Visual Cortex And Deep Networks: Learning Invariant Representations

Hardcover | September 23, 2016

byTomaso A. Poggio, Fabio Anselmi

not yet rated|write a review

The ventral visual stream is believed to underlie object recognition in primates. Over the past fifty years, researchers have developed a series of quantitative models that are increasingly faithful to the biological architecture. Recently, deep learning convolution networks -- which do not reflect several important features of the ventral stream architecture and physiology -- have been trained with extremely large datasets, resulting in model neurons that mimic object recognition but do not explain the nature of the computations carried out in the ventral stream. This book develops a mathematical framework that describes learning of invariant representations of the ventral stream and is particularly relevant to deep convolutional learning networks.

The authors propose a theory based on the hypothesis that the main computational goal of the ventral stream is to compute neural representations of images that are invariant to transformations commonly encountered in the visual environment and are learned from unsupervised experience. They describe a general theoretical framework of a computational theory of invariance (with details and proofs offered in appendixes) and then review the application of the theory to the feedforward path of the ventral stream in the primate visual cortex.

Pricing and Purchase Info

$43.32

In stock online
Ships free on orders over $25
HURRY, ONLY 2 LEFT!

From the Publisher

The ventral visual stream is believed to underlie object recognition in primates. Over the past fifty years, researchers have developed a series of quantitative models that are increasingly faithful to the biological architecture. Recently, deep learning convolution networks -- which do not reflect several important features of the ven...

Tomaso A. Poggio is Eugene McDermott Professor in the Department of Brain and Cognitive Sciences at MIT, where he is also Director of the Center for Brains, Minds, and Machines and Codirector of the Center for Biological and Computational Learning. He is coeditor of Perceptual Learning (MIT Press). Fabio Anselmi is a Postdoctoral Fell...

other books by Tomaso A. Poggio

Vision: A Computational Investigation into the Human Representation and Processing of Visual…
Vision: A Computational Investigation into the Human Re...

Kobo ebook|Jul 9 2010

$45.49 online$59.04list price(save 22%)
Format:HardcoverDimensions:136 pages, 9 × 6 × 0.38 inPublished:September 23, 2016Publisher:The MIT PressLanguage:English

The following ISBNs are associated with this title:

ISBN - 10:0262034727

ISBN - 13:9780262034722

Customer Reviews of Visual Cortex And Deep Networks: Learning Invariant Representations

Reviews

Extra Content

Editorial Reviews

Poggio and Anselmi present a scholarly and rigorous theoretical framework supported by experimental findings and computational simulations of how to build robust and invariant representations. Visual Cortex and Deep Networks features recent theoretical developments, which enable us to formalize the notion of how deep hierarchical structures can provide flexible image representations. Highly recommended.