O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Java Machine Learning for Computer Vision

Video Description

Learn machine learning by building advanced Java Computer Vision applications. Get hands-on with ML, ranging from handwriting recognition to self-driving cars

About This Video

  • Build real-world Java applications quickly using simple Neural Networks with advanced Neural Network architectures.
  • Solve the most commons obstacles in the field of Machine Learning by mastering the industry's most modern best practices.
  • Apply theory practically by building exciting applications using different Java frameworks.

In Detail

Although Machine Learning is an exciting world to explore, you may feel confused by all the theory and math out there. As a Java developer, you are used to telling the computer exactly what to do instead of being shown how data is generated; this makes many developers struggle to adapt to this new world of Machine Learning.

The goal of this course is to walk you through the process of efficiently training Deep Neural Networks for Computer Vision using the most modern techniques. The course is designed to get you familiar with Deep Neural Networks in order to be able to train them efficiently, customize existing state-of-the-art architectures, build real world Java applications, and get great results in a short time. You will build real-world Computer Vision applications, ranging from simple Java handwritten digit recognition to real-time Java autonomous car driving systems and face recognition.

By the end of the course you will have mastered the best practices and most modern techniques to build advanced Computer Vision Java applications and achieve production-grade accuracy.

The code bundle for this video course is available at: https://github.com/PacktPublishing/Java-Machine-Learning-for-Computer-Vision

Table of Contents

  1. Chapter 1 : Introduction to Computer Vision and Training Neural Networks
    1. The Course Overview 00:04:01
    2. Computer Vision State 00:05:39
    3. Exploring Neural Network 00:07:05
    4. How Is Neural Network Learning? 00:13:48
    5. Organizing Your Data and Application 00:08:07
    6. Effective Training Techniques 00:09:22
    7. Optimization Algorithms 00:11:50
    8. Neural Network Training Parameters 00:09:17
    9. Images and Outputs Representations 00:08:15
    10. Build a Handwritten Digit Recognizer with 97% Accuracy 00:07:48
  2. Chapter 2 : Convolution Neural Network Architectures
    1. Understanding Edge Detection 00:10:30
    2. Java Edge Detection Application 00:08:32
    3. Convolution on Colored RGB Images 00:05:18
    4. Working with Convolutional Layers Parameters 00:06:05
    5. Pooling Layers 00:06:30
    6. Building and Training Convolutional Neural Network 00:07:17
    7. Improve Handwritten Digit Recognition Application (With 99.95% Accuracy) 00:09:15
  3. Chapter 3 : Transfer Learning and Deep CNN Architectures
    1. Working with Classical Networks 00:10:46
    2. Using Residual Networks for Image Recognition 00:06:39
    3. The Power of 1x1 Convolution and Inception Network 00:08:43
    4. Applying Transfer Learning 00:08:45
    5. Building Animal Image Classification (Using Transfer Learning and VGG-16 Architecture) 00:09:42
  4. Chapter 4 : Real Time Object Detection
    1. Resolving Object Localization Problem 00:09:02
    2. Object Detection with Sliding Window Solution 00:05:47
    3. Convolution Sliding Window 00:10:01
    4. Detecting Objects with YOLO Algorithm 00:09:05
    5. Max Suppression and Anchor Boxes 00:07:26
    6. Build a Java Real Time Video Car and Pedestrians Detection Application 00:10:06
  5. Chapter 5 : Creating Art with Neural Style Transfer
    1. What Are Convolution Network Layers Learning? 00:05:41
    2. Neural Style Transfer 00:05:11
    3. Applying Content Cost Function 00:05:16
    4. Applying Style Cost Function 00:11:51
    5. Build a Neural Network Which Produces Art 00:12:29
  6. Chapter 6 : Face Recognition
    1. Problems in Face Detection 00:06:35
    2. Differentiating Inputs with Siamese Networks 00:04:12
    3. Exploring Triplet Loss 00:09:05
    4. Binary Classification 00:03:51
    5. Build Face Recognition Java Application 00:07:32