Understanding CNNs as a model of the inferior temporal cortex: using mediation analysis to unpack the contribution of perceptual and semantic features in random and trained networks

no code implementations • NeurIPS Workshop SVRHM 2020 • Anna Truzzi, Rhodri Cusack

The ability of the CNNs to predict IT activity patterns and the role played by perceptual and semantic features was evaluated using regression models, multidimensional scaling, and mediation analysis.

Layerwise Learning Rates for Object Features in Unsupervised and Supervised Neural Networks And Consequent Predictions for the Infant Visual System

no code implementations • 25 Sep 2019 • Rhodri Cusack, Cliona O'Doherty, Anna Birbeck, Anna Truzzi

CORnet and DeepCluster differ in both supervision and in the convolutional networks at their heart, thus to isolate the effect of supervision, we ran a control experiment in which we trained the convolutional network from DeepCluster (an AlexNet variant) in a supervised manner.