PARALLEL SELF-ORGANIZING MAP

来源期刊：中国有色金属学报(英文版)1999年第1期

论文作者：Li Weigang

文章页码：172 - 180

Key words：artificial neural networks;　competitive learning;　parallel computing;　quantum computing

Abstract: A new self-organizing map, parallel self-organizing map (PSOM), was proposed for information parallel processing purpose. In this model, there are two separate layers of neurons connected together, the number of neurons in both layer and connections between them is equal to the number of total elements of input signals, the weight updating is managed through a sequence of operations among some unitary transformation and operation matrixes, so the conventional repeated learning procedure was modified to learn just once and an algorithm was developed to realize this new learning method. With a typical classification example, the performance of PSOM demonstrated convergence results similar to Kohonen’s model. Theoretic analysis and proofs also showed some interesting properties of PSOM. As it was pointed out, the contribution of such a network may not be so significant, but its parallel mode may be interesting for quantum computation.