Kohonen Feature Map Associative Memory with Refractoriness Based on Area Representation

Abstract

Recently, neural networks are drawing much attention as a method to realize flexible information processing. Neural networks consider neuron groups of the brain in the creature, and imitate these neurons technologically. Neural networks have some features, especially one of the important features is that the networks can learn to acquire the ability of information processing. In the field of neural networks, a lot of models have been proposed such as the Back Propagation algorithm In these models, the learning process and the recall process are divided, and therefore they need all information to learn in advance. However, in the real world, it is very difficult to get all information to learn in advance, so we need the model whose learning process and recall process are not divided. As such model, Grossberg and Carpenter proposed the ART (Adaptive Resonance Theory) However, the ART is based on the local representation, and therefore it is not robust for damaged neurons in the Map-Layer. While in the field of associative memories, some models have been proposed Since these models are based on the distributed representation, they have the robustness for damaged neurons. However, their storage capacities are small because their learning algorithm is based on Hebbian learning. On the other hand, the Kohonen Feature Map associative memory (KFM associative memory) Although the KFM associative memory is based on the local representation as similar as the ART It can deal with auto and hetero associations and the associations for plural sequential patterns including common terms Moreover, the KFM associative memory with area representation (Abe & Osana, 2006) has been proposed. In the model, the area representation However, it can not deal with one-tomany associations and associations of analog patterns. www.intechopen.com New Developments in Robotics, Automation and Control 260