Cover image for AI for Data Science: Artificial Intelligence Frameworks and Functionality for Deep Learning, Optimization, and Beyond

AI for Data Science: Artificial Intelligence Frameworks and Functionality for Deep Learning, Optimization, and Beyond

Author Yunus Emrah Bulut , Zacharias Voulgaris PhD
Release Date: 2018/10/01
ISBN: 9781634624114
Topic:
0%
25
Chapters
0-1
Hours read
0k
Total Words
    Start Reading Now    
       Add to Wishlist       
View table of contents

Book Description

Master the approaches and principles of Artificial Intelligence (AI) algorithms, and apply them to Data Science projects with Python and Julia code.

Aspiring and practicing Data Science and AI professionals, along with Python and Julia programmers, will practice numerous AI algorithms and develop a more holistic understanding of the field of AI, and will learn when to use each framework to tackle projects in our increasingly complex world.  

The first two chapters introduce the field, with Chapter 1 surveying Deep Learning models and Chapter 2 providing an overview of algorithms beyond Deep Learning, including Optimization, Fuzzy Logic, and Artificial Creativity.

The next chapters focus on AI frameworks; they contain data and Python and Julia code in a provided Docker, so you can practice. Chapter 3 covers Apache's MXNet, Chapter 4 covers TensorFlow, and Chapter 5 investigates Keras. After covering these Deep Learning frameworks, we explore a series of optimization frameworks, with Chapter 6 covering Particle Swarm Optimization (PSO), Chapter 7 on Genetic Algorithms (GAs), and Chapter 8 discussing Simulated Annealing (SA).

Chapter 9 begins our exploration of advanced AI methods, by covering Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). Chapter 10 discusses optimization ensembles and how they can add value to the Data Science pipeline.

Chapter 11 contains several alternative AI frameworks including Extreme Learning Machines (ELMs), Capsule Networks (CapsNets), and Fuzzy Inference Systems (FIS).

Chapter 12 covers other considerations complementary to the AI topics covered, including Big Data concepts, Data Science specialization areas, and useful data resources to experiment on.

A comprehensive glossary is included, as well as a series of appendices covering Transfer Learning, Reinforcement Learning, Autoencoder Systems, and Generative Adversarial Networks. There is also an appendix on the business aspects of AI in data science projects, and an appendix on how to use the Docker image to access the book's data and code.

The field of AI is vast, and can be overwhelming for the newcomer to approach. This book will arm you with a solid understanding of the field, plus inspire you to explore further.

Table of Contents

  1. Introduction
    1. About AI
    2. AI facilitates data science
    3. About the book
  2. Chapter 1: Deep Learning Frameworks
    1. About deep learning systems
    2. How deep learning systems work
    3. Main deep learning frameworks
    4. Main deep learning programming languages
    5. How to leverage deep learning frameworks
    6. Deep learning methodologies and applications
    7. Assessing a deep learning framework
    8. Summary
  3. Chapter 2: AI Methodologies Beyond Deep Learning
    1. Optimization
    2. Fuzzy inference systems
    3. Artificial creativity
    4. Additional AI methodologies
    5. Glimpse into the future
    6. About the methods
    7. Summary
  4. Chapter 3: Building a DL Network Using MXNet
    1. Core components
    2. MXNet in action
    3. MXNet tips
    4. Summary
  5. Chapter 4: Building a DL Network Using TensorFlow
    1. TensorFlow architecture
    2. Core components
    3. TensorFlow in action
    4. Visualization in TensorFlow: TensorBoard
    5. High level APIs in TensorFlow: Estimators
    6. Summary
  6. Chapter 5: Building a DL Network Using Keras
    1. Core components
    2. Keras in action
    3. Model Summary and Visualization
    4. Converting Keras models to TensorFlow Estimators
    5. Summary
  7. Chapter 6: Building an Optimizer Based on the Particle Swarm Optimization Algorithm
    1. PSO algorithm
    2. Main PSO variants
    3. PSO versus other optimization methods
    4. PSO implementation in Julia
    5. PSO in action
    6. PSO tips
    7. Summary
  8. Chapter 7: Building an Optimizer Based on Genetic Algorithms
    1. Standard Genetic Algorithm
    2. Implementation of GAs in Julia
    3. GAs in action
    4. Main variants of GAs
    5. GA framework tips
    6. Summary
  9. Chapter 8: Building an Optimizer Based on Simulated Annealing
    1. Pseudo-code of the Standard Simulated Annealing Algorithm
    2. Implementation of Simulated Annealing in Julia
    3. Simulated Annealing in action
    4. Main Variants of Simulated Annealing
    5. Simulated Annealing Optimizer tips
    6. Summary
  10. Chapter 9: Building an Advanced Deep Learning System
    1. Convolutional Neural Networks (CNNs)
    2. Recurrent Neural Networks
    3. Summary
  11. Chapter 10: Building an Optimization Ensemble
    1. The role of parallelization in optimization ensembles
    2. Framework of a basic optimization ensemble
    3. Case study with PSO Systems in an ensemble
    4. Case study with PSO and Firefly ensemble
    5. How optimization ensembles fit into the data science pipeline
    6. Ensemble tips
    7. Summary
  12. Chapter 11: Alternative AI Frameworks in Data Science
    1. Extreme Learning Machines (ELMs)
    2. Capsule Networks (CapsNets)
    3. Fuzzy logic and fuzzy inference systems
    4. Summary
  13. Chapter 12: Next Steps
    1. Big data
    2. Specializations in data science
    3. Publicly available datasets
    4. Summary
  14. Closing Thoughts
  15. Glossary
  16. Transfer Learning
    1. When is transfer learning useful?
    2. When to use transfer learning
    3. How to apply transfer learning
    4. Applications of transfer learning
  17. Reinforcement Learning
    1. Key terms
    2. Reward hypothesis
    3. Types of tasks
    4. Reinforcement learning frameworks
  18. Autoencoder Systems
    1. Components
    2. Extensions of conventional autoencoder models
    3. Use cases and applications
  19. Generative Adversarial Networks
    1. Components
    2. Training process
    3. Pain points of a GAN model
  20. The Business Aspect of AI in Data Science Projects
    1. Description of relevant technologies
    2. AI resources
    3. Industries and applications benefiting the most from AI
    4. Data science education for AI-related projects
  21. Using Docker Image of the Book’s Code and Data
    1. Downloading the Docker software
    2. Using Docker with an image file
    3. Docker tips
  22. Index
3.146.37.35