DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems

TL;DR

This paper introduces DecisiveNets, a method to convert deep neural networks into deep associative memories, enhancing explainability and reducing computational costs without sacrificing predictive accuracy.

Contribution

It presents a novel transformation technique that simplifies deep neural networks into associative memories, improving interpretability and efficiency.

Findings

Transformations do not reduce predictive performance.

Deep associative memories are more explainable.

Reduced computational complexity in transformed models.

Abstract

Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years. Indeed, Deep Neural Networks are now the golden standard in domains as various as computer vision, natural language processing or even playing combinatorial games. However, problematic limitations are hidden behind this surprising universal capability. Among other things, explainability of the decisions is a major concern, especially since deep neural networks are made up of a very large number of trainable parameters. Moreover, computational complexity can quickly become a problem, especially in contexts constrained by real time or limited resources. Therefore, understanding how information is stored and the impact this storage can have on the system remains a major and open issue. In this chapter, we introduce a method to transform deep neural network models into deep associative memories, with simpler, more explicable and less expensive operations. We show through experiments that these transformations can be done without penalty on predictive performance. The resulting deep associative memories are excellent candidates for artificial intelligence that is easier to theorize and manipulate.