Addressing the interpretability problem for deep learning using many valued quantum logic
This addresses the lack of understanding in deep learning decisions for the ML community, offering a novel approach to interpretability.
The paper tackles the interpretability problem in deep learning by showing how many-valued quantum logic emerges in Convolutional Deep Belief Networks, providing a theoretical framework for interpretable models without sacrificing efficiency.
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.