A mathematical framework for bridging Marr’s levels

A mathematical framework for bridging Marr’s levels

Abstract

The increasing success of deep neural networks (DNNs) in solving complex tasks on par with human-level performance raises the question of whether artificial and biological neural networks perform specific tasks similarly. While current methods of comparison have identified similarities in their respective intermediate representations, a rigorous theory of algorithms and their physical implementations is indispensable for understanding the computational processes biological neural networks implement. This work proposes mathematical definitions of the terms algorithm and implementation and demonstrates on a toy model how to empirically test whether a physical system implements a specific algorithm. Our conceptual framework thus contributes to the efforts in cognitive computational neuroscience to develop rigorous theories that can link the computational, algorithmic, and implementational levels.

Grafik Top
Authors
  • Meunier, Anja
  • Grosse-Wentrup, Moritz
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
Conference on Cognitive Computational Neuroscience 2022
Divisions
Neuroinformatics
Subjects
Kuenstliche Intelligenz
Theoretische Informatik
Event Location
San Francisco, California, USA
Event Type
Conference
Event Dates
25-28 Aug 2022
Date
August 2022
Export
Grafik Top