Visual Cortex and Deep Networks: Learning Invariant Representations (Computational Neuroscience Series)

Tomaso A. Poggio, Fabio Anselmi

  • 出版商: MIT
  • 出版日期: 2016-09-23
  • 售價: $1,200
  • 貴賓價: 9.8$1,176
  • 語言: 英文
  • 頁數: 136
  • 裝訂: Hardcover
  • ISBN: 0262034727
  • ISBN-13: 9780262034722
  • 相關分類: 人工智慧DeepLearning
  • 立即出貨(限量) (庫存=2)

商品描述

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.

商品描述(中文翻譯)

腹側視覺通道被認為是靈長類動物中物體識別的基礎。在過去的五十年中,研究人員已經開發了一系列越來越貼近生物結構的定量模型。最近,使用非常大的數據集訓練的深度學習卷積網絡,模擬了物體識別的模型神經元,但並未解釋腹側通道中進行的計算的本質,因為這些模型並未反映出腹側通道的結構和生理學的幾個重要特徵。本書開發了一個數學框架,描述了腹側通道中不變表示的學習,對於深度卷積學習網絡尤其相關。

作者提出了一個理論,基於腹側通道的主要計算目標是計算對於視覺環境中常見變換具有不變性的神經表示,並從無監督經驗中學習。他們描述了一個通用的理論框架,即不變性的計算理論(詳細和證明在附錄中提供),然後回顧了該理論在靈長類動物視覺皮層中前向通道的應用。