Interpretability of Neural Network With Physiological Mechanisms

TL;DR

This paper explores the interpretability of neural networks by comparing them to biological neural circuits, aiming to enhance understanding of their functional processes through physiological realism.

Contribution

It introduces a comparative analysis between neural networks and biological circuits to improve interpretability and understanding of neural network mechanisms.

Findings

Neural networks share similarities with biological circuits in certain aspects.

Understanding biological behaviors can inform neural network design.

Physiological realism may enhance interpretability of AI models.

Abstract

Deep learning continues to play as a powerful state-of-art technique that has achieved extraordinary accuracy levels in various domains of regression and classification tasks, including images, video, signal, and natural language data. The original goal of proposing the neural network model is to improve the understanding of complex human brains using a mathematical expression approach. However, recent deep learning techniques continue to lose the interpretations of its functional process by being treated mostly as a black-box approximator. To address this issue, such an AI model needs to be biological and physiological realistic to incorporate a better understanding of human-machine evolutionary intelligence. In this study, we compare neural networks and biological circuits to discover the similarities and differences from various perspective views. We further discuss the insights into how neural networks learn from data by investigating human biological behaviors and understandable justifications.