A Kantian Cognitive Architecture

In Matteo Vincenzo D'Alfonso & Don Berkich, On the Cognitive, Ethical, and Scientific Dimensions of Artificial Intelligence. Springer Verlag. pp. 233-262 (2019)
  Copy   BIBTEX

Abstract

In this paper, I reinterpret Kant’s Transcendental Analytic as a description of a cognitive architecture. I describe a computer implementation of this architecture, and show how it has been applied to two unsupervised learning tasks. The resulting program is very data efficient, able to learn from a tiny handful of examples. I show how the program achieves data-efficiency: the constraints described in the Analytic of Principles are reinterpreted as strong prior knowledge, constraining the set of possible solutions.

Other Versions

No versions found

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 103,486

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Analytics

Added to PP
2019-02-01

Downloads
70 (#311,921)

6 months
15 (#168,777)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Richard Evans
Cambridge University

Citations of this work

Formalizing Kant’s Rules.Richard Evans, Andrew Stephenson & Marek Sergot - 2019 - Journal of Philosophical Logic 48:1-68.
The Apperception Engine.Richard Evans - 2022 - In Hyeongjoo Kim & Dieter Schönecker, Kant and Artificial Intelligence. De Gruyter. pp. 39-104.
Kant's doctrine of education and the problem of artificial intelligence.Leonid Kornilaev - 2021 - Journal of Philosophy of Education 55 (6):1072-1080.

Add more citations

References found in this work

No references found.

Add more references