Orthogonal Bases are the Best: A Theorem Justifying Bruno Apolloni's Heuristic Neural Network Idea

摘要

One of the main problems with neural networks is that they are often very slow in learning the desired dependence. To speed up neural networks, Bruno Apolloni proposed to othogonalize neurons during training, i.e., to select neurons whose output functions are orthogonal to each other. In this paper, we use symmetries to provide a theoretical explanation for this heuristic idea.