INTERPRETING CONVOLUTIONAL SEQUENCE MODEL BY LEARNING LOCAL AND RESOLUTION-CONTROLLABLE PROTOTYPES

摘要

A method interprets a convolutional sequence model. The method converts (610) an input data sequence having input segments into output features. The method clusters (620) the input segments into clusters using respective resolution-controllable class prototypes allocated to each of classes. Each respective class prototype includes a respective output feature subset characterizing a respective associated class. The method calculates (630), using the clusters, similarity scores that indicate a similarity of an output feature to a respective class prototypes responsive to distances between the output feature and the respective class prototypes. The method concatenates (640) the similarity scores to obtain a similarity vector. The method performs (650) a prediction and prediction support operation that provides a value of prediction and an interpretation for the value responsive to the input segments and similarity vector. The interpretation for the value of prediction is provided using only non-negative weights and lacking a weight bias in the fully connected layer.