Fast Artificial Neural Network Library is a free open source neural network library, which implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution
SIMBRAIN is a free tool for building, running, and analyzing neural-networks (computer simulations of brain circuitry). Simbrain aims to be as visual and easy-to-use as possible.
This project contains Naive and Fishers bayesian classifiers, as described in Toby Segaran's book "Programming Collective Intelligence." The book has python implementations; this is a Java implementation.
ConceptNet is a freely available commonsense knowledgebase and natural-language-processing toolkit which supports many practical textual-reasoning tasks over real-world documents right out-of-the-box (without additional statistical training) including
If you are starting with Neural Networks you should check out my online book on the subject. It contains over 300 pages of information on Neural Network Programming in Java. You can access it here.
In analyzing my data I wanted to classify it with a naive Bayesian classifier. I wasn't sure I had the math right, so I wrote a tiny abstract classifier to test with. The code is pretty cool:
You've built a vibrant community of Family Guy enthusiasts. The SVD recommendation algorithm took your site to the next level by allowing you to leverage the implicit knowledge of your community. But now you're ready for the next iteration - you are about
In this blog entry I’ll look at Drools/JBoss Rules implementation of Alpha and Beta Nodes indexing. How such an index looks like. When it is created. What are the benefits. Some examples are also given.
Stochastic matrices are easy to get -- just normalize the rows. Doubly stochastic matrices require more work -- simply normalizing columns/rows will not converge may take few dozen iterations to converge. One approach that works is to do constrained optim
Get the entire book! Introduction to Neural Networks with Java Programming Neural Networks in Java will show the intermediate to advanced Java programmer how to create neural networks. This book attempts to teach neural network programming through two mec
Libtextcat is a library with functions that implement the classification technique described in Cavnar & Trenkle, "N-Gram-Based Text Categorization" [1]. It was primarily developed for language guessing, a task on which it is known to perform with near-pe
This is an overview of AmonI research projects that are either currently active or likely to be active again. Both Alwyn Barry and Joanna Bryson maintain complete lists of former student projects, click those links to see them. The sofware associated with
Duck typing is the concept in programming by which an object is interchangeable with any other object as long as it can run through the same code while providing a sufficiently complete interface
Structure and Interpretation of Computer Programs has been MIT's introductory pre-professional computer science subject since 1981. It emphasizes the role of computer languages as vehicles for expressing knowledge and it presents basic principles of abstr
The Rete algorithm is an efficient pattern matching algorithm for implementing production rule systems. The Rete algorithm was designed by Dr Charles L. Forgy of Carnegie Mellon University, first published in a working paper in 1974, and later elaborated
I made a decision to discontinue the Cut The Knot column. The column has a distinction of having straddled two decades, two centuries, and in fact, two millennia. It was never meant to last that long. I thank all the readers who cared to send me their sug
The Rete Algorithm [References] is intended to improve the speed of forward-chained rule systems by limiting the effort required to recompute the conflict set after a rule is fired. Its drawback is that it has high memory space requirements. It takes adva
This introductory textbook on reinforcement learning is targeted toward engineers and scientists in artificial intelligence, operations research, neural networks, and control systems, and we hope it will also be of interest to psychologists and neuroscien
The goal of the Java-Chess project is to develop an OpenSource chess application written in Java. We want to demonstrate that Java can be tuned to a point, where it is almost up to the performance of an application, that was directly compiled to native co