Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing

Nikolaus Kriegeskorte*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademic

Abstract

Recent advances in neural network modeling have enabled major strides in computer vision and other artificial intelligence applications. Human-level visual recognition abilities are coming within reach of artificial systems. Artificial neural networks are inspired by the brain, and their computations could be implemented in biological neurons. Convolutional feedforward networks, which now dominate computer vision, take further inspiration from the architecture of the primate visual hierarchy. However, the current models are designed with engineering goals, not to model brain computations. Nevertheless, initial studies comparing internal representations between these models and primate brains find surprisingly similar representational spaces. With human-level performance no longer out of reach, we are entering an exciting new era, in which we will be able to build biologically faithful feedforward and recurrent computational models of how biological brains perform high-level feats of intelligence, including vision.
Original languageEnglish
Pages (from-to)417-446
JournalAnnual Review of Vision Science
Volume1
DOIs
Publication statusPublished - Nov 2015

Keywords

  • biological vision
  • computer vision
  • object recognition
  • neural network
  • deep learning
  • artificial intelligence
  • computational neuroscience

Fingerprint

Dive into the research topics of 'Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing'. Together they form a unique fingerprint.

Cite this