Artificial Intelligence Frameworks and Functionality for Deep Learning, Optimization


Artificial Intelligence Frameworks and Functionality for Deep Learning, Optimization


Artificial Intelligence Framework

    There is no doubt that Artificial Intelligence (commonly abbreviated AI) is making waves these days, perhaps more than the world anticipated as recently as the mid-2010s. Back then, AI was an esoteric topic that was too math-heavy to attract the average computer scientist, but now, it seems to be a household term. While it was once considered sci-fi lingo, it’s now common to see and hear the term “AI” featured in ads about consumer products like smart phones.


    This is to be expected, though; once an idea or technology reaches critical mass, it naturally becomes more acceptable to a wider audience, even if just on the application level. This level refers to what AI can do for us, by facilitating certain processes, or automating others. However, all this often gives rise to a series of misunderstandings. As AI itself has become more well-known, so have spread various ominous predictions about potential dangers of AI  predictions that are fueled by fear and fantasy, rather than fact.


Table of content

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

Download full PDF in Comment section



Previous Post Next Post