Work

The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work).

Year: 2012

Type: article

Abstract: This paper explores the theoretical consequences of a simple assumption: the computational goal of the feedforward path in the ventral stream -- from V1, V2, V4 and to IT -- is to discount image transformations, after learning them during development.

Source: DSpace@MIT (Massachusetts Institute of Technology)

Authors: Tomaso Poggio, Jim Mutch, Joel Z. Leibo, Lorenzo Rosasco, Andrea Tacchetti

Language: English

Topic: Visual perception and processing mechanisms

Subfield: Cognitive Neuroscience

Field: Neuroscience

Domain: Life Sciences

Open Access status: green

Funders: National Science Foundation, Honda Research Institute, USA, Defense Advanced Research Projects Agency, McGovern Institute for Brain Research, Massachusetts Institute of Technology

Awards: Collaborative Proposal: Object and Action Recognition in Time Sequences of Images: Computational Neuroscience and Neurophysiology, Computational Models and Physiological Studies of Feedback in Visual Object Recognition Tasks

OpenAlex ID: W1586192175

FWCI: 2.213

Cites: 70

Cited by: 25

Related to: 10