Deep Learning for Beginners 2: Implementing Recurrent Neural Networks, VAE, and GAN (Machine Learning) in Python

This is the second installment of a series on the fundamentals of deep learning, taught by a popular instructor on the online education platform Udemy. The previous book, "Deep Learning for Beginners," explained the most basic of basics: neural networks and backpropagation, in an easy-to-understand manner even for beginners. This book explains recurrent neural networks (RNNs), which are highly valuable in the field of natural language processing, as well as the generative deep learning models VAE (Variational Autoencoder) and GAN (Generative Adversarial Networks), including implementation methods. Following the previous book, the program implementation is done entirely in Python, without relying on existing frameworks.

[Book Features] - For those who haven't read the previous book, there are chapters explaining the basics of Python, mathematics, and neural networks. - The sample programs are written entirely in Python, without using any frameworks. This makes the principles of coding mathematical formulas easy to understand, even for beginners. - The sample programs can be downloaded from the SB Creative Corporation website. Compatible with Python 3, Jupyter Notebook, and Google Colaboratory

Chapter 1: The Development of Deep Learning Overview of Deep Learning Applications of Deep Learning Technologies Covered in This Book How to Use This Book

Chapter 2: Preparation for Learning Setting Up an Anaconda Environment How to Use Google Colaboratory How to Use Jupyter Notebook Python Basics NumPy and matplotlib Basic Mathematics

Chapter 3: Deep Learning Basics Overview of Neural Networks and Deep Learning Forward Propagation through Fully Connected Layers Backpropagation through Fully Connected Layers Implementing a Fully Connected Layer Simple Deep Learning Implementation

Chapter 4: RNN Overview of RNNs Forward Propagation through RNN Layers Backpropagation through RNN Layers Implementing an RNN Layer Simple RNN Implementation Problems Facing RNNs

Chapter 5: LSTM Overview of LSTMs Forward Propagation through LSTM Layers Backpropagation through LSTM Layers Implementing an LSTM Layer Simple LSTM Implementation Automatic Text Generation

Chapter 6: GRU Overview of GRU Forward Propagation of GRU Layer Backward Propagation of GRU Layer Implementation of GRU Layer Simple GRU Implementation Encoder-Decoder

Chapter 7: VAE Overview of VAE How VAE Works Implementing Autoencoders Layers Required for VAE Implementing VAE VAE Derivatives Chapter 8: GAN Overview of GAN How GAN Works Layers Required for GAN Implementing GAN GAN Derivatives