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

Share

COinS
 
May 13th, 4:50 PM May 13th, 5:15 PM

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.