PhilSci Archive

Polytopes as vehicles of informational content in feedforward neural networks

Azhar, Feraz (2014) Polytopes as vehicles of informational content in feedforward neural networks. [Preprint]

[img] PDF
azhar_PP.pdf

Download (9MB)

Abstract

Localizing content in neural networks provides a bridge to understanding the way in which the brain stores and processes information. In this paper, I propose the existence of polytopes in the state space of the hidden layer of feedforward neural networks as vehicles of content. I analyze these geometrical structures from an information-theoretic point of view, invoking mutual information to help define the content stored within them. I establish how this proposal addresses the problem of misclassification, and provide a novel solution to the disjunction problem, which hinges on the precise nature of the causal-informational framework for content advocated herein.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Azhar, Ferazferaz.azhar@alumni.physics.ucsb.edu
Additional Information: Preprint of a paper forthcoming in Philosophical Psychology
Keywords: Informational Content, Neural Networks, Information Theory
Subjects: Specific Sciences > Cognitive Science
Specific Sciences > Biology > Neuroscience
Specific Sciences > Psychology/Psychiatry
Depositing User: Dr. Feraz Azhar
Date Deposited: 25 Mar 2016 02:17
Last Modified: 25 Mar 2016 02:17
Item ID: 11992
Subjects: Specific Sciences > Cognitive Science
Specific Sciences > Biology > Neuroscience
Specific Sciences > Psychology/Psychiatry
Date: 30 September 2014
URI: http://philsci-archive.pitt.edu/id/eprint/11992

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item