Deep Learning Essentials with PyTorch
 |
Description
Book Introduction
From neural networks to transformers with PyTorch,
We will practice various applications, optimizations, and distributions.
Master practical deep learning!
Artificial intelligence technology has been advancing at an astonishing pace, and deep learning is at the heart of this development. In particular, PyTorch, a deep learning framework beloved by both researchers and practitioners, is widely used in education and research thanks to its intuitive structure and design.
"Deep Learning Essentials with PyTorch" was written with a wide range of readers in mind, from undergraduate and graduate students learning deep learning for the first time to non-majors who want to learn about artificial intelligence in the field.
In particular, this book is not limited to theory, but is structured to allow readers to acquire concepts through hands-on implementation and experimentation with models through a practice-oriented approach.
Rather than simply memorizing code, we focus on the question, “Why is it designed this way?” to help you understand the principles.
Now, with "Deep Learning Essentials with PyTorch," you can solidify your foundation in deep learning with PyTorch, no longer confined to a specific field of expertise, and take on the challenge of creative AI applications.
We will practice various applications, optimizations, and distributions.
Master practical deep learning!
Artificial intelligence technology has been advancing at an astonishing pace, and deep learning is at the heart of this development. In particular, PyTorch, a deep learning framework beloved by both researchers and practitioners, is widely used in education and research thanks to its intuitive structure and design.
"Deep Learning Essentials with PyTorch" was written with a wide range of readers in mind, from undergraduate and graduate students learning deep learning for the first time to non-majors who want to learn about artificial intelligence in the field.
In particular, this book is not limited to theory, but is structured to allow readers to acquire concepts through hands-on implementation and experimentation with models through a practice-oriented approach.
Rather than simply memorizing code, we focus on the question, “Why is it designed this way?” to help you understand the principles.
Now, with "Deep Learning Essentials with PyTorch," you can solidify your foundation in deep learning with PyTorch, no longer confined to a specific field of expertise, and take on the challenge of creative AI applications.
- You can preview some of the book's contents.
Preview
index
Chapter 1 | Introduction and Installation of PyTorch
1.1 PyTorch Overview and History
1.2 Key Features and Benefits of PyTorch
1.3 Setting up the development environment - Google Colab-focused
1.4 Installing PyTorch and Running Your First Code (Colab)
Practice problems
Chapter 2 | Basic PyTorch Operations
2.1 Tensor concept and creation
2.2 Basic Tensor Operations
2.3 Comparing Tensors and NumPy Arrays
2.4 GPU Utilization of Tensors
2.5 Comprehensive Practice Example
Practice problems
Chapter 3 | Neural Network Implementation
3.1 Overview of Neural Networks
3.2 Understanding the basic neural network structure
3.3 Neural network learning process
3.4 Implementing a Neural Network Using PyTorch
3.5 MNIST Classifier Practice
3.6 Model Evaluation and Improvement
Practice problems
Chapter 4 | Building a Deep Learning Model
4.1 Understanding the Model Training Process Using PyTorch
4.2 Data Preprocessing and DataLoader Utilization
4.3 Model Performance Evaluation and Improvement
Practice problems
Chapter 5 | Convolutional Neural Networks (CNNs)
5.1 Basic concepts and structure of convolutional neural networks
5.2 Key Components of a Convolutional Neural Network
5.3 Advanced Convolutional Neural Network Architectures
5.4 ResNet structure
5.5 Performance Optimization of Convolutional Neural Networks
5.6 Visualizing and Interpreting Convolutional Neural Networks
Practice problems
Chapter 6 | Recurrent Neural Networks (RNNs)
6.1 Basics of Recurrent Neural Networks
6.2 Advanced Recurrent Neural Network Architecture
6.3 Implementing a Recurrent Neural Network Using PyTorch
6.4 Implementing a Recurrent Neural Network Using PyTorch
6.5 Natural Language Processing Applications
6.6 Tuning Recurrent Neural Network Hyperparameters
6.7 Practical Applications and Optimization of Recurrent Neural Networks
Practice problems
Chapter 7 | Transformers and Transfer Learning
7.1 Understanding Transformer Structure
7.2 Integrating Pre-trained Models with Transfer Learning
7.3 Overview of Natural Language Processing and Vision Transformer
Practice problems
Chapter 8 | Image Processing Applications
8.1 Key Challenges in Computer Vision
8.2 ResNet Implementation and Utilization
8.3 Implementing the Object Detection Model
8.4 Segmentation Practice
8.5 Advanced Application Techniques
8.6 Practical Application Examples
Practice problems
Chapter 9 | Text Processing Applications and Deep Learning for LSTM Sentiment Analyzers
9.1 Implementing and Training a Natural Language Processing Model
9.2 LSTM and Sentiment Analyzer Practice
9.3 Additional Practice
9.4 Model Evaluation and Performance Improvement
Practice problems
Chapter 10 | Audio Processing Applications
10.1 Audio Signal Processing Fundamentals
10.2 Audio Processing with PyTorch
10.3 WaveNet Model Implementation
Practice problems
Chapter 11 | Reinforcement Learning
11.1 Basic Concepts of Reinforcement Learning
11.2 DQN (Deep Q-Network) Implementation
11.3 Applying the Policy Gradient Technique
11.4 Utilizing Various Reinforcement Learning Environments
11.5 Model Evaluation and Performance Improvement
Practice problems
Chapter 12 | Model Performance Optimization and Deployment
12.1 Fundamentals of Model Optimization and Performance Analysis
12.2 Model lightweighting techniques
12.3 Model Conversion and Service Deployment
12.4 Monitoring and Maintenance
Practice problems
1.1 PyTorch Overview and History
1.2 Key Features and Benefits of PyTorch
1.3 Setting up the development environment - Google Colab-focused
1.4 Installing PyTorch and Running Your First Code (Colab)
Practice problems
Chapter 2 | Basic PyTorch Operations
2.1 Tensor concept and creation
2.2 Basic Tensor Operations
2.3 Comparing Tensors and NumPy Arrays
2.4 GPU Utilization of Tensors
2.5 Comprehensive Practice Example
Practice problems
Chapter 3 | Neural Network Implementation
3.1 Overview of Neural Networks
3.2 Understanding the basic neural network structure
3.3 Neural network learning process
3.4 Implementing a Neural Network Using PyTorch
3.5 MNIST Classifier Practice
3.6 Model Evaluation and Improvement
Practice problems
Chapter 4 | Building a Deep Learning Model
4.1 Understanding the Model Training Process Using PyTorch
4.2 Data Preprocessing and DataLoader Utilization
4.3 Model Performance Evaluation and Improvement
Practice problems
Chapter 5 | Convolutional Neural Networks (CNNs)
5.1 Basic concepts and structure of convolutional neural networks
5.2 Key Components of a Convolutional Neural Network
5.3 Advanced Convolutional Neural Network Architectures
5.4 ResNet structure
5.5 Performance Optimization of Convolutional Neural Networks
5.6 Visualizing and Interpreting Convolutional Neural Networks
Practice problems
Chapter 6 | Recurrent Neural Networks (RNNs)
6.1 Basics of Recurrent Neural Networks
6.2 Advanced Recurrent Neural Network Architecture
6.3 Implementing a Recurrent Neural Network Using PyTorch
6.4 Implementing a Recurrent Neural Network Using PyTorch
6.5 Natural Language Processing Applications
6.6 Tuning Recurrent Neural Network Hyperparameters
6.7 Practical Applications and Optimization of Recurrent Neural Networks
Practice problems
Chapter 7 | Transformers and Transfer Learning
7.1 Understanding Transformer Structure
7.2 Integrating Pre-trained Models with Transfer Learning
7.3 Overview of Natural Language Processing and Vision Transformer
Practice problems
Chapter 8 | Image Processing Applications
8.1 Key Challenges in Computer Vision
8.2 ResNet Implementation and Utilization
8.3 Implementing the Object Detection Model
8.4 Segmentation Practice
8.5 Advanced Application Techniques
8.6 Practical Application Examples
Practice problems
Chapter 9 | Text Processing Applications and Deep Learning for LSTM Sentiment Analyzers
9.1 Implementing and Training a Natural Language Processing Model
9.2 LSTM and Sentiment Analyzer Practice
9.3 Additional Practice
9.4 Model Evaluation and Performance Improvement
Practice problems
Chapter 10 | Audio Processing Applications
10.1 Audio Signal Processing Fundamentals
10.2 Audio Processing with PyTorch
10.3 WaveNet Model Implementation
Practice problems
Chapter 11 | Reinforcement Learning
11.1 Basic Concepts of Reinforcement Learning
11.2 DQN (Deep Q-Network) Implementation
11.3 Applying the Policy Gradient Technique
11.4 Utilizing Various Reinforcement Learning Environments
11.5 Model Evaluation and Performance Improvement
Practice problems
Chapter 12 | Model Performance Optimization and Deployment
12.1 Fundamentals of Model Optimization and Performance Analysis
12.2 Model lightweighting techniques
12.3 Model Conversion and Service Deployment
12.4 Monitoring and Maintenance
Practice problems
Detailed image
Publisher's Review
PyTorch Deep Learning: Learn Through Practice
From concepts to the latest models and practical projects, all in one book.
Starting from the basics of PyTorch, it is designed to systematically learn core concepts by implementing various deep learning models such as neural networks, CNNs, RNNs, and transformers.
You'll learn practical project-based learning across a wide range of application areas, including video, text, audio, and reinforcement learning, and develop a broad range of practical skills, from model optimization to deployment techniques.
This hands-on approach goes beyond theory and provides a deep understanding of "why things work this way," making it easy for anyone to get started with deep learning.
STEP 1 - Basics
STEP 2 - Building a Deep Learning Model
STEP 3 - Deep Learning Advancement
STEP 4 - Optimization and Deployment
STEP 5 - Various Deep Learning Applications
From concepts to the latest models and practical projects, all in one book.
Starting from the basics of PyTorch, it is designed to systematically learn core concepts by implementing various deep learning models such as neural networks, CNNs, RNNs, and transformers.
You'll learn practical project-based learning across a wide range of application areas, including video, text, audio, and reinforcement learning, and develop a broad range of practical skills, from model optimization to deployment techniques.
This hands-on approach goes beyond theory and provides a deep understanding of "why things work this way," making it easy for anyone to get started with deep learning.
STEP 1 - Basics
STEP 2 - Building a Deep Learning Model
STEP 3 - Deep Learning Advancement
STEP 4 - Optimization and Deployment
STEP 5 - Various Deep Learning Applications
GOODS SPECIFICS
- Date of issue: September 30, 2025
- Page count, weight, size: 536 pages | 183*235*22mm
- ISBN13: 9791140715206
You may also like
카테고리
korean
korean
![ELLE 엘르 스페셜 에디션 A형 : 12월 [2025]](http://librairie.coreenne.fr/cdn/shop/files/b8e27a3de6c9538896439686c6b0e8fb.jpg?v=1766436872&width=3840)
