras
- coefficient of determination (R²), Accuracy Measures for Regression Models, Using a Neural Network to Predict Taxi Fares
- collaborative recommender system, Recommender Systems
- Computer Vision service, Image Classification with Convolutional Neural Networks, Introducing Azure Cognitive Services, The Computer Vision Service-The Computer Vision Service
- ComputerVisionClient class, The Computer Vision Service
- conditional probability, Naive Bayes
- confidence value, object detection, YOLOv3 and Keras
- confusion matrix, Accuracy Measures for Classification Models, Using SVMs for Facial Recognition-Using SVMs for Facial Recognition
- ConfusionMatrixDisplay class, Accuracy Measures for Classification Models, Spam Filtering
- confusion_matrix function, Accuracy Measures for Classification Models
- consuming Python model from C# client, Consuming a Python Model from a C# Client-Consuming a Python Model from a C# Client
- container image, Containerizing a Machine Learning Model
- container registry, Containerizing a Machine Learning Model
- containerizing an ML model, Operationalizing Machine Learning Models, Containerizing a Machine Learning Model-Containerizing a Machine Learning Model, Azure Cognitive Services Containers-Azure Cognitive Services Containers
- Content Moderator service, Introducing Azure Cognitive Services
- content-based recommender system, Recommender Systems
- continual learning, Saving and Loading Models
- Contoso Travel exercise, Putting It All Together: Contoso Travel-Putting It All Together: Contoso Travel
- Conv1D class, Factoring Word Order into Predictions
- Conv2D layers, Sizing a Neural Network, Using Keras and TensorFlow to Build CNNs-Using Keras and TensorFlow to Build CNNs
- convolutional kernels (kernels), Understanding CNNs-Understanding CNNs
- convolutional neural networks (CNNs), Understanding Neural Networks, Image Classification with Convolutional Neural Networks-Summary
- architectures, Pretrained CNNs
- arctic wildlife recognition, Training a CNN to Recognize Arctic Wildlife-Training a CNN to Recognize Arctic Wildlife, Using Transfer Learning to Identify Arctic Wildlife-Using Transfer Learning to Identify Arctic Wildlife
- audio classification, Audio Classification with CNNs-Audio Classification with CNNs
- building with Keras and TensorFlow, Using Keras and TensorFlow to Build CNNs-Using Keras and TensorFlow to Build CNNs
- convolution layers, Understanding CNNs-Understanding CNNs
- data augmentation, Data Augmentation-Applying Image Augmentation to Arctic Wildlife
- face detection, Face Detection with Convolutional Neural Networks-Face Detection with Convolutional Neural Networks, Putting It All Together: Detecting and Recognizing Faces in Photos-Putting It All Together: Detecting and Recognizing Faces in Photos
- facial recognition, Applying Transfer Learning to Facial Recognition-Putting It All Together: Detecting and Recognizing Faces in Photos
- GANs, Understanding Neural Networks
- global pooling, Global Pooling-Global Pooling
- object detection with R-CNNs, R-CNNs-Mask R-CNN
- pretrained models, Pretrained CNNs-Using ResNet50V2 to Classify Images
- corr method, Using Regression to Predict Taxi Fares-Using Regression to Predict Taxi Fares
- cosine similarity, Cosine Similarity-Building a Movie Recommendation System, ArcFace
- CountVectorizer class, Preparing Text for Classification-Preparing Text for Classification, Sentiment Analysis-Sentiment Analysis, Spam Filtering, Recommender Systems, Consuming a Python Model from a Python Client, Text Preparation
- covariance matrix, Understanding Principal Component Analysis
- Cover’s theorem, How Support Vector Machines Work
- credit card fraud detection
- cross-validation, Accuracy Measures for Regression Models-Accuracy Measures for Regression Models, Logistic Regression, Classifying Passengers Who Sailed on the Titanic
- cross_val_score function, Accuracy Measures for Regression Models
- CSVLogger class, Keras Callbacks
- Custom Vision service, Training a Custom Object Detection Model with the Custom Vision Service-Training a Custom Object Detection Model with the Custom Vision Service, Introducing Azure Cognitive Services
- customer segmentation, Applying k-Means Clustering to Customer Data-Segmenting Customers Using More Than Two Dimensions
- customers dataset, Applying k-Means Clustering to Customer Data
D
- Darknet, YOLOv3 and Keras
- data
- overfitting of, Decision Trees, Hyperparameter Tuning, Building Neural Networks with Keras and TensorFlow
- preprocessing of (see preprocessing data)
- shuffling of, Building Neural Networks with Keras and TensorFlow, Text Classification
- test set, Using k-Nearest Neighbors to Classify Flowers, Accuracy Measures for Regression Models, Accuracy Measures for Regression Models
- time series, Recurrent Neural Networks (RNNs)
- training set, Using k-Nearest Neighbors to Classify Flowers
- underfitting of, Hyperparameter Tuning, Building Neural Networks with Keras and TensorFlow
- visualizing high-dimensional, Visualizing High-Dimensional Data-Visualizing High-Dimensional Data
- data augmentation, Data Augmentation-Applying Image Augmentation to Arctic Wildlife
- data cleaning, Using k-Nearest Neighbors to Classify Flowers, Preparing Text for Classification, Building a Transformer-Based NMT Model
- data normalization, Data Normalization-Data Normalization
- DataFrame, Categorical Data
- Dataset.to_tf_dataset method, Fine-Tuning BERT to Perform Sentiment Analysis
- Datasets library, Hugging Face, Fine-Tuning BERT to Perform Sentiment Analysis
- DBSCAN (density-based spatial clustering of applications with noise), Segmenting Customers Using More Than Two Dimensions
- decision boundaries, How Support Vector Machines Work, Kernels, Kernel Tricks-Hyperparameter Tuning
- Decision services, Introducing Azure Cognitive Services
- decision tree stumps, Gradient-Boosting Machines
- decision trees, Decision Trees-Decision Trees
- DecisionTreeClassifier class, Decision Trees
- DecisionTreeRegressor class, Decision Trees
- decode_predictions function, YOLOv3 and Keras
- deep learning, Machine Learning Versus Artificial Intelligence, Deep Learning-Summary
- (see also neural networks)
- Deepset, Building a BERT-Based Question Answering System
- Dense layers, Building Neural Networks with Keras and TensorFlow, Sizing a Neural Network
- dense vector representation, Using Keras and TensorFlow to Build CNNs
- density-based spatial clustering of applications with noise (DBSCAN), Segmenting Customers Using More Than Two Dimensions
- dependent decision trees, Gradient-Boosting Machines
- depthwise separable convolutions, Pretrained CNNs
- describe_image method, The Computer Vision Service
- describe_image_in_stream method, The Computer Vision Service
- detectMultiScale, Using the OpenCV Implementation of Viola-Jones
- digit recognition model, Building a Digit Recognition Model-Building a Digit Recognition Model
- dimensionality reduction
- disconnected containers, Azure Cognitive Services, Azure Cognitive Services Containers
- DistilBERT model, Bidirectional Encoder Representations from Transformers (BERT)
- docker build command, Containerizing a Machine Learning Model
- Docker container, Operationalizing Machine Learning Models, Containerizing a Machine Learning Model
- document translation, The Translator Service
- dot product, Using Keras and TensorFlow to Build CNNs
- Dropout layers, Sizing a Neural Network, Dropout-Dropout, Global Pooling
E
- EarlyStopping class, Keras Callbacks, Building a Transformer-Based NMT Model
- eigenvectors and eigenvalues, Understanding Principal Component Analysis
- Elasticsearch, Building a BERT-Based Question Answering System
- elbow method to plot inertias, Unsupervised Learning with k-Means Clustering
- Embedding class, Word Embeddings
- embedding layer, Natural Language Processing, Word Embeddings-Text Classification
- encoder–decoder models, LSTM Encoder-Decoders-Transformer Encoder-Decoders
- ensemble learning, random forests, Random Forests-Random Forests, Detecting Credit Card Fraud, Using PCA to Detect Credit Card Fraud
- epochs, Building Neural Networks with Keras and TensorFlow
- estimators, Pipelining, Consuming a Python Model from a Python Client
- Euclidean distance, k-Nearest Neighbors
- Excel, adding ML capabilities to, Adding Machine Learning Capabilities to Excel-Adding Machine Learning Capabilities to Excel
- expert systems, Machine Learning Versus Artificial Intelligence
- explained variance, plotting, Understanding Principal Component Analysis-Understanding Principal Component Analysis
- extracting faces from photos, Extracting Faces from Photos-Extracting Faces from Photos
- extract_key_phrases method, The Language Service
F
- F1 score, Accuracy Measures for Classification Models
- face detection, Face Detection and Recognition-Extracting Faces from Photos
- face embedding, ArcFace
- Face service, Introducing Azure Cognitive Services, The Computer Vision Service
- face verification, ArcFace
- FaceNet, Facial Recognition
- facial recognition, Facial Recognition-Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- false positive rate (FPR), Accuracy Measures for Classification Models
- Fast R-CNN, R-CNNs
- Faster R-CNN, R-CNNs
- feature columns, What Is Machine Learning?
- feature maps, Understanding CNNs
- filtering noise in images, Filtering Noise-Filtering Noise
- fit method
- fit_on_texts method, Text Preparation
- Flask framework, Operationalizing Machine Learning Models, Putting It All Together: Contoso Travel
- Flatten layer, Global Pooling, Text Classification
- flow method, Image Augmentation with ImageDataGenerator
- flow_from_directory method, Image Augmentation with ImageDataGenerator
- folds, Accuracy Measures for Regression Models
- FPR (false positive rate), Accuracy Measures for Classification Models
- fully connected layers, Understanding Neural Networks
- functional API, Keras, Neural Networks, Building a Transformer-Based NMT Model-Building a Transformer-Based NMT Model
G
- gamma parameter, SVM kernels, Hyperparameter Tuning-Hyperparameter Tuning
- GANs (generative adversarial networks), Understanding Neural Networks
- gated recurrent unit (GRU) layer, Recurrent Neural Networks (RNNs)
- GBDTs (gradient-boosted decision trees), Gradient-Boosting Machines-Gradient-Boosting Machines
- GBMs (gradient-boosting machines), Gradient-Boosting Machines-Gradient-Boosting Machines
- generative adversarial networks (GANs), Understanding Neural Networks
- get_weights method, Saving and Loading Models
- Gini impurity, Decision Trees
- global minimum, Training Neural Networks
- global pooling, Global Pooling-Global Pooling
- GlobalAveragePooling2D layer, Global Pooling, Audio Classification with CNNs
- GlobalMaxPooling2D layer, Global Pooling
- GlorotUniform initializer, Building Neural Networks with Keras and TensorFlow
- GloVe word vectors, Word Embeddings
- GPUs (graphics processing units), Machine Learning Versus Artificial Intelligence, Deep Learning, Training a CNN to Recognize Arctic Wildlife
- gradient descent, Training Neural Networks
- gradient-boosted decision trees (GBDTs), Gradient-Boosting Machines-Gradient-Boosting Machines
- gradient-boosting machines (GBMs), Gradient-Boosting Machines-Gradient-Boosting Machines
- GradientBoostingClassifier class, Gradient-Boosting Machines-Gradient-Boosting Machines, Detecting Credit Card Fraud
- GradientBoostingRegressor class, Gradient-Boosting Machines-Gradient-Boosting Machines, Using Regression to Predict Taxi Fares
- graphics processing units (GPUs), Machine Learning Versus Artificial Intelligence, Deep Learning, Training a CNN to Recognize Arctic Wildlife
- GridSearchCV, Hyperparameter Tuning, Pipelining, Using SVMs for Facial Recognition-Using SVMs for Facial Recognition
- GRU (gated recurrent unit) layer, Recurrent Neural Networks (RNNs)
- GRU class, Recurrent Neural Networks (RNNs)
H
- H2O framework, Building ML Models in C# with ML.NET, Sentiment Analysis with ML.NET
- H5 file format, Saving and Loading Models
- Haar-like features, Face Detection with Viola-Jones
- handwritten text
- HashingVectorizer class, Preparing Text for Classification, Preparing Text for Classification, Consuming a Python Model from a Python Client
- Haystack library, Building a BERT-Based Question Answering System
- hidden layers, Understanding Neural Networks, Understanding Neural Networks, Building Neural Networks with Keras and TensorFlow
- hidden state, layer, Recurrent Neural Networks (RNNs)
- high recall then precision pattern, Face Detection with Viola-Jones
- high-dimensional data visualization, Visualizing High-Dimensional Data-Visualizing High-Dimensional Data
- Hugging Face, Using Pretrained Models to Classify Text, Using Pretrained Models to Translate Text, Building a BERT-Based Question Answering System-Fine-Tuning BERT to Perform Sentiment Analysis
- hyperparameter tuning, Hyperparameter Tuning-Hyperparameter Tuning
I
- IDataView, Building ML Models in C# with ML.NET, Sentiment Analysis with ML.NET
- ImageDataGenerator, Image Augmentation with ImageDataGenerator-Image Augmentation with ImageDataGenerator
- ImageNet dataset, Pretrained CNNs
- images, classifying and generating, What Is Machine Learning?-What Is Machine Learning?
- IMDB movie dataset, Sentiment Analysis, Using TextVectorization in a Sentiment Analysis Model, Fine-Tuning BERT to Perform Sentiment Analysis
- impurity measures, Decision Trees
- imputing missing values, Classifying Passengers Who Sailed on the Titanic
- Inception, Pretrained CNNs
- incremental training, Saving and Loading Models
- inertias, plotting, Unsupervised Learning with k-Means Clustering
- InferenceSession method, ONNX, Using ONNX to Bridge the Language Gap
- Input class, ML.NET, Sentiment Analysis with ML.NET
- input layer, neural network, Understanding Neural Networks, Understanding Neural Networks, Building Neural Networks with Keras and TensorFlow
- instance segmentation, Mask R-CNN-Mask R-CNN
- integral images, Face Detection with Viola-Jones
- Intellipix, Introducing Azure Cognitive Services
- intersection-over-union (IoU) score, R-CNNs
- inverse_transform method, Preparing Text for Classification, Understanding Principal Component Analysis
- Iris dataset, Using k-Nearest Neighbors to Classify Flowers, Linear Regression
- isolation forest, Anomaly Detection
- Isomap, Visualizing High-Dimensional Data
K
- k-fold cross-validation, Accuracy Measures for Regression Models-Accuracy Measures for Regression Models
- k-means clustering, Unsupervised Learning with k-Means Clustering-Segmenting Customers Using More Than Two Dimensions
- k-nearest neighbors, k-Nearest Neighbors-Using k-Nearest Neighbors to Classify Flowers, Data Normalization
- Keras API, Training Neural Networks, Neural Networks
- building neural networks with, Building Neural Networks with Keras and TensorFlow-Using a Neural Network to Predict Taxi Fares
- callbacks, Keras Callbacks-Keras Callbacks
- CNNs, Using Keras and TensorFlow to Build CNNs-Using Keras and TensorFlow to Build CNNs
- functional API, Neural Networks, Building a Transformer-Based NMT Model-Building a Transformer-Based NMT Model
- LSTM-based models, LSTM Encoder-Decoders-LSTM Encoder-Decoders
- MobileNetV2, Pretrained CNNs
- pretrained CNN models, Pretrained CNNs-Using ResNet50V2 to Classify Images
- saving models, Saving and Loading Models, Using TextVectorization in a Sentiment Analysis Model
- sequential API, Neural Networks-Building Neural Networks with Keras and TensorFlow
- tensorflow.keras.callbacks.CSVLogger, Keras Callbacks
- tensorflow.keras.callbacks.EarlyStopping, Keras Callbacks, Building a Transformer-Based NMT Model
- tensorflow.keras.callbacks.LearningRateScheduler, Keras Callbacks
- tensorflow.keras.callbacks.ModelCheckpoint, Keras Callbacks
- tensorflow.keras.callbacks.TensorBoard, Keras Callbacks
- tensorflow.keras.layers.Conv1D, Factoring Word Order into Predictions
- tensorflow.keras.layers.Conv2D, Sizing a Neural Network, Using Keras and TensorFlow to Build CNNs-Using Keras and TensorFlow to Build CNNs
- tensorflow.keras.layers.Dense, Building Neural Networks with Keras and TensorFlow, Using a Neural Network to Predict Taxi Fares
- tensorflow.keras.layers.Dropout, Sizing a Neural Network, Dropout-Dropout, Global Pooling
- tensorflow.keras.layers.Embedding, Word Embeddings
- tensorflow.keras.layers.Flatten, Global Pooling, Text Classification
- tensorflow.keras.layers.GlobalAveragePooling2D, Global Pooling, Audio Classification with CNNs
- tensorflow.keras.layers.GlobalMaxPooling2D, Global Pooling-Global Pooling
- tensorflow.keras.layers.GRU, Recurrent Neural Networks (RNNs)
- tensorflow.keras.layers.Input, Automating Text Vectorization
- tensorflow.keras.layers.LSTM, Recurrent Neural Networks (RNNs)
- tensorflow.keras.layers.MaxPooling1D, Factoring Word Order into Predictions
- tensorflow.keras.layers.MaxPooling2D, Using Keras and TensorFlow to Build CNNs-Using Keras and TensorFlow to Build CNNs
- tensorflow.keras.layers.MultiHeadAttention, Building a Transformer-Based NMT Model
- tensorflow.keras.layers.Rescaling, Image Augmentation with Augmentation Layers
- tensorflow.keras.layers.TextVectorization, Text Preparation, Automating Text Vectorization-Using TextVectorization in a Sentiment Analysis Model
- tensorflow.keras.losses.binary_crossentropy, Binary Classification with Neural Networks
- tensorflow.keras.losses.categorical_crossentropy, Multiclass Classification with Neural Networks
- tensorflow.keras.losses.sparse_categorical_crossentropy, Multiclass Classification with Neural Networks, Training a Neural Network to Recognize Faces
- tensorflow.keras.models.load_model, Saving and Loading Models
- tensorflow.keras.models.Sequential, Building Neural Networks with Keras and TensorFlow, Using a Neural Network to Predict Taxi Fares
- tensorflow.keras.preprocessing.image.ImageDataGenerator, Image Augmentation with ImageDataGenerator-Image Augmentation with ImageDataGenerator
- tensorflow.keras.preprocessing.sequence.pad_sequences, Text Preparation
- tensorflow.keras.preprocessing.text.Tokenizer, Text Preparation-Text Preparation, Automating Text Vectorization, Building a Transformer-Based NMT Model
- tensorflow.keras.utils.to_categorical, Multiclass Classification with Neural Networks
- transformer-based NMT model, Building a Transformer-Based NMT Model-Building a Transformer-Based NMT Model
- and YOLO, YOLOv3 and Keras-YOLOv3 and Keras
- KerasNLP, Building a Transformer-Based NMT Model-Building a Transformer-Based NMT Model
- kernel tricks, Support Vector Machines, Kernel Tricks-Kernel Tricks
- kernels (convolution kernels), Understanding CNNs-Understanding CNNs
- kernels, SVM, Kernels-Kernel Tricks
- keyword extraction, Preparing Text for Classification
- KMeans class, Unsupervised Learning with k-Means Clustering
- KNeighborsClassifier class, Using k-Nearest Neighbors to Classify Flowers-Using k-Nearest Neighbors to Classify Flowers
- KNeighborsRegressor class, Using k-Nearest Neighbors to Classify Flowers
- Kubernetes, Containerizing a Machine Learning Model
L
- L-BFGS (Limited-memory Broyden–Fletcher–Goldfarb–Shanno) algorithm, Logistic Regression
- label column, What Is Machine Learning?
- labeled data, Supervised Versus Unsupervised Learning, Supervised Learning
- Labeled Faces in the Wild (LFW) dataset, What Is Machine Learning?, Using SVMs for Facial Recognition, Understanding Principal Component Analysis, Training a Neural Network to Recognize Faces, Facial Recognition
- LabelEncoder class, Categorical Data
- labels
- language models (see natural language processing)
- Language service, Introducing Azure Cognitive Services, The Language Service-The Language Service
- Laplace smoothing, Naive Bayes
- Lasso class, Linear Regression
- lazy learning algorithm, Using k-Nearest Neighbors to Classify Flowers
- leaf node, decision tree, Decision Trees
- learning algorithm, Machine Learning
- learning rates, Gradient-Boosting Machines, Training Neural Networks
- LearningRateScheduler class, Keras Callbacks
- lemmatizing, Preparing Text for Classification
- LFW (Labeled Faces in the Wild) dataset, What Is Machine Learning?, Using SVMs for Facial Recognition, Understanding Principal Component Analysis, Training a Neural Network to Recognize Faces, Facial Recognition
- Librosa package, Audio Classification with CNNs
- Limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) algorithm, Logistic Regression
- linear kernel, Kernels, Using SVMs for Facial Recognition-Using SVMs for Facial Recognition
- linear regression, Linear Regression-Linear Regression, Understanding Neural Networks
- LinearRegression class, Linear Regression, Using Regression to Predict Taxi Fares
- LinearSVC class, Using SVMs for Facial Recognition
- LoadFromTextFile method, ML.NET, Sentiment Analysis with ML.NET
- load_iris function, Using k-Nearest Neighbors to Classify Flowers
- local outlier factor (LOF), Anomaly Detection
- logistic function, Logistic Regression
- logistic regression, Logistic Regression-Logistic Regression
- LogisticRegression class, Logistic Regression
- LogisticRegressionCV class, Logistic Regression
- logit function, Logistic Regression
- long short-term memory (LSTM) cell, Recurrent Neural Networks (RNNs)
- loss functions, Training Neural Networks, Multiclass Classification with Neural Networks
- loss landscape, Training Neural Networks
- loss parameter, Building Neural Networks with Keras and TensorFlow
- LSTM (long short-term memory) cell, Recurrent Neural Networks (RNNs)
- LSTM class, Recurrent Neural Networks (RNNs)
- LSTM encoder-decoders, LSTM Encoder-Decoders-LSTM Encoder-Decoders
M
- machine learning (ML), Machine Learning-Summary
- MAE (mean absolute error), Building Neural Networks with Keras and TensorFlow, Building Neural Networks with Keras and TensorFlow
- make_blobs function, Unsupervised Learning with k-Means Clustering
- make_pipeline function, Pipelining, Consuming a Python Model from a Python Client
- Manhattan distance, Using k-Nearest Neighbors to Classify Flowers
- mAP (mean Average Precision), Training a Custom Object Detection Model with the Custom Vision Service
- Mask R-CNN, Mask R-CNN-Mask R-CNN
- masked language modeling, Bidirectional Encoder Representations from Transformers (BERT)
- Matplotlib, Unsupervised Learning with k-Means Clustering, Visualizing High-Dimensional Data
- max pooling layer, Understanding CNNs, Using Keras and TensorFlow to Build CNNs
- MaxPooling1D class, Factoring Word Order into Predictions
- MaxPooling2D class, Using Keras and TensorFlow to Build CNNs
- max_df parameter, Preparing Text for Classification
- MBGD (mini-batch gradient descent), Training Neural Networks
- mean absolute error (MAE), Building Neural Networks with Keras and TensorFlow, Building Neural Networks with Keras and TensorFlow
- mean Average Precision (mAP), Training a Custom Object Detection Model with the Custom Vision Service
- mean squared error (MSE), Linear Regression, Building Neural Networks with Keras and TensorFlow
- metrics parameter, Building Neural Networks with Keras and TensorFlow
- MHA (multi-head attention), Transformer Encoder-Decoders
- Microsoft.ML.OnnxRuntime, Using ONNX to Bridge the Language Gap
- mini-batch gradient descent (MBGD), Training Neural Networks
- MiniLM models, Building a BERT-Based Question Answering System-Building a BERT-Based Question Answering System
- Minkowski distance, Using k-Nearest Neighbors to Classify Flowers
- MinMaxScaler, Data Normalization, Data Normalization
- minNeighbors parameter, Using the OpenCV Implementation of Viola-Jones
- min_df parameter, Preparing Text for Classification
- ML (see machine learning)
- ML Operations (MLOps), Versioning Pickle Files
- ML.NET, building models in C#, Building ML Models in C# with ML.NET-Saving and Loading ML.NET Models
- MLContext class, Sentiment Analysis with ML.NET
- MLPClassifier class, Understanding Neural Networks
- MLPRegressor class, Understanding Neural Networks
- MLPs (multilayer perceptrons), Understanding Neural Networks, Understanding CNNs
- MNIST dataset, Using Keras and TensorFlow to Build CNNs, Training a CNN to Recognize Arctic Wildlife, Global Pooling
- MobiFace, Facial Recognition
- MobileNetV2, Pretrained CNNs, Audio Classification with CNNs
- ModelCheckpoint class, Keras Callbacks
- movie recommendations, Building a Movie Recommendation System-Building a Movie Recommendation System
- Mplot3D, Visualizing High-Dimensional Data
- MSE (mean squared error), Linear Regression, Building Neural Networks with Keras and TensorFlow
- MTCNNs (multitask cascaded convolutional neural networks), Face Detection with Convolutional Neural Networks-Face Detection with Convolutional Neural Networks, Putting It All Together: Detecting and Recognizing Faces in Photos-Putting It All Together: Detecting and Recognizing Faces in Photos
- multi-head attention (MHA), Transformer Encoder-Decoders
- multiclass classification models, Supervised Learning, Using k-Nearest Neighbors to Classify Flowers-Using k-Nearest Neighbors to Classify Flowers, Classification Models, Multiclass Classification-Multiclass Classification, Multiclass Classification with Neural Networks-Multiclass Classification with Neural Networks
- multicollinearity, Linear Regression
- MultiHeadAttention class, Building a Transformer-Based NMT Model
- multilabel classification models, Classification Models
- multilayer perceptrons (MLPs), Understanding Neural Networks, Understanding CNNs
- multinomial logistic regression, Multiclass Classification
- MultinomialNB class, Naive Bayes, Spam Filtering
- multiple linear regression, Linear Regression
- multitask cascaded convolutional neural networks (MTCNNs), Face Detection with Convolutional Neural Networks-Face Detection with Convolutional Neural Networks, Putting It All Together: Detecting and Recognizing Faces in Photos-Putting It All Together: Detecting and Recognizing Faces in Photos
- multivariate anomaly detection, Multivariate Anomaly Detection
N
- n-grams, Preparing Text for Classification, Factoring Word Order into Predictions
- Naive Bayes learning algorithm, Naive Bayes-Naive Bayes
- named-entity recognition, The Language Service
- natural language processing (NLP), Natural Language Processing-Summary
- and AI as a service, Introducing Azure Cognitive Services
- Azure Language service, Introducing Azure Cognitive Services, The Language Service-The Language Service
- Azure Speech service, Introducing Azure Cognitive Services, The Speech Service-The Speech Service
- Azure Translator service, Introducing Azure Cognitive Services, The Translator Service-The Translator Service
- BERT, Bidirectional Encoder Representations from Transformers (BERT)-Fine-Tuning BERT to Perform Sentiment Analysis
- combining with computer vision, Image Classification with Convolutional Neural Networks
- encoder-decoder network for machine translation, LSTM Encoder-Decoders-Transformer Encoder-Decoders
- extracting text from photos, The Computer Vision Service
- neural machine translation, Neural Machine Translation-Using Pretrained Models to Translate Text
- sentiment analysis (see sentiment analysis)
- text classification (see text classification and processing)
- text preparation, Text Preparation-Text Preparation
- word embeddings, Natural Language Processing, Word Embeddings-Word Embeddings, Recurrent Neural Networks (RNNs)-Recurrent Neural Networks (RNNs)
- Natural Language Toolkit (NLTK), Preparing Text for Classification, Text Preparation
- neural machine translation (NMT), Neural Machine Translation-Using Pretrained Models to Translate Text
- neural networks, Deep Learning-Understanding Neural Networks, Neural Networks-Summary
- backpropagation, Training Neural Networks-Training Neural Networks, Building Neural Networks with Keras and TensorFlow, Dropout
- binary classification with, Binary Classification with Neural Networks-Training a Neural Network to Detect Credit Card Fraud
- dropout, Sizing a Neural Network, Dropout-Dropout, Global Pooling
- facial recognition, Training a Neural Network to Recognize Faces-Training a Neural Network to Recognize Faces
- Keras callbacks, Keras Callbacks-Keras Callbacks
- multiclass classification with, Multiclass Classification with Neural Networks-Multiclass Classification with Neural Networks
- multilayer perceptrons, Understanding Neural Networks, Understanding CNNs
- saving and loading models, Saving and Loading Models-Saving and Loading Models
- sizing, Sizing a Neural Network
- taxi fare prediction, Using a Neural Network to Predict Taxi Fares-Using a Neural Network to Predict Taxi Fares
- training, Training Neural Networks-Training Neural Networks
- NimbusML, Building ML Models in C# with ML.NET
- NLTK (Natural Language Toolkit), Preparing Text for Classification, Text Preparation
- NMS (non-maximum suppression), R-CNNs
- NMT (see neural machine translation)
- noise, filtering, Filtering Noise-Filtering Noise
- non-maximum suppression (NMS), R-CNNs
- nonparametric models, Linear Regression, Random Forests-Gradient-Boosting Machines, Detecting Credit Card Fraud, Using PCA to Detect Credit Card Fraud
- (see also decision trees)
- normalization, Linear Regression, Data Normalization-Data Normalization, Training a Neural Network to Recognize Faces
- NumPy, Using Keras and TensorFlow to Build CNNs
- NumPy arrays, Using ONNX to Bridge the Language Gap
- NuSVC class, Using SVMs for Facial Recognition
- Nvidia GPU card, Deep Learning, Training a CNN to Recognize Arctic Wildlife
O
- object detection, Object Detection-Summary
- bounding boxes, Using the OpenCV Implementation of Viola-Jones, R-CNNs, R-CNNs, Mask R-CNN, YOLO, Training a Custom Object Detection Model with the Custom Vision Service
- Computer Vision service, The Computer Vision Service-The Computer Vision Service
- custom, Custom Object Detection-Using the Exported Model
- faces (see face detection)
- R-CNNs, R-CNNs-Mask R-CNN
- YOLO, YOLO-YOLOv3 and Keras
- objectness score, R-CNNs
- occlusions, Training a Custom Object Detection Model with the Custom Vision Service
- OLS (ordinary least squares) regression, Linear Regression
- one-class SVM, Anomaly Detection
- one-hot encoding, Categorical Data
- one-versus-all strategy, Multiclass Classification
- one-versus-one strategy, Multiclass Classification
- one-versus-rest strategy, Multiclass Classification
- OneHotEncoder class, Categorical Data
- ONNX (Open Neural Network Exchange), Operationalizing Machine Learning Models, Using ONNX to Bridge the Language Gap-Using ONNX to Bridge the Language Gap, Mask R-CNN-Mask R-CNN
- open-set versus closed-set classification, Handling Unknown Faces: Closed-Set Versus Open-Set Classification-Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- OpenCV library, Using the OpenCV Implementation of Viola-Jones-Using the OpenCV Implementation of Viola-Jones
- openmax output layer, Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- operationalizing ML models, Operationalizing Machine Learning Models-Summary
- Optical Recognition of Handwritten Digits dataset, Building a Digit Recognition Model, Visualizing High-Dimensional Data
- optimizers, Training Neural Networks, Building Neural Networks with Keras and TensorFlow
- ordinary least squares (OLS) regression, Linear Regression
- outlier detection (see anomaly detection)
- outliers, Segmenting Customers Using More Than Two Dimensions, Linear Regression, Using Regression to Predict Taxi Fares, Anomaly Detection
- Output class, ML.NET, Sentiment Analysis with ML.NET
- output layer, neural network, Understanding Neural Networks, Understanding Neural Networks, Building Neural Networks with Keras and TensorFlow, Multiclass Classification with Neural Networks
- Output Network (O-Net), Face Detection with Convolutional Neural Networks
- overfitting of data, Decision Trees, Hyperparameter Tuning, Building Neural Networks with Keras and TensorFlow
P
- pad_sequences function, Text Preparation, Automating Text Vectorization
- pair plots, Linear Regression
- pairplot function, Linear Regression
- parallelism
- parametric learning algorithm, Linear Regression
- (see also support vector machines)
- PCA (see principal component analysis)
- PCA transform, Understanding Principal Component Analysis
- Perceptron class, Understanding Neural Networks
- Personalizer service, Introducing Azure Cognitive Services
- personally identifiable information (PII), The Language Service
- pickle files, versioning, Versioning Pickle Files
- pickle module, Consuming a Python Model from a Python Client
- pipelines
- plot_confusion_matrix function, Accuracy Measures for Classification Models
- polynomial kernel, Kernels, Hyperparameter Tuning, Using SVMs for Facial Recognition
- PolynomialFeatures class, Linear Regression
- pooling layers, Understanding CNNs
- popularity-based recommender system, Recommender Systems
- positional encoding (positional embedding), Transformer Encoder-Decoders
- Power BI, Accuracy Measures for Classification Models
- precision and recall, classifier metrics, Accuracy Measures for Classification Models-Accuracy Measures for Classification Models, Classifying Passengers Who Sailed on the Titanic
- predict method, Using k-Nearest Neighbors to Classify Flowers, Logistic Regression, Spam Filtering, Building Neural Networks with Keras and TensorFlow
- predictions, What Is Machine Learning?
- accuracy measures, Training a Neural Network to Detect Credit Card Fraud-Training a Neural Network to Detect Credit Card Fraud, Training a CNN to Recognize Arctic Wildlife
- anomaly detection, Using PCA to Predict Bearing Failure-Using PCA to Predict Bearing Failure
- confusion matrix, Accuracy Measures for Classification Models, Using SVMs for Facial Recognition-Using SVMs for Facial Recognition
- decision trees, Decision Trees-Decision Trees
- k-nearest neighbors for image classification, Using k-Nearest Neighbors to Classify Flowers
- with neural network, Making Predictions-Making Predictions
- pipelining, Pipelining
- regression models, Using Regression to Predict Taxi Fares-Using Regression to Predict Taxi Fares
- taxi fares, Using Regression to Predict Taxi Fares-Using Regression to Predict Taxi Fares, Using a Neural Network to Predict Taxi Fares-Using a Neural Network to Predict Taxi Fares
- word order in, Factoring Word Order into Predictions-Factoring Word Order into Predictions
- predictors, Gradient-Boosting Machines
- predict_proba method, Logistic Regression, Sentiment Analysis, Spam Filtering
- preprocess function, Mask R-CNN, Mask R-CNN
- preprocessing data
- image preprocessing layers, Image Augmentation with ImageDataGenerator-Image Augmentation with ImageDataGenerator
- LabelEncoder, Segmenting Customers Using More Than Two Dimensions, Categorical Data
- Mask R-CNN, Mask R-CNN
- MinMaxScaler, Data Normalization
- StandardScaler, Data Normalization, Data Normalization, Pipelining, Training a Neural Network to Recognize Faces
- text sequences, Text Preparation
- preprocessor parameter, Preparing Text for Classification
- pretraining and pretrained models, Pretrained CNNs-Using ResNet50V2 to Classify Images
- primary principal component, Understanding Principal Component Analysis
- principal component analysis (PCA), Linear Regression, Detecting Credit Card Fraud, Principal Component Analysis-Summary
- privacy issue, and facial recognition, Face Detection and Recognition
- probabilities, estimating, What Is Machine Learning?
- Proposal Network (P-Net), Face Detection with Convolutional Neural Networks
- Python, Running the Book’s Code Samples
R
- R-CNNs (region-based CNNs), R-CNNs-Mask R-CNN
- R² (coefficient of determination), Accuracy Measures for Regression Models, Using a Neural Network to Predict Taxi Fares
- radius neighbors, Using k-Nearest Neighbors to Classify Flowers
- RadiusNeighborsClassifier class, Using k-Nearest Neighbors to Classify Flowers
- RadiusNeighborsRegressor class, Using k-Nearest Neighbors to Classify Flowers
- Rainforest Connection, Audio Classification with CNNs
- rainforest sounds dataset, Audio Classification with CNNs
- random forests, Random Forests-Random Forests, Detecting Credit Card Fraud, Using PCA to Detect Credit Card Fraud
- RandomForestClassifier class, Random Forests, Detecting Credit Card Fraud, Detecting Credit Card Fraud
- RandomForestRegressor class, Random Forests, Using Regression to Predict Taxi Fares
- random_state parameter, Unsupervised Learning with k-Means Clustering, Accuracy Measures for Regression Models
- RBF kernel, Kernels, Hyperparameter Tuning-Hyperparameter Tuning, Using SVMs for Facial Recognition
- RBMT (rules-based machine translation), Neural Machine Translation
- read_in_stream method, The Computer Vision Service
- recall and precision classifier metrics, Accuracy Measures for Classification Models-Accuracy Measures for Classification Models, Classifying Passengers Who Sailed on the Titanic
- recall_score, Accuracy Measures for Classification Models
- receiver operating characteristic (ROC) curve, Accuracy Measures for Classification Models
- recognize_once_async method, The Speech Service
- recognize_pii_entities method, The Language Service
- recognize_printed_text_in_stream method, The Computer Vision Service
- recommender systems, Recommender Systems-Building a Movie Recommendation System
- reconstruction error, Anomaly Detection
- rectified linear units (ReLU), Understanding Neural Networks, Understanding Neural Networks, Building Neural Networks with Keras and TensorFlow, Sizing a Neural Network
- recurrent neural networks (RNNs), Understanding Neural Networks, Recurrent Neural Networks (RNNs)-Recurrent Neural Networks (RNNs)
- Refine Network (R-Net), Face Detection with Convolutional Neural Networks
- region of interest (ROI) alignment, Mask R-CNN
- region of interest (ROI) pooling, R-CNNs
- region proposal network (RPN), R-CNNs, R-CNNs
- region-based CNNs (R-CNNs), R-CNNs-Mask R-CNN
- regression models, Supervised Learning-Supervised Learning, Regression Models-Summary
- accuracy measures for, Accuracy Measures for Regression Models-Accuracy Measures for Regression Models
- and coefficient of determination, Accuracy Measures for Regression Models
- decision trees, Decision Trees-Decision Trees
- GBMs, Gradient-Boosting Machines-Gradient-Boosting Machines
- and k-nearest neighbors, k-Nearest Neighbors-k-Nearest Neighbors
- linear regression, Linear Regression-Linear Regression, Using Regression to Predict Taxi Fares
- random forests, Random Forests-Random Forests, Detecting Credit Card Fraud, Using PCA to Detect Credit Card Fraud
- softmax regression, Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- SVMs, Support Vector Machines
- taxi fare prediction, Using Regression to Predict Taxi Fares-Using Regression to Predict Taxi Fares
- regularization, Linear Regression, How Support Vector Machines Work, Using SVMs for Facial Recognition
- reinforcement learning, Machine Learning Versus Artificial Intelligence
- Rekognition service, Azure Cognitive Services
- ReLU (rectified linear units), Understanding Neural Networks, Understanding Neural Networks, Building Neural Networks with Keras and TensorFlow, Sizing a Neural Network
- RepeatVector layer, LSTM Encoder-Decoders
- Requests package, Calling Azure Cognitive Services APIs
- Rescaling layer, Image Augmentation with Augmentation Layers
- residual layers, Pretrained CNNs
- residuals, decision trees, Gradient-Boosting Machines
- ResNet-152, Image Classification with Convolutional Neural Networks
- ResNet-50V2, Pretrained CNNs-Using ResNet50V2 to Classify Images, Using Transfer Learning to Identify Arctic Wildlife-Using Transfer Learning to Identify Arctic Wildlife
- Responsible AI initiative, Microsoft, The Computer Vision Service
- REST APIs, and AI as a service, Azure Cognitive Services, Keys and Endpoints
- retriever-reader architecture, Building a BERT-Based Question Answering System
- Ridge class, Linear Regression
- RNNs (recurrent neural networks), Understanding Neural Networks, Recurrent Neural Networks (RNNs)-Recurrent Neural Networks (RNNs)
- ROC (receiver operating characteristic) curve, Accuracy Measures for Classification Models
- RocCurveDisplay class, Accuracy Measures for Classification Models, Spam Filtering
- roc_auc_score, Accuracy Measures for Classification Models
- ROI (region of interest) alignment, Mask R-CNN
- ROI (region of interest) pooling, R-CNNs
- RPN (region proposal network), R-CNNs, R-CNNs
- rules-based machine translation (RBMT), Neural Machine Translation
S
- SavedModel format, Saving and Loading Models, Using TextVectorization in a Sentiment Analysis Model
- Scaper, soundscape synthesis, Audio Classification with CNNs
- scatter function, Unsupervised Learning with k-Means Clustering
- Scikit-Learn, Unsupervised Learning with k-Means Clustering
- hyperparameter optimizers, Hyperparameter Tuning
- versus ML.Net, Building ML Models in C# with ML.NET, Sentiment Analysis with ML.NET
- multiclass classification feature, Multiclass Classification-Multiclass Classification
- Skl2onnx conversion, Using ONNX to Bridge the Language Gap
- sklearn.cluster.KMeans, Unsupervised Learning with k-Means Clustering
- sklearn.datasets.fetch_california_housing, Accuracy Measures for Regression Models
- sklearn.datasets.fetch_lfw_people, Using SVMs for Facial Recognition, Training a Neural Network to Recognize Faces
- sklearn.datasets.load_breast_cancer, Anonymizing Data
- sklearn.datasets.load_digits, Visualizing High-Dimensional Data
- sklearn.datasets.load_iris, Using k-Nearest Neighbors to Classify Flowers
- sklearn.decomposition.PCA, Understanding Principal Component Analysis, Visualizing High-Dimensional Data, Using PCA to Detect Credit Card Fraud, Using PCA to Predict Bearing Failure
- sklearn.ensemble.GradientBoostingClassifier, Gradient-Boosting Machines-Gradient-Boosting Machines, Detecting Credit Card Fraud
- sklearn.ensemble.GradientBoostingRegressor, Gradient-Boosting Machines-Gradient-Boosting Machines, Using Regression to Predict Taxi Fares
- sklearn.ensemble.RandomForestClassifier, Random Forests, Detecting Credit Card Fraud, Detecting Credit Card Fraud
- sklearn.ensemble.RandomForestRegressor, Random Forests, Using Regression to Predict Taxi Fares
- sklearn.feature_extraction.text.CountVectorizer, Preparing Text for Classification-Preparing Text for Classification, Spam Filtering, Recommender Systems, Consuming a Python Model from a Python Client, Text Preparation
- sklearn.feature_extraction.text.HashingVectorizer, Preparing Text for Classification, Preparing Text for Classification, Consuming a Python Model from a Python Client
- sklearn.feature_extraction.text.TfidfVectorizer, Preparing Text for Classification, Preparing Text for Classification
- sklearn.linear_model.Lasso, Linear Regression
- sklearn.linear_model.LinearRegression, Linear Regression, Accuracy Measures for Regression Models, Using Regression to Predict Taxi Fares
- sklearn.linear_model.LogisticRegression, Consuming a Python Model from a Python Client
- sklearn.linear_model.Perceptron, Understanding Neural Networks
- sklearn.linear_model.Ridge, Linear Regression
- sklearn.manifold.TSNE, Visualizing High-Dimensional Data
- sklearn.metrics.ConfusionMatrixDisplay, Accuracy Measures for Classification Models, Spam Filtering
- sklearn.metrics.RocCurveDisplay, Spam Filtering
- sklearn.metrics.roc_auc_score, Accuracy Measures for Classification Models
- sklearn.model_selection.GridSearchCV, Hyperparameter Tuning, Pipelining, Using SVMs for Facial Recognition-Using SVMs for Facial Recognition
- sklearn.model_selection.train_test_split, Using k-Nearest Neighbors to Classify Flowers, Accuracy Measures for Regression Models-Accuracy Measures for Regression Models
- sklearn.naive_bayes.MultinomialNB, Spam Filtering
- sklearn.neighbors.KNeighborsClassifier, Using k-Nearest Neighbors to Classify Flowers
- sklearn.neural_network.MLPClassifier, Understanding Neural Networks
- sklearn.neural_network.MLPRegressor, Understanding Neural Networks
- sklearn.pipeline.make_pipeline, Pipelining, Consuming a Python Model from a Python Client
- sklearn.preprocessing.LabelEncoder, Segmenting Customers Using More Than Two Dimensions, Categorical Data
- sklearn.preprocessing.MinMaxScaler, Data Normalization
- sklearn.preprocessing.OneHotEncoder, Categorical Data
- sklearn.preprocessing.PolynomialFeatures, Linear Regression
- sklearn.preprocessing.StandardScaler, Data Normalization, Data Normalization, Pipelining, Training a Neural Network to Recognize Faces
- sklearn.svm.SVC, Support Vector Machines, Support Vector Machines, Hyperparameter Tuning
- sklearn.svm.SVR, Support Vector Machines, Support Vector Machines
- sklearn.tree.DecisionTreeClassifier, Decision Trees
- sklearn.tree.DecisionTreeRegressor, Decision Trees
- sklearn.utils.shuffle, Accuracy Measures for Regression Models
- score method, Using k-Nearest Neighbors to Classify Flowers, Accuracy Measures for Regression Models
- scree plot, Understanding Principal Component Analysis
- segmentation masks, Mask R-CNN-Mask R-CNN
- selective search, R-CNNs
- self-attention, Transformer Encoder-Decoders
- sensitivity metric, Accuracy Measures for Classification Models, Classifying Passengers Who Sailed on the Titanic
- sentiment analysis, What Is Machine Learning?, Text Classification
- separable convolutions, Pretrained CNNs
- sequence-to-sequence model, LSTM Encoder-Decoders
- sequences, word embeddings, Natural Language Processing, Text Preparation
- sequence_to_texts method, Text Preparation
- sequential API, Keras, Neural Networks-Building Neural Networks with Keras and TensorFlow
- set_weights method, Saving and Loading Models
- SGD (stochastic gradient descent), Training Neural Networks
- shuffling data, Accuracy Measures for Regression Models, Building Neural Networks with Keras and TensorFlow, Text Classification
- sigmoid activation function, Building Neural Networks with Keras and TensorFlow, Binary Classification with Neural Networks-Making Predictions, Understanding CNNs
- sigmoid kernel, Kernels
- similarity matrix, recommender system, Cosine Similarity
- simple linear regression, Linear Regression
- sizing a neural network, Sizing a Neural Network
- SMT (statistical machine translation), Neural Machine Translation
- soft mask, Mask R-CNN
- softmax activation function, Multiclass Classification, Building Neural Networks with Keras and TensorFlow
- softmax regression, Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- spam filtering, What Is Machine Learning?, Supervised Versus Unsupervised Learning, Naive Bayes-Spam Filtering, Text Classification-Text Classification
- sparse_categorical_crossentropy function, Multiclass Classification with Neural Networks, Training a Neural Network to Recognize Faces
- spatial analysis, The Computer Vision Service
- specificity metric, Accuracy Measures for Classification Models, Classifying Passengers Who Sailed on the Titanic
- spectrogram images, Audio Classification with CNNs-Audio Classification with CNNs
- Speech service, Introducing Azure Cognitive Services, The Speech Service-The Speech Service
- SpeechSynthesizer class, The Speech Service
- SQuAD 2.0, Building a BERT-Based Question Answering System
- standardization, Data Normalization
- StandardScaler class, Data Normalization, Data Normalization, Pipelining, Training a Neural Network to Recognize Faces
- statistical machine translation (SMT), Neural Machine Translation
- stemming, Preparing Text for Classification
- stochastic gradient descent (SGD), Training Neural Networks
- stop words, removing, Preparing Text for Classification, Sentiment Analysis, Text Preparation, Text Preparation, Automating Text Vectorization
- subsampling, Gradient-Boosting Machines
- supervised learning models, Supervised Versus Unsupervised Learning, Supervised Learning-Using k-Nearest Neighbors to Classify Flowers
- support vector machines (SVMs), Support Vector Machines, Support Vector Machines-Summary
- SVC class, Support Vector Machines, Support Vector Machines, Hyperparameter Tuning
- SVR class, Support Vector Machines, Support Vector Machines
T
- t-distributed stochastic neighbor embedding (t-SNE), Linear Regression, Visualizing High-Dimensional Data
- tag_image_in_stream method, The Computer Vision Service
- tanh activation function, Building Neural Networks with Keras and TensorFlow
- task-specific weights to boost transfer learning, Boosting Transfer Learning with Task-Specific Weights-Boosting Transfer Learning with Task-Specific Weights
- Tatoeba project, Building a Transformer-Based NMT Model
- taxi fare prediction, Using Regression to Predict Taxi Fares-Using Regression to Predict Taxi Fares, Using a Neural Network to Predict Taxi Fares-Using a Neural Network to Predict Taxi Fares
- tensor arrays, Neural Networks
- tensor processing units (TPUs), Deep Learning
- TensorBoard, Keras Callbacks
- tensordot function, Using Keras and TensorFlow to Build CNNs
- TensorFlow, Training Neural Networks
- TensorFlow Lite, Audio Classification with CNNs
- term frequency-inverse document frequency (TF-IDF), Preparing Text for Classification
- test set, Using k-Nearest Neighbors to Classify Flowers, Accuracy Measures for Regression Models, Accuracy Measures for Regression Models
- text classification and processing, What Is Machine Learning?, Text Classification-Summary, Text Classification-Using Pretrained Models to Classify Text
- cleaning text, Preparing Text for Classification
- datasets for working with text, What Is Machine Learning?
- extracting text from photos, The Computer Vision Service
- factoring word order into predictions, Factoring Word Order into Predictions-Factoring Word Order into Predictions
- handwritten text, Building a Digit Recognition Model-Building a Digit Recognition Model, The Computer Vision Service-The Computer Vision Service
- Naive Bayes learning algorithm, Naive Bayes-Naive Bayes
- NMT as extension of (see neural machine translation)
- pretrained models for, Using Pretrained Models to Classify Text
- recommender systems, Recommender Systems-Building a Movie Recommendation System
- and RNNs, Recurrent Neural Networks (RNNs)-Recurrent Neural Networks (RNNs)
- sentiment analysis, Sentiment Analysis-Sentiment Analysis, Using TextVectorization in a Sentiment Analysis Model-Using TextVectorization in a Sentiment Analysis Model
- spam filtering, Naive Bayes-Spam Filtering
- vectorization, Preparing Text for Classification-Preparing Text for Classification, Automating Text Vectorization-Using TextVectorization in a Sentiment Analysis Model
- TextAnalyticsClient class, Calling Azure Cognitive Services APIs, The Language Service
- texts_to_sequences method, Text Preparation
- TextVectorization layer, Text Preparation, Automating Text Vectorization-Using TextVectorization in a Sentiment Analysis Model
- TF-IDF (term frequency-inverse document frequency), Preparing Text for Classification
- TfidfVectorizer class, Preparing Text for Classification, Preparing Text for Classification
- time series data, forecasting, Recurrent Neural Networks (RNNs)
- TimeDistributed wrapper, LSTM Encoder-Decoders
- Titanic passenger classification dataset, Classifying Passengers Who Sailed on the Titanic-Classifying Passengers Who Sailed on the Titanic
- TokenAndPositionEmbedding class, Building a Transformer-Based NMT Model, Building a Transformer-Based NMT Model
- tokenization, BERT, Building a BERT-Based Question Answering System-Fine-Tuning BERT to Perform Sentiment Analysis
- tokenized words, Preparing Text for Classification
- Tokenizer class, Text Preparation-Text Preparation, Automating Text Vectorization, Building a Transformer-Based NMT Model
- tokens, word, Text Preparation
- TPR (true positive rate), Accuracy Measures for Classification Models
- TPUs (tensor processing units), Deep Learning
- trainable parameters, Using a Neural Network to Predict Taxi Fares
- training set, Using k-Nearest Neighbors to Classify Flowers
- training versus validation accuracy, Dropout
- train_test_split function, Using k-Nearest Neighbors to Classify Flowers, Accuracy Measures for Regression Models-Accuracy Measures for Regression Models, Building Neural Networks with Keras and TensorFlow
- transfer learning, Building ML Models in C# with ML.NET, Transfer Learning-Using Transfer Learning to Identify Arctic Wildlife, Applying Transfer Learning to Facial Recognition-Boosting Transfer Learning with Task-Specific Weights
- transformer models, Natural Language Processing, Transformer Encoder-Decoders
- TransformerDecoder class, Building a Transformer-Based NMT Model, Building a Transformer-Based NMT Model
- TransformerEncoder class, Building a Transformer-Based NMT Model, Building a Transformer-Based NMT Model
- translate_text function, Building a Transformer-Based NMT Model
- translation (see neural machine translation)
- TranslationRecognizer object, The Speech Service
- Translator service, Introducing Azure Cognitive Services, The Translator Service-The Translator Service
- true positive rate (TPR), Accuracy Measures for Classification Models
- TSNE class, Visualizing High-Dimensional Data
- 2D to 3D space, kernel trick, Kernel Tricks-Kernel Tricks
U
- UDFs (user-defined functions), Excel, Adding Machine Learning Capabilities to Excel
- underfitting of data, Hyperparameter Tuning, Building Neural Networks with Keras and TensorFlow
- unit variance, normalizing data to, Data Normalization
- universal approximation theorem, Understanding Neural Networks
- unsupervised learning, Supervised Versus Unsupervised Learning
- UrbanSound8K dataset, Audio Classification with CNNs
- user-defined functions (UDFs), Excel, Adding Machine Learning Capabilities to Excel
V
- validation accuracy, Building Neural Networks with Keras and TensorFlow, Using a Neural Network to Predict Taxi Fares-Using a Neural Network to Predict Taxi Fares
- validation_split function, Building Neural Networks with Keras and TensorFlow, Using a Neural Network to Predict Taxi Fares, Text Classification
- vanishing gradient problem, Sizing a Neural Network
- vectorization, text, Preparing Text for Classification-Preparing Text for Classification, Automating Text Vectorization-Using TextVectorization in a Sentiment Analysis Model
- versioning pickle files, Versioning Pickle Files
- VGGFace
- Viola-Jones, face detection with, Face Detection with Viola-Jones-Using the OpenCV Implementation of Viola-Jones
- Vision services
- visualization of data
- vocabulary, word dataset, Text Preparation
W
- weak learners, Gradient-Boosting Machines
- web service, accessing Python through, Operationalizing Machine Learning Models, Consuming a Python Model from a C# Client-Consuming a Python Model from a C# Client, Using ONNX to Bridge the Language Gap
- Weibull distribution, Handling Unknown Faces: Closed-Set Versus Open-Set Classification
- weights, Understanding Neural Networks, Understanding Neural Networks, Building Neural Networks with Keras and TensorFlow, Using a Neural Network to Predict Taxi Fares, Boosting Transfer Learning with Task-Specific Weights-Boosting Transfer Learning with Task-Specific Weights
- word embeddings, Natural Language Processing, Word Embeddings-Word Embeddings, Recurrent Neural Networks (RNNs)-Recurrent Neural Networks (RNNs)
- word order, factoring into predictions, Factoring Word Order into Predictions-Factoring Word Order into Predictions
- word vectors, Natural Language Processing, Recurrent Neural Networks (RNNs)-Recurrent Neural Networks (RNNs)
- WordPiece format, Building a BERT-Based Question Answering System
- wrapping a model, Operationalizing Machine Learning Models
..................Content has been hidden....................
You can't read the all page of ebook, please click
here login for view all page.