|Computing Partial Functions and Fractal Decision Boundaries with Efficient Spiking Neural Nets (PDF)|
A paper detailing a neural network model similar to standard spiking neural networks which does not require numerical integration. Source code included.
|Optimizing Functions on the Real Numbers|
This article provides a guide to optimizing general functions of the form f : |Rn → |R. Techniques for solving this problem include analytical solution, gradient descent, annealing, evolution, particle swarm optimization and hybrid approaches.
|Universal Meta Optimization|
Many problems in artificial intelligence such as training neural networks are optimization problems. The process of using an optimization algorithm to search all computable optimizers is meta optimization.
|Multi-Backpropagation Network: Concept and Modeling|
A look at groupings of multiple backpropagation neural nets
|Wan Hussain Wan Ishak||18/04/2004|
|Some Reviews on Distributed Learning in Neural Networks|
Training a single network is time consuming therefore distributed learning approaches such as hierarchical, multi-stage, parallel neural network computing are explored in this article.
|Wan Hussain Wan Ishak||09/04/2004|
|Applying Kohonen Networks|
A look at how to apply networks, using a simple example of RGB mapping and a more complicated example using image classification.
|Self Organizing Map AI for Pictures|
This article is about creating an application to cluster and search for related pictures.
|Medical Diagnosis Using Neural Networks|
Discusses using neural networks to aid diagnosis of several common medical conditions.
|Neural Networks in Anaemia Classification|
A look at applying a multilayer perceptron to the classification of anaemia
|Shuzlina Abd. Rahman||19/03/2004|
|The Potential of Neural Networks in Medical Applications|
Discusses the uses of neural networks within basic sciences, clinical medicine, signal processing and interpretation of medical images.
|Wan Hussain Wan Ishak||07/03/2004|
|Kohonen-based Image Analysis using the Generation5 JDK|
A look at how to write a Kohonen neural network to analyze and group similar photos.
|Simple BMP File Analysis Using MLPs|
This article looks at recognizing bitmapped smiley faces using MLPs.
Neural Network explorer allows you to train and watch a neural network in real-time and tweak a variety of parameters.
|Gesture Recognition Application (Delphi)|
Delphi program that uses a neural network to recognize alphabetical gestures.
|Michiel van Oudheusden|
Data file only
|Neural Network Explorer|
Create an run your own neural networks in a graphical environment.
|Kohonen Demonstrator - Java Applet|
A Kohonen neural network self-organizes itself across a simple cartesian plane.
|XOR Neural Network Code|
Neural network code to solve the XOR problem.
Data file only
|Mouse Gestures Recognition|
Feedforward multilayer neural network and mouse gesture recognition
|Optical Number Recognizor (ONR)|
Uses perceptrons to recognize the digits 0-9.
|Hopfield Image Recognizor (HIR)|
Another simple program that uses a Hopfield associative neural network to recognize simple binary images.
|PDA32 - Perceptron Demonstrator|
Separates two groups of points uses a perceptron.
|Simulated Annealing Demonstrator (SAD)|
A very simple program that uses simulated annealing to find the minimum of a complicated function.
A simple C++ program that shows how to use a genetic algorithm to evolve neural network weights.
A simple C++ class implementing backpropagation.
A simple dialog-based Windows application that demonstrate a Kohonen self-organizing neural network.
|Back-propagation using the Generation5 JDK|
A case study using the Generation5 JDK to understand feedforward neural networks and backpropagation.
Perceptrons are the simplest type of neural network.
|Simple OCR Using Perceptrons|
This articles looks at using perceptrons to recognize noisy images of the numbers 0-9.
|Notes on Neural Network Learning and Training|
An overview of learning and training for neural networks.
|Wan Hussain Wan Ishak||14/03/2004|
|Summing with Neural Networks|
This article will try to explain how you can make a network capable of summing numbers as big as you want.
|BP Example: XOR Net|
A step-by-step look at how the back-propagation algorithm works. Includes some C++ code to work with.
|An Introduction to Neural Networks|
Basic introduction to the theory of neural networks.
|Tablet PC OCR with Neural Network AI|
This article will start out with an overview of neural networks and how I applied one to do custom OCR on the Tablet PC.
|Character Recognition with Hebbian Links|
Discusses character recognition using neural networks using hebbian links.
|Neural Architecture Part 1: Simple Logic Functions|
This article is going to discuss neural network construction from a different perspective than is usual in conventional approaches.
|Realtime Evolution of Agent Controllers in Games |
After introducing the abstract concepts behind realtime evolutionary control of game agents, this paper discusses the application of these techniques to space invaders and a realtime strategy game similar to Warcraft. Source code included.
|Using Genetic Algorithms with Neural Networks|
How to use genetic algorithms to evolve the weights in a neural network.
|Perceptron 'OR' Project|
Train a perceptron to calculate the OR logic gate.
|Simple OCR Project|
Use a neural network to recognize digits and characters.
Introductory look at self-organizing neural networks - in particular, Kohonen networks.
|Back-propagation for the Uninitiated|
BP is a difficult algorithm to grasp at the best of times…this tutorials aims to provide a simple, but effective, introduction to back-propagation.
A method taken from metallurgy that helps neural networks and genetic algorithms avoid local minima!
|Neural Networks: Motivation, Theory and DANN|
Motivation and theory of specific artificial neural networks are explained.
|Associative Neural Networks|
An introduction to associative neural networks (ie., Hopfield Networks).
|Multilayer Feedforward Network and the Backpropagation Algorithm|
A complete look at the backpropagation algorithms.