A biologically inspired filter significance assessment method for model explanation

Neuron importance assessment is crucial for understanding the inner workings of artificial neural networks (ANNs) and improving their interpretability and efficiency. This paper introduces a novel approach to neuron significance assessment inspired by frequency tagging, a technique from neuroscience. By applying sinusoidal contrast modulation to image inputs and analyzing resulting neuron activations, this method enables finegrained analysis of a network’s decision making processes. Experiments conducted with a convolutional neural network for image classification reveal notable harmonics and intermodulations in neuron-specific responses under part based frequency tagging. These findings suggest that ANNs exhibit behavior akin to biological brains in tuning to flickering frequencies, there by opening avenues for neuron/filter importance assessment through frequency tagging. The proposed method holds promise for applications in network pruning, and model interpretability, contributing to the advancement of explainable artificial intelligence and addressing the lack of transparency in neural networks. Future research directions include developing novel loss functions to encourage biologically plausible behavior in ANNs.