Neural Networks from Scratch in Java

Hopfield networks, backpropagation
4.4 (27 ratings) Instead of using a simple lifetime average, Udemy calculates a
course's star rating by considering a number of different factors
such as the number of ratings, the age of ratings, and the
likelihood of fraudulent ratings.
333 students enrolled
Instructed by Holczer Balazs IT & Software / Other
$19
$20
5% off
Take This Course
  • Lectures 30
  • Length 2.5 hours
  • Skill Level All Levels
  • Languages English
  • Includes Lifetime access
    30 day money back guarantee!
    Available on iOS and Android
    Certificate of Completion
Wishlisted Wishlist

How taking a course works

Discover

Find online courses made by experts from around the world.

Learn

Take your courses with you and learn anywhere, anytime.

Master

Learn and practice real-world skills and achieve your goals.

About This Course

Published 2/2016 English

Course Description

This course is about artificial neural networks. Artificial intelligence and machine learning are getting more and more popular nowadays. In the beginning, other techniques such as Support Vector Machines outperformed neural networks, but in the 21th century neural networks again gain popularity. In spite of the slow training procedure, neural networks can be very powerful. Applications ranges from regression problems to optical character recognition and face detection. In the first part of the course you will learn about the theoretical background of neural networks, later you will learn how to implement them. If you are keen on learning methods, let's get started!

What are the requirements?

  • Basic Java

What am I going to get from this course?

  • Basics of neural networks
  • Backpropagation
  • Concrete implementation of neural networks

What is the target audience?

  • This course is recommended for students who are interested in artificial intelligence focusing on neural networks

What you get with this course?

Not for you? No problem.
30 day money back guarantee.

Forever yours.
Lifetime access.

Learn on the go.
Desktop, iOS and Android.

Get rewarded.
Certificate of completion.

Curriculum

Section 1: Introduction
Introduction
Preview
01:16
Section 2: Neural Networks Introduction
Axons and neurons in the human brain
05:41
Modeling human brain
04:59
Applications of neural networks
03:33
Section 3: Hopfield Neural Network
Hopfield neural network introduction
Preview
04:55
Hopfield network energy
Preview
02:22
Hopfield neural network training and learning
Preview
03:17
Hopfield neural network problems
01:36
Hopfield neural network example
04:17
Hopfield network implementation
09:28
Section 4: Neural Networks With Backpropagation Theory
Neural networks introduction
11:03
Feedforward neural networks
07:42
Training a neural network
08:37
Error calculation
03:12
Gradient calculation
08:35
Backpropagation
03:18
Resilient propagation
04:20
Deep learning
02:41
Applications of neural networks
05:56
Section 5: Backpropagation Implementation
Linearly separable AND problem
10:29
Structure of the nonlinear program
04:31
Neural network implementation - structure
06:44
Neural network implementation - activation functions
03:34
Neural network implementation - feedforward
04:50
Neural network implementation - backpropagation
06:44
Neural network implementation - error calculation
04:14
Neural network implementation - running the app
07:13
Section 6: Source Code
Slides
Article
Source code
Article
Get other courses for a discounted price!
Article

Students Who Viewed This Course Also Viewed

  • Loading
  • Loading
  • Loading

Instructor Biography

Holczer Balazs, Software Engineer

Hi!

My name is Balazs Holczer. I am from Budapest, Hungary. I am qualified as a physicist and later on I decided to get a master degree in applied mathematics. At the moment I am working as a simulation engineer at a multinational company. I have been interested in algorithms and data structures and its implementations especially in Java since university. Later on I got acquainted with machine learning techniques, artificial intelligence, numerical methods and recipes such as solving differential equations, linear algebra, interpolation and extrapolation. These things may prove to be very very important in several fields: software engineering, research and development or investment banking. I have a special addiction to quantitative models such as the Black-Scholes model, or the Merton-model. Quantitative analysts use these algorithms and numerical techniques on daily basis so in my opinion these topics are definitely worth learning.

Ready to start learning?
Take This Course