An Improved Bilinear Deep Belief Network Algorithm for Image Classification

摘要

A novel image recognition method based on the improved BDBN (Bilinear Deep Belief Network) model is presented, optimized with a MKL (Multiple Kernel Learning) strategy. All kernel functions in MKL are replaced by hierarchical feature representations, and the number of kernels is set to the number of layers of BDBN. The method is performed on the standard Caltech101 image dataset. The experiments show that the proposed method can improve the accuracy of traditional BDBN methods by up to 2.8%, and the accuracy of the method is superior to some methods in the literature.