Learn Neural Net Programming: http://www.heatonresearch.com/course/intro-neural-nets-cs
Solving the XOR, AND and OR logic gates with a neural network. This video is part of an online course on neural network programming.
Duration : 0:9:3
Home > June, 2009
Jun 27
Introduction to Neural Networks for C# (Class 1/16, Part 3/3)
Archived in the category: neural networks
Jun 24
Both are usually used in synthesizing artificial intelligence. While neural networks build on the biological way of learning, that is, it is used to make an AI unit "learn" in a manner similar to humans, fuzzy logic is an extension of digital logic, with multiple levels instead of just 1s and 0s. High speed trains in Japan have been using fuzzy logic for decades to ensure a smooth ride. However, both fields are open to much research, and giant steps are expected to be taken in the near future to provid more intelligent AI.
powered by Yahoo Answers
Jun 19
Introduction to Neural Networks for C#(Class 1/16, Part 2/3)
Archived in the category: neural networks
Learn Neural Net Programming: http://www.heatonresearch.com/course/intro-neural-nets-cs
Problems solved with neural networks. This video is part of an online course on neural network programming.
Duration : 0:5:6
Jun 12
Neural Networks Lesson 2: Probabilisitic Neural Networks
Archived in the category: neural networks
http://xoax.net/
This lesson demonstrates how a Probabilistic Neural Network works, is programmed, and can be used to analyze data.
Please submit all questions to our forum:
http://xoax.net/forum/
Duration : 0:3:21
Jun 06
Introduction to Neural Networks for Java (Class 1/16, Part 1/3)
Archived in the category: neural networks
Learn Neural Net Programming: http://www.heatonresearch.com/course/intro-neural-nets-java
Introduction to Neural Networks with java is a course that introduces the java programmer to the world of Neural Networks and Artificial Intelligence. Neural network architectures, such as the feedforward, Hopfield, and self-organizing map architectures will be presented. Training techniques, such as backpropagation, genetic algorithms and simulated annealing are also introduced. Practical examples are given for each neural network. Examples will be examined that include the traveling salesman problem, handwriting recognition, financial prediction, game strategy, mathematical functions, and Internet bots.
Duration : 0:9:35