
Deep Learning on the JVM
Build a Document Intelligence Platform with JVM Deep LearningBy Sofia HalloranLength7h 31m
About this audiobook
Java deep learning build neural networks Java JVM machine learning If you're a Java developer ready to dive into AI without leaving your familiar ecosystem, this book is your hands-on guide. From tensors and layers to training loops and deployment, you'll learn to build and ship production-ready deep learning models entirely on the JVM. No Python required.
Start with the fundamentals: tensors, automatic differentiation, and the core building blocks of neural networks. Progress through hands-on chapters that teach you to construct layers, implement forward and backward passes, and write custom training loops. You'll master key concepts like activation functions, loss functions, optimizers, and regularization—all in Java. The book then moves to advanced topics: convolutional networks for image data, recurrent networks for sequences, and attention mechanisms. Each chapter includes complete code examples you can run immediately.
Deployment is a first-class concern. You'll learn to export models, integrate with Spring Boot, serve predictions via REST APIs, and optimize for performance using JVM profiling tools. Real-world case studies show you how to apply deep learning to recommendation systems, anomaly detection, and natural language processing—all within your existing Java stack. By the end, you'll be able to design, train, evaluate, and deploy neural networks that solve practical business problems.
Who this book is for: Java developers, data engineers, and software architects who want to add deep learning to their toolkit without learning a new language. Prior machine learning experience is helpful but not required. The book assumes you're comfortable with Java 11+ and basic OOP concepts.
Competitor books like Machine Learning System Design Interview and Building LLMs for Production cover system design or LLM-specific topics, but none focus on hands-on JVM deep learning from scratch. This book fills that gap—giving you the code, the theory, and the deployment know-how to build neural networks in Java.
Audiobook details
GenreTechnology
Length7 hrs 31 mins
Narrated byListen with 1,000+ voices
FormateBook with Audio
LanguageEnglish
Table of contents
1Preface
2Chapter 1 — Why Deep Learning in Java? Setting Up the JVM for AI
3Chapter 2 — Project Kickoff: The Document Intelligence Platform
4Chapter 3 — Neural Network Fundamentals: From Perceptrons to Multi-Layer Networks
5Chapter 4 — Activation Functions, Loss Functions, and Optimization in Java
Show all chaptersShow less
6Chapter 5 — Backpropagation Step-by-Step and Custom Training Loops
7Chapter 6 — Data Preparation: Handling Images, Text, and Time Series with DataVec
8Chapter 7 — Building a Document Classifier with Convolutional Neural Networks
9Chapter 8 — Advanced CNNs: Transfer Learning for Document Layout Analysis
10Chapter 9 — Recurrent Neural Networks: Text Sequence Modeling for Document Summaries
11Chapter 10 — LSTM Networks: Long-Document Understanding and Question Answering
12Chapter 11 — GRUs: Efficient Sequence Modeling for Real-Time Document Processing
13Chapter 12 — Hybrid Models: Combining CNNs and RNNs for Full Document Understanding
14Chapter 13 — Attention Mechanisms and Transformer Encoders in Java
15Chapter 14 — Model Evaluation, Hyperparameter Tuning, and Regularization Techniques
16Chapter 15 — Scaling with Apache Spark and GPU Training on the JVM
17Chapter 16 — Model Export, ONNX, and Deployment as a Microservice
18Chapter 17 — Monitoring, A/B Testing, and Continuous Learning
19Chapter 18 — Final Integration: End-to-End Document Intelligence Platform with Full-Stack
20About the Author