A mathematical framework that describes learning of invariant representations in the ventral stream, offering both theoretical development and applications.
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.
Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.
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 Fellow in the Istituto Italiano di Tecnologia Laboratory for Computational and Statistical Learning at MIT and part of the Center for Brains, Minds, and Machines.
Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.
Vendeur : Bellwetherbooks, McKeesport, PA, Etats-Unis
hardcover. Etat : Fine. LIKE NEW!!! Has a red or black remainder mark on bottom/exterior edge of pages. N° de réf. du vendeur 413452
Quantité disponible : 9 disponible(s)
Vendeur : Once Upon A Time Books, Siloam Springs, AR, Etats-Unis
hardcover. Etat : Good. This is a used book in good condition and may show some signs of use or wear . This is a used book in good condition and may show some signs of use or wear . N° de réf. du vendeur mon0001323911
Quantité disponible : 1 disponible(s)
Vendeur : HPB Inc., Dallas, TX, Etats-Unis
hardcover. Etat : Very Good. Connecting readers with great books since 1972! Used books may not include companion materials, and may have some shelf wear or limited writing. We ship orders daily and Customer Service is our top priority! N° de réf. du vendeur S_454134954
Quantité disponible : 1 disponible(s)
Vendeur : Moe's Books, Berkeley, CA, Etats-Unis
Hard cover. Etat : Very good. No jacket. Spine is tight. Cover is very lightly worn, particularly along edges. Inside is clean and unmarked. N° de réf. du vendeur 1139826
Quantité disponible : 1 disponible(s)
Vendeur : Toscana Books, AUSTIN, TX, Etats-Unis
Hardcover. Etat : new. Excellent Condition.Excels in customer satisfaction, prompt replies, and quality checks. N° de réf. du vendeur Scanned0262034727
Quantité disponible : 1 disponible(s)
Vendeur : Mispah books, Redhill, SURRE, Royaume-Uni
Hardcover. Etat : Like New. Like New. book. N° de réf. du vendeur ERICA78702620347276
Quantité disponible : 1 disponible(s)