Links to various pattern recognition and machine learning resources

A machine learning resources from Applications to Tutorials.

A centralized resource for researchers of reinforcement learning. Maintained at University of Massachusetts, Amherst.

Artificial Neural Network-based natural language conversational agent and intelligent dialogue generator

Programming by example (or by demonstration) is a technique for teaching the computer new behavior by demonstrating actions on concrete examples. The system records user actions and generalizes a program that can be used in new examples.

A hub for Pattern Recognition linking to journals, books, bibliographies, jobs, conferences and news.

How computers can learn to get better at playing games. This site is for artificial intelligence researchers and intrepid game programmers. I describe game programs and their workings; they rely on heuristic search algorithms, neural networks, genetic algorithms, temporal differences, and other methods.

Resources for researchers and practitioners interested in the use of learning techniques in intelligent, user-adaptive systems.

A central information source for the area of Support Vector Machines, Gaussian Process prediction, Mathematical Programming with Kernels, Regularization Networks, Reproducing Kernel Hilbert Spaces, and related methods. Provides links to papers, upcoming events, datasets, code.

Introduction to k-means clustering, a popular data mining and unsupervised learning algorithm. Free code, software, resources and examples are available for download.

Site dedicated to research of artificial intelligence algorithms applied to information retrieval, data mining and optimization methods. Includes FAQs and AI resources for math/science teachers and students.

Repository of information on grammatical inference, automata induction, and language acquisition.

A competition on Grammatical Inference.

A research field devoted to studying the design and analysis of algorithms for making predictions about the future based on past experiences. The emphasis in COLT is on rigorous mathematical analysis. COLT is largely concerned with computational and data efficiency.