Examining Representational Similarity in ConvNets and the Primate Visual Cortex
This work addresses the problem of understanding brain-inspired AI models for neuroscientists and AI researchers, but it is incremental as it builds on existing comparisons.
The study investigated how convolutional neural networks (ConvNets) compare to the primate visual cortex in representational similarity, finding that deeper networks with better validation performance align more closely with cortical IT representations.
We compare several ConvNets with different depth and regularization techniques with multi-unit macaque IT cortex recordings and assess the impact of the same on representational similarity with the primate visual cortex. We find that with increasing depth and validation performance, ConvNet features are closer to cortical IT representations.