Cover image for Codeless Deep Learning with KNIME

Codeless Deep Learning with KNIME

Release Date: 2020/11/01
ISBN: 9781800566613
Topic:
0%
19
Chapters
0-1
Hours read
0k
Total Words
    Start Reading Now    
       Add to Wishlist       
View table of contents

Discover how to integrate KNIME Analytics Platform with deep learning libraries to implement artificial intelligence solutions

Key Features

  • Become well-versed with KNIME Analytics Platform to perform codeless deep learning
  • Design and build deep learning workflows quickly and more easily using the KNIME GUI
  • Discover different deployment options without using a single line of code with KNIME Analytics Platform

Book Description

KNIME Analytics Platform is an open source software used to create and design data science workflows. This book is a comprehensive guide to the KNIME GUI and KNIME deep learning integration, helping you build neural network models without writing any code. It'll guide you in building simple and complex neural networks through practical and creative solutions for solving real-world data problems.

Starting with an introduction to KNIME Analytics Platform, you'll get an overview of simple feed-forward networks for solving simple classification problems on relatively small datasets. You'll then move on to build, train, test, and deploy more complex networks, such as autoencoders, recurrent neural networks (RNNs), long short-term memory (LSTM), and convolutional neural networks (CNNs). In each chapter, depending on the network and use case, you'll learn how to prepare data, encode incoming data, and apply best practices.

By the end of this book, you'll have learned how to design a variety of different neural architectures and will be able to train, test, and deploy the final network.

What you will learn

  • Use various common nodes to transform your data into the right structure suitable for training a neural network
  • Understand neural network techniques such as loss functions, backpropagation, and hyperparameters
  • Prepare and encode data appropriately to feed it into the network
  • Build and train a classic feedforward network
  • Develop and optimize an autoencoder network for outlier detection
  • Implement deep learning networks such as CNNs, RNNs, and LSTM with the help of practical examples
  • Deploy a trained deep learning network on real-world data

Who this book is for

This book is for data analysts, data scientists, and deep learning developers who are not well-versed in Python but want to learn how to use KNIME GUI to build, train, test, and deploy neural networks with different architectures. The practical implementations shown in the book do not require coding or any knowledge of dedicated scripts, so you can easily implement your knowledge into practical applications. No prior experience of using KNIME is required to get started with this book.

Table of Contents

  1. Codeless Deep Learning with KNIME
  2. Why subscribe?
  3. Contributors
  4. About the authors
  5. About the reviewers
  6. Packt is searching for authors like you
  7. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
    4. Download the example workflows
    5. Download the color images
    6. Conventions used
    7. Get in touch
    8. Reviews
  8. Section 1: Feedforward Neural Networks and KNIME Deep Learning Extension
  9. Chapter 1: Introduction to Deep Learning with KNIME Analytics Platform
    1. The Importance of Deep Learning
    2. Exploring KNIME Software
    3. KNIME Analytics Platform
    4. KNIME Server for the Enterprise
    5. Exploring KNIME Analytics Platform
    6. Useful Links and Materials
    7. Build and Execute Your First Workflow
    8. Installing KNIME Deep Learning – Keras Integration
    9. Installing the Keras and TensorFlow Nodes
    10. Setting up the Python Environment
    11. Goal and Structure of this Book
    12. Summary
  10. Chapter 2: Data Access and Preprocessing with KNIME Analytics Platform
    1. Accessing Data
    2. Reading Data from Files
    3. Data Types and Conversions
    4. Transforming Data
    5. Parameterizing the Workflow
    6. Summary
    7. Questions and Exercises
  11. Chapter 3: Getting Started with Neural Networks
    1. Neural Networks and Deep Learning – Basic Concepts
    2. Artificial Neuron and Artificial Neural Networks
    3. Signal Propagation within a Feedforward Neural Network
    4. Understanding the Need for Hidden Layers
    5. Training a Multilayer Perceptron
    6. Designing your Network
    7. Commonly Used Activation Functions
    8. Regularization Techniques to Avoid Overfitting
    9. Other Commonly used Layers
    10. Training a Neural Network
    11. Loss Functions
    12. Parameters and Optimization of the Training Algorithm
    13. Summary
    14. Questions and Exercises
  12. Chapter 4: Building and Training a Feedforward Neural Network
    1. Preparing the Data
    2. Datasets and Classification Examples
    3. Encoding of Nominal Features
    4. Normalization
    5. Other Helpful Preprocessing Nodes
    6. Data Preparation on the Iris Dataset
    7. Data Preparation on the Adult Dataset
    8. Building a Feedforward Neural Architecture
    9. The Keras Input Layer Node
    10. The Keras Dense Layer Node
    11. Building a Neural Network for Iris Flower Classification
    12. Building a Neural Network for Income Prediction
    13. Training the Network
    14. Selecting the Loss Function
    15. Defining the Input and Output Data
    16. Setting the Training Parameters
    17. Tracking the Training Progress
    18. Training Settings for Iris Flower Classification
    19. Training Settings for Income Prediction
    20. Testing and Applying the Network
    21. Executing the Network
    22. Extracting the Predictions and Evaluating the Network Performance
    23. Testing the Network Trained to Classify Iris Flowers
    24. Testing the Network Trained for Income Prediction
    25. Summary
    26. Questions and Exercises
  13. Section 2: Deep Learning Networks
  14. Chapter 5: Autoencoder for Fraud Detection
    1. Introducing Autoencoders
    2. Architecture of the Autoencoder
    3. Reducing the Input Dimensionality with an Autoencoder
    4. Detecting Anomalies Using an Autoencoder
    5. Why is Detecting Fraud so Hard?
    6. Building and Training the Autoencoder
    7. Data Access and Data Preparation
    8. Building the Autoencoder
    9. Training and Testing the Autoencoder
    10. Detecting Fraudulent Transactions
    11. Optimizing the Autoencoder Strategy
    12. Optimizing Threshold
    13. Threshold is defined on a separate subset of data, called the optimization set. There are two options here:
    14. Deploying the Fraud Detector
    15. Reading Network, New Transactions, and Normalization Parameters
    16. Applying the Fraud Detector
    17. Taking Actions
    18. Summary
    19. Questions and Exercises
  15. Chapter 6: Recurrent Neural Networks for Demand Prediction
    1. Introducing RNNs
    2. Recurrent Neural Networks
    3. Recurrent Neural Units
    4. Long Short-Term Memory
    5. The Demand Prediction Problem
    6. Demand Prediction
    7. Predicting Energy Demand
    8. Data Preparation – Creating the Past
    9. Data Loading and Standardization
    10. Data Cleaning and Partitioning
    11. Creating the Input Tensors
    12. Building, Training, and Deploying an LSTM-Based RNN
    13. Building the LSTM-Based RNN
    14. Training the LSTM-Based RNN
    15. Testing the LSTM-Based RNN
    16. Building a Deployment Loop
    17. Deploying the LSTM-Based RNN
    18. Summary
    19. Questions and Exercises
  16. Chapter 7: Implementing NLP Applications
    1. Exploring Text Encoding Techniques for Neural Networks
    2. Index Encoding
    3. One-Hot Vector Encoding
    4. Embeddings for Word Encoding
    5. Finding the Tone of Your Customers' Voice – Sentiment Analysis
    6. Preprocessing Movie Reviews
    7. Defining and Training the Network Architecture
    8. Executing and Evaluating the Network on the Test Set
    9. Generating Free Text with RNNs
    10. The Dataset
    11. Predicting Words or Characters?
    12. Preprocessing and Encoding
    13. Defining and Training the Network Architecture
    14. Building a Deployment Workflow
    15. The New Fairy Tale
    16. Generating Product Names with RNNs
    17. The Problem of Product Name Generation
    18. Preprocessing and Encoding Mountain Names
    19. Defining and Training the Network Architecture
    20. Building a Deployment Workflow
    21. Summary
    22. Questions and Exercises
  17. Chapter 8: Neural Machine Translation
    1. Idea of Neural Machine Translation
    2. Encoder-Decoder Architecture
    3. Applying the Encoder
    4. Applying the Decoder during Training
    5. Applying the Decoder during Deployment
    6. Preparing the Data for the Two Languages
    7. Building and Training the Encoder-Decoder Architecture
    8. Defining the Network Structure
    9. Training the Network
    10. Extracting the Trained Encoder and Decoder
    11. Applying the Trained Network for Neural Machine Translation
    12. Summary
    13. Questions and Exercises
  18. Chapter 9: Convolutional Neural Networks for Image Classification
    1. Introduction to CNNs
    2. How are Images Stored?
    3. Why do we need CNNs?
    4. How does a Convolution Layer work?
    5. Introducing Padding
    6. Introducing Stride and Dilation Rate
    7. Introducing Pooling
    8. Classifying Images with CNNs
    9. Reading and Preprocessing Images
    10. Designing the Network
    11. Training and Applying the Network
    12. Prediction Extraction and Model Evaluation
    13. Introduction to transfer learning
    14. Why use Transfer Learning?
    15. Formal Definition of Transfer Learning
    16. Applying Transfer Learning
    17. Applying Transfer Learning for Cancer Type Prediction
    18. Downloading the Dataset
    19. Reading and Preprocessing the Images
    20. Training the Network
    21. Summary
    22. Questions and Exercises
  19. Section 3: Deployment and Productionizing
  20. Chapter 10: Deploying a Deep Learning Network
    1. Conversion of the Network Structure
    2. Saving a Trained Network
    3. Reading a Trained Network
    4. Using TensorFlow 2
    5. Building a Simple Deployment Workflow
    6. Building a Deployment Workflow Manually, without Integrated Deployment
    7. Building a Deployment Workflow Automatically with Integrated Deployment
    8. Improving Scalability – GPU Execution
    9. Summary
    10. Questions and Exercises
  21. Chapter 11: Best Practices and Other Deployment Options
    1. Building a Web Application
    2. Introduction to KNIME WebPortal
    3. Creating a Workflow to Run on KNIME WebPortal
    4. Creating Composite Views
    5. Shared Components
    6. Building a WebPortal Application for Cancer Cell Classification
    7. Building a Web Service with the REST Interface
    8. Building a REST Service Workflow
    9. KNIME Tips and Tricks
    10. Shuffling Data during Training
    11. Using Batch Normalization
    12. Keeping Your Workflow Clean and Structured
    13. Using the GroupBy Node and Pivoting Node to Avoid Loops
    14. Specifying the Execution Order
    15. Summary
    16. Questions and Exercises
  22. Other Books You May Enjoy
    1. Leave a review - let other readers know what you think
18.221.129.19