Create a Neural Network in Java

Create a Neural Network in Java, available at $69.99, has an average rating of 4.4, with 196 lectures, based on 93 reviews, and has 773 subscribers.

You will learn about Create a neural network from scratch in Java Understand how to use neural networks for handwritten digit recognition Implement the backpropagation algorithm Use neural networks for categorisation This course is ideal for individuals who are Java programmers who want to get started with artificial intelligence It is particularly useful for Java programmers who want to get started with artificial intelligence.

Enroll now: Create a Neural Network in Java

Summary

Title: Create a Neural Network in Java

Price: $69.99

Average Rating: 4.4

Number of Lectures: 196

Number of Published Lectures: 196

Number of Curriculum Items: 196

Number of Published Curriculum Objects: 196

Original Price: $24.99

Quality Status: approved

Status: Live

What You Will Learn

Create a neural network from scratch in Java
Understand how to use neural networks for handwritten digit recognition
Implement the backpropagation algorithm
Use neural networks for categorisation

Who Should Attend

Java programmers who want to get started with artificial intelligence

Target Audiences

Java programmers who want to get started with artificial intelligence

Learn how to create and use neural networks in your Java programs. This course teaches you not only how to implement machine learning AI with your own artificial neural networks (ANNs), but also the principles of how artificial neural networks work — to the point that you can implement your own.

You’ll need only a knowledge of Java programming and basic algebra; in this course you’ll learn the relevant linear algebra, information theory and calculus, and together we’ll build a fast and efficient neural network from scratch, able to recognise handwritten digits and easily adapted to other tasks.

Among other things, we’ll cover:

What artificial neural networks are and how to write them yourself
How matrixes and linear algebra can be used to create efficient neural networks
The basic principles of the calculus needed to train your networks
Writing and organising fast, efficient, multithreaded neural network code
The fundamental information theory concepts that can enable us to evaluate our neural network performance
Training your network on the freely-available MNIST hand-written digit database

After taking the course, artificial neural networks won’t be a mystery to you any more. You’ll be able to write your own neural networks and integrate them seamlessly into your Java programs, and understand in detail how they work.

Whether you’re completely new to neural networks and the relevant mathematics, or you’re using neural network libraries and you know some mathematics but you just don’t know how it all actually works and fits together, this course aims to clear up all the mystery.

Artificial intelligence is an increasingly important technology in the modern world, and this course will teach you the fundamentals of perhaps the most important building block of it.

Course Curriculum

Chapter 1: Introduction and Perceptron

Lecture 1: Introduction

Lecture 2: Why Write a Neural Network?

Lecture 3: Getting the Most Out of This Course

Lecture 4: Java vs Python

Lecture 5: Neurons

Lecture 6: Perceptron

Lecture 7: A Project With JUnit Support

Lecture 8: Coding Perceptron

Lecture 9: Where to Find the Source Code

Lecture 10: Eclipse Formatters

Lecture 11: Logic Gates

Lecture 12: Perceptron AND

Lecture 13: OR, NOR, NAND

Lecture 14: XOR and XNOR

Lecture 15: Linear Separability

Lecture 16: Some Layer Terminology

Lecture 17: Labelling Weights

Lecture 18: Matrices

Lecture 19: Some Mathematical Terminology

Chapter 2: Matrix Mathematics

Lecture 1: A Matrix Class

Lecture 2: Initialising the Matrix

Lecture 3: Matrix toString Method

Lecture 4: Testing the toString Method

Lecture 5: Modifying Matrices

Lecture 6: Multiplying Matrices By a Value

Lecture 7: Comparing Matrices

Lecture 8: Using the Equals Method

Lecture 9: Adding Matrices

Lecture 10: Motivation for Matrix Multiplication

Lecture 11: Multiplying the Tables

Lecture 12: Matrix Multiplication

Lecture 13: Matrix Multiplication Rule

Lecture 14: Matrix Multiplication Summary

Lecture 15: Matrix Multiplication Examples

Lecture 16: Assertions

Lecture 17: 2D to 1D

Lecture 18: Iterating Over Multiplicand Rows

Lecture 19: Completing the Multiplication Implementation

Lecture 20: Timing Matrix Multiplication

Lecture 21: Optimising Matrix Multiplication

Chapter 3: Activation Functions

Lecture 1: Neural Net Test Class

Lecture 2: Modifying Matrices

Lecture 3: Adding Bias

Lecture 4: Multiple Columns of Input

Lecture 5: ReLu

Lecture 6: A ReLu Test

Lecture 7: Matrix forEach

Lecture 8: Implementing ReLu

Lecture 9: Introducing Softmax

Lecture 10: Softmax Worked Example

Lecture 11: Summing Columns

Lecture 12: Implementing Softmax

Lecture 13: Testing Softmax

Lecture 14: The Engine

Lecture 15: Deciding Weight Matrix Sizes

Lecture 16: An Untrained Network

Lecture 17: Configuring Dense Layers

Lecture 18: Adding Multiple Layers

Lecture 19: Running the Engine

Chapter 4: Information Theory and Cross Entropy

Lecture 1: Mean Squares Loss

Lecture 2: What is Information?

Lecture 3: Symbol Spaces

Lecture 4: Entropy

Lecture 5: An Optimal Encoding Strategy

Lecture 6: Unequally Probable Symbols

Lecture 7: Calculating the Information Assoicated With a Symbol

Lecture 8: Entropy for Unequally Probable Symbols

Lecture 9: Introducing Cross Entropy

Lecture 10: Cross Entropy Example

Lecture 11: Cross Entropy as a Loss Function

Lecture 12: Implementing Cross Entropy

Lecture 13: A Cross Entropy Test

Lecture 14: Implementing the Cross Entropy Test

Chapter 5: Calculus and Backpropagation

Lecture 1: Training the Network

Lecture 2: Gradient Descent

Lecture 3: Gradients and Neural Networks

Lecture 4: A Calculus Class

Lecture 5: Implementing Differentiation

Lecture 6: Basic Mathematical Notation

Lecture 7: Partial Derivatives

Lecture 8: Overview of a 3 Layer Network

Lecture 9: The Network as a Transform

Lecture 10: Approximator

Lecture 11: Mock Expected Data

Lecture 12: Implementing the Transform

Lecture 13: Examining Loss

Lecture 14: An AddIncrement Method

Lecture 15: Completing the Approximator

Lecture 16: Recap and Natural Logarithms

Lecture 17: Finishing the Approximator Test

Lecture 18: Backpropagation

Lecture 19: Obtaining Softmax Cross Entropy Gradient

Lecture 20: Backpropagating Errors Through Weighted Sums

Lecture 21: Introducing the Chain Rule

Lecture 22: Programming the Chain Rule

Instructors

John Purcell
Software Development Trainer

Rating Distribution

1 stars: 2 votes
2 stars: 2 votes
3 stars: 4 votes
4 stars: 16 votes
5 stars: 69 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu