Book (Practical) Mathematics Fundamentals of Deep Learning Generation AI / Tsuyoshi Okadome

Product description ※Please note that product information is not in full comprehensive meaning because of the machine translation.

Mathematics
[Introduction to Contents]
This book is a deep learning textbook mainly for second - and third year undergraduate students and above.
Starting from the basics of neural networks, it aims to understand generated AI (language generation and image generation).
First, this book explains the elemental technologies of advanced and advanced deep learning, word embedding as a representative example of expression learning, and TRANSFORMERS as a network infrastructure with attention mechanism.
Regarding language generation, this book introduces a large-scale language model with a wide range of applications as a basic architecture of language processing, and introduces a language generation model as an advanced form.
Regarding image generation, this book introduces a diffusion model with a wide range of applications as a basic architecture of language processing, and also explains in detail the reinforcement learning required to sublimate a large-scale language model into a language generation model.
Regarding image generation, this book takes up a diffusion model with a remarkable development as a generation model, and also explains GAN (Generative Adversarial Network).
Finally, it explains various learning frameworks such as semi-teacher learning and learning and knowledge distillation in unbalanced data.
Chapter 1 Introduction
1.1 Fundamentals of neural networks
1.2 Matrix representation of neural networks
1.3 Development of deep learning and its factors
>
7.2 RNN Language Model
7.3 Series Conversion Model
7.4 Large Language Model
7.5 Language Generation Model
7.7 Addendum
Chapter 8 Diffusion Model
8.1 Diffusion Model Overview
8.2 Markov Process (Markov Chain)
8.3 Diffusion Model Formulation
8.4 Diffusion Model Learning
8.5 Stable diffusion : Diffusion Model Implementation
8.6 Addendum
Chapter 9 GAN : Generative Adversarial Network
9.1 Basics of GAN
9.2 Development of GAN
[Part III Deep Learning A La Carte]
Chapter 10 Data of Attention Given
10.1 Data Imbalance Between Classes
10.2 Class Label Error
Chapter 11 Framework of Diverse Learning
11.1 Distance Metric Learning
11.2 Knowledge Distillation
11.3 Semi-supervised Learning
Chapter 12 Differentiable Arithmetic Mechanism <3.1 3.2 4.1 4.2 4.3 4.4 5.1 5.2 5.3 6.1 6.2 6.3 7.1 7.6 1.4 12.1 12.2 12.3 2.1 2.2 2.3 2.4 2.5 TRANSFORMERS TRANSFORMERS TRANSFORMERS