Beyond the feedforward sweep: feedback computations in the visual cortex

Abstract

Visual perception involves the rapid formation of a coarse image representation at the onset of visual processing, which is iteratively refined by late computational processes. These early versus late time windows approximately map onto feedforward and feedback processes, respectively. State‐of‐the‐art convolutional neural networks, the main engine behind recent machine vision successes, are feedforward architectures. Their successes and limitations provide critical information regarding which visual tasks can be solved by purely feedforward processes and which require feedback mechanisms. We provide an overview of recent work in cognitive neuroscience and machine vision that highlights the possible role of feedback processes for both visual recognition and beyond. We conclude by discussing important open questions for future research.

Document Details

Document Type
Pub Defense Publication
Publication Date
Feb 28, 2020
Source ID
10.1111/nyas.14320

Entities

People

  • Gabriel Kreiman
  • Thomas Serre

Organizations

  • Agence Nationale de la Recherche
  • Brown University
  • Harvard Medical School
  • National Science Foundation
  • Office of Naval Research

Tags

Fields of Study

  • Computer science

Readers

  • Computer Programming and Software Development.
  • Computer Vision.
  • Neuroscience

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks