Large Scale Hetero-Associative Networks with Very High Classification Ability and Attractor Discrimination Consisting of Cumulative-Learned 3-Layer Neural Networks

摘要

Auto-Associative neural networks have limited memory capacity and no classification capability. We propose a hetero-associative network consisting of a cumulative-learned forward 3-layer neural network and a backward 3-layer neural network, and a hetero-tandem associative network. The hetero-tandem associative network has a spindle type single cyclic-associative network with cumulative learning and is connected in tandem with the subsequent hetero-associative network. These hetero-associative networks with classification ability have high recognition performance as well as rapid attractor absorption. Consecutive codification of outputs in the forward network was found to produce no spurious attractors, and coarse codification of converged attractors can be easily identified as training or spurious attractors. Cumulative learning with prototypes and additive training data adjacent to prototypes can also drastically improve associative performance of both the spindle type single cyclic- and hetero-associative networks, allowing them to effectively be connected in tandem.