Python Deep Learning : Understand How Deep Neural Networks Work and Apply Them to Real-World Tasks / Ivan Vasilev.

Format:

Book

Author/Creator:

Vasilev, Ivan, 1909-1969, author.

Language:

English

Subjects (All):

Python (Computer program language).

Machine learning.

Neural networks (Computer science).

Physical Description:

1 online resource (362 pages)

Edition:

Third edition.

Place of Publication:

Birmingham, England : Packt Publishing Ltd., [2023]

System Details:

Mode of access: World Wide Web.

Biography/History:

Vasilev Ivan: Ivan Vasilev started working on the first open source Java deep learning library with GPU support in 2013. The library was acquired by a German company, with whom he continued its development. He has also worked as a machine learning engineer and researcher in medical image classification and segmentation with deep neural networks. Since 2017, he has focused on financial machine learning. He co-founded an algorithmic trading company, where he's the lead engineer. He holds an MSc in artificial intelligence from Sofia University St. Kliment Ohridski and has written two previous books on the same topic.

Summary:

Master effective navigation of neural networks, including convolutions and transformers, to tackle computer vision and NLP tasks using Python Key Features Understand the theory, mathematical foundations and the structure of deep neural networks Become familiar with transformers, large language models, and convolutional networks Learn how to apply them on various computer vision and natural language processing problems Purchase of the print or Kindle book includes a free PDF eBook Book Description The field of deep learning has developed rapidly recently and today covers a broad range of applications. This makes it challenging to navigate and hard to understand without solid foundations. This book will guide you from the basics of neural networks to the state-of-the-art large language models in use today. The first part of the book introduces the main machine learning concepts and paradigms. It covers the mathematical foundations, the structure, and the training algorithms of neural networks and dives into the essence of deep learning. The second part of the book introduces convolutional networks for computer vision. We'll learn how to solve image classification, object detection, instance segmentation, and image generation tasks. The third part focuses on the attention mechanism and transformers - the core network architecture of large language models. We'll discuss new types of advanced tasks they can solve, such as chatbots and text-to-image generation. By the end of this book, you'll have a thorough understanding of the inner workings of deep neural networks. You'll have the ability to develop new models and adapt existing ones to solve your tasks. You'll also have sufficient understanding to continue your research and stay up to date with the latest advancements in the field. What you will learn Establish theoretical foundations of deep neural networks Understand convolutional networks and apply them in computer vision applications Become well versed with natural language processing and recurrent networks Explore the attention mechanism and transformers Apply transformers and large language models for natural language and computer vision Implement coding examples with PyTorch, Keras, and Hugging Face Transformers Use MLOps to develop and deploy neural network models Who this book is for This book is for software developers/engineers, students, data scientists, data analysts, machine learning engineers, statisticians, and anyone interested in deep learning. Prior experience with Python programming is a prerequisite.

Contents:

Cover

Title Page

Copyright and Credit

Contributors

Table of Contents

Preface

Part 1: Introduction to Neural Networks

Chapter 1: Machine Learning - an Introduction

Technical requirements

Introduction to ML

Different ML approaches

Supervised learning

Unsupervised learning

Reinforcement learning

Components of an ML solution

Neural networks

Introducing PyTorch

Summary

Chapter 2: Neural Networks

The need for NNs

The math of NNs

Linear algebra

An introduction to probability

Differential calculus

An introduction to NNs

Units - the smallest NN building block

Layers as operations

Multi-layer NNs

Activation functions

The universal approximation theorem

Training NNs

GD

Backpropagation

A code example of an NN for the XOR function

Chapter 3: Deep Learning Fundamentals

Introduction to DL

Fundamental DL concepts

Feature learning

The reasons for DL's popularity

Deep neural networks

Training deep neural networks

Improved activation functions

DNN regularization

Applications of DL

Introducing popular DL libraries

Classifying digits with Keras

Classifying digits with PyTorch

Part 2: Deep Neural Networks for Computer Vision

Chapter 4: Computer Vision with Convolutional Networks

Intuition and justification for CNNs

Convolutional layers

A coding example of the convolution operation

Cross-channel and depthwise convolutions

Stride and padding in convolutional layers

Pooling layers

The structure of a convolutional network

Classifying images with PyTorch and Keras

Convolutional layers in deep learning libraries

Data augmentation

Classifying images with PyTorch

Classifying images with Keras.

Advanced types of convolutions

1D, 2D, and 3D convolutions

1×1 convolutions

Depthwise separable convolutions

Dilated convolutions

Transposed convolutions

Advanced CNN models

Introducing residual networks

Inception networks

Introducing Xception

Squeeze-and-Excitation Networks

Introducing MobileNet

EfficientNet

Using pre-trained models with PyTorch and Keras

Chapter 5: Advanced Computer Vision Applications

Transfer learning (TL)

Transfer learning with PyTorch

Transfer learning with Keras

Object detection

Approaches to object detection

Object detection with YOLO

Object detection with Faster R-CNN

Introducing image segmentation

Semantic segmentation with U-Net

Instance segmentation with Mask R-CNN

Image generation with diffusion models

Introducing generative models

Denoising Diffusion Probabilistic Models

Part 3: Natural Language Processing and Transformers

Chapter 6: Natural Language Processing and Recurrent Neural Networks

Natural language processing

Tokenization

Introducing word embeddings

Word2Vec

Visualizing embedding vectors

Language modeling

Introducing RNNs

RNN implementation and training

Backpropagation through time

Vanishing and exploding gradients

Long-short term memory

Gated recurrent units

Implementing text classification

Chapter 7: The Attention Mechanism and Transformers

Introducing seq2seq models

Understanding the attention mechanism

Bahdanau attention

Luong attention

General attention

Transformer attention

Implementing TA

Building transformers with attention

Transformer encoder

Transformer decoder

Putting it all together

Decoder-only and encoder-only models.

Bidirectional Encoder Representations from Transformers

Generative Pre-trained Transformer

Chapter 8: Exploring Large Language Models in Depth

Introducing LLMs

LLM architecture

LLM attention variants

Prefix decoder

Transformer nuts and bolts

Models

Training LLMs

Training datasets

Pre-training properties

FT with RLHF

Emergent abilities of LLMs

Introducing Hugging Face Transformers

Chapter 9: Advanced Applications of Large Language Models

Classifying images with Vision Transformer

Using ViT with Hugging Face Transformers

Understanding the DEtection TRansformer

Using DetR with Hugging Face Transformers

Generating images with stable diffusion

Autoencoder

Conditioning transformer

Diffusion model

Using stable diffusion with Hugging Face Transformers

Exploring fine-tuning transformers

Harnessing the power of LLMs with LangChain

Using LangChain in practice

Part 4: Developing and Deploying Deep Neural Networks

Chapter 10: Machine Learning Operations (MLOps)

Understanding model development

Choosing an NN framework

PyTorch versus TensorFlow versus JAX

Open Neural Network Exchange

Introducing TensorBoard

Developing NN models for edge devices with TF Lite

Mixed-precision training with PyTorch

Exploring model deployment

Deploying NN models with Flask

Building ML web apps with Gradio

Index

Other Books You May Enjoy.

Notes:

Includes index.

Includes bibliographical references and index.

Description based on print version record.

ISBN:

1-83763-345-2

OCLC:

1410900597