Emergence of Complex-Like Cells in a Temporal Product Network with Local Receptive Fields

06/02/2010
by   Karo Gregor, et al.
0

We introduce a new neural architecture and an unsupervised algorithm for learning invariant representations from temporal sequence of images. The system uses two groups of complex cells whose outputs are combined multiplicatively: one that represents the content of the image, constrained to be constant over several consecutive frames, and one that represents the precise location of features, which is allowed to vary over time but constrained to be sparse. The architecture uses an encoder to extract features, and a decoder to reconstruct the input from the features. The method was applied to patches extracted from consecutive movie frames and produces orientation and frequency selective units analogous to the complex cells in V1. An extension of the method is proposed to train a network composed of units with local receptive field spread over a large image of arbitrary size. A layer of complex cells, subject to sparsity constraints, pool feature units over overlapping local neighborhoods, which causes the feature units to organize themselves into pinwheel patterns of orientation-selective receptive fields, similar to those observed in the mammalian visual cortex. A feed-forward encoder efficiently computes the feature representation of full images.

READ FULL TEXT

page 8

page 11

page 15

page 20

research
10/24/2022

On representation of natural image patches

Starting from the first principle I derive an unsupervised learning meth...
research
10/11/2019

A sub-Riemannian model of the visual cortex with frequency and phase

In this paper we present a novel model of the primary visual cortex (V1)...
research
05/29/2019

Nonvolatile Spintronic Memory Cells for Neural Networks

A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-d...
research
07/18/2022

The Brain-Inspired Decoder for Natural Visual Image Reconstruction

Decoding images from brain activity has been a challenge. Owing to the d...
research
04/16/2019

Response of Selective Attention in Middle Temporal Area

The primary visual cortex processes a large amount of visual information...
research
01/24/2019

Learning Vector Representation of Content and Matrix Representation of Change: Towards a Representational Model of V1

This paper entertains the hypothesis that the primary purpose of the cel...

Please sign up or login with your details

Forgot password? Click here to reset