Artificial neural networks
Get flash to fully experience Pearltrees
AN ARTIFICIAL brain has taught itself to estimate the number of objects in an image without actually counting them, emulating abilities displayed by some animals including lions and fish , as well as humans. Because the model was not preprogrammed with numerical capabilities, the feat suggests that this skill emerges due to general learning processes rather than number-specific mechanisms.
Neural network gets an idea of number without counting - tech - 20 January 2012 - New Scientist
This course provides an introduction to the theory of neural computation.
VS265: Neural Computation - RedwoodCenter
A data-driven technique to find visual similarity which does not depend on any particular image domain or feature representation.
Data-driven Visual Similarity for Cross-domain Image Matching
Intro & basic
Tech papers
Neuroscience
Information transmission with spiking Bayesian neurons
Abstract. Spike trains of cortical neurons resulting from repeatedpresentations of a stimulus are variable and exhibit Poisson-like statistics. Many models of neural coding therefore assumed that sensory information is contained in instantaneous firing rates, not spike times.
Simulators and tools
The Computational Neuroscience PhD specialization of Boston University’s Graduate Program for Neuroscience provides students with a uniquely specialized curriculum that supplements core neuroscience coursework with advanced training in a wide array of computational methods for studying the nervous system and developing neuroscience-related technologies. Topics of study include: neural network modeling, neural dynamics, sensory, motor, and cognitive modeling, statistical modeling, sensory and motor prosthesis, brain-machine interfaces, neuroinformatics, neuromorphic engineering, and robotics. Coursework is chosen from the wide array of computational and neuroscience courses offered by the many departments and programs of the main Boston University campus and the BU School of Medicine.
Neurdon
Neocognitron neural network
Artificial neural network architectures such as backpropagation tend to have general applicability. We can use a single network type in many different applications by changing the network's size, parameters, and training sets. In contrast, the developers of the neocognitron set out to tailor architecture for a specific application: recognition of handwritten characters.
Steven E. Lamberson, Jr. Funwork #3 Page
In all the previous homework assignments we have discussed supervised neural networks - that is, networks that require a "teacher" to "instruct" them before they can properly perform their task. Now we will be discussing the Winner-take-all (WTA) neural net, which is one of the types of neural networks classified as an unsupervised (or self-organized) network. The WTA is capable of learning as it is going, and does not need a particular learning phase because it learns as it goes.
[ edit ] Competitive Learning
Artificial Neural Networks/Competitive Learning - Wikibooks, open books for an open world
Welcome to Heaton Research, Inc.
Heaton Research | Books for Neural Networks, Encog, and Artificial Intelligence
Hopfield Neural Network Example | Heaton Research
Now that you have been shown some of the basic concepts of neural network we will example an actual Java example of a neural network. The example program for this chapter implements a simple Hopfield neural network that you can used to experiment with Hopfield neural networks. The example given in this chapter implements the entire neural network.
Associations - While individual items and contexts are represented as single vectors ( a , b , x ), associations between items and contexts are represented by matrices derived from the matrix product of these vectors. The resulting matrix product represents the association (or binding) between either items, or between items and context. The memory of the matrix Model is formed by adding these associations together.
Long Term Memory: Matching versus Retrieval, Episodic versus Semantic
This document describes in detail HTM technology and the new algorithms for learning and prediction. This document will be updated periodically with additional material.
Numenta Papers and videos
Numenta new HTM Algorithms
Jeff Hawkins presents the new HTM Cortical Learning algorithms at the Beckman Institute, University of Illinois at Urbana-Champaign. The talk is technical in nature and complements the written document "Hierarchical Temporal Memory including HTM Cortical Learning Algorithms".Having established that CV and Bayes are different, I have three reasons for preferring Bayesian methods:
Bayesian FAQ
Vision