Method and system for multimodal classification based on brain-inspired unsupervised learning

Abstract

A computer implemented method is provided for multimodal data classification with brain-inspired unsupervised learning, and a neuromorphic computing hardware structure for implementing the method. In a preferred embodiment, the method comprises the steps of: training with unsupervised learning based on a multimodal training dataset each of a plurality of Artificial Neural Networks (ANNs); training with unsupervised learning based on the multimodal training dataset a multimodal association between the ANNs to generate a plurality of bidirectional lateral connections between co-activated Best Matching Units (BMUs); labeling the neurons of each of the at least two ANNs with a divergence algorithm; and electing a global BMU with a convergence algorithm.