Addressing the interpretability problem for deep learning using many valued quantum logic

TL;DR

This paper proposes a novel theoretical framework that integrates many-valued quantum logic into deep learning models, specifically Convolutional Deep Belief Networks, to enhance interpretability without sacrificing computational efficiency.

Contribution

It introduces a new quantum logic-based approach to improve the interpretability of deep learning models, bridging quantum theory and machine learning.

Findings

Quantum logic naturally arises in Convolutional Deep Belief Networks

Framework enhances interpretability of deep models

Maintains computational efficiency

Abstract

Deep learning models are widely used for various industrial and scientific applications. Even though these models have achieved considerable success in recent years, there exists a lack of understanding of the rationale behind decisions made by such systems in the machine learning community. This problem of interpretability is further aggravated by the increasing complexity of such models. This paper utilizes concepts from machine learning, quantum computation and quantum field theory to demonstrate how a many valued quantum logic system naturally arises in a specific class of generative deep learning models called Convolutional Deep Belief Networks. It provides a robust theoretical framework for constructing deep learning models equipped with the interpretability of many valued quantum logic systems without compromising their computing efficiency.