Abstract
Our model builds on a convolutional-style neural network with hierarchical stages representing processing steps in the ventral visual pathway. It was designed to capture the translation-invariance and shape-selectivity of neurons in area V4. The model uses biologically plausible linear filters at the front end, normalization and sigmoidal nonlinear activation functions. The max() function is used to generate translation invariance.
Keywords
CNN, Area V4, Object Recognition
Session Number
02
Session Title
Shape and Form
Start Date
13-5-2015 4:50 PM
End Date
13-5-2015 5:15 PM
Recommended Citation
Bair, Wyeth; Popovkina, Dina; De, Abhishek; and Pasupathy, Anitha, "Modeling Shape Representation in Area V4" (2015). MODVIS Workshop. 7.
https://docs.lib.purdue.edu/modvis/2015/session02/7
Modeling Shape Representation in Area V4
Our model builds on a convolutional-style neural network with hierarchical stages representing processing steps in the ventral visual pathway. It was designed to capture the translation-invariance and shape-selectivity of neurons in area V4. The model uses biologically plausible linear filters at the front end, normalization and sigmoidal nonlinear activation functions. The max() function is used to generate translation invariance.