About: Minimal spiking neuron for solving multi-label classification tasks

Not logged in : Login

(Sponging disallowed)

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: Minimal spiking neuron for solving multi-label classification tasks Goto Sponge NotDistinct Permalink

An Entity of Type : bibo:AcademicArticle, within Data Space : linkeddata.uriburner.com:28898 associated with source document(s)

Attributes	Values
type	http://eprints.org/ontology/ArticleEPrint http://eprints.org/ontology/EPrint Article Academic Article
seeAlso	HTML Summary of #80477 Minimal spiking neuron for solving multi-label classification tasks
sameAs	Minimal spiking neuron for solving multi-label classification tasks
http://eprints.org/ontology/hasDocument	Minimal spiking neuron for solving multi-label classification tasks (PDF) Minimal spiking neuron for solving multi-label classification tasks (Other) Minimal spiking neuron for solving multi-label classification tasks (Other) Minimal spiking neuron for solving multi-label classification tasks (Other) Minimal spiking neuron for solving multi-label classification tasks (Other) Minimal spiking neuron for solving multi-label classification tasks (Other)
http://eprints.org/ontology/hasPublished	Minimal spiking neuron for solving multi-label classification tasks (PDF)
dc:hasVersion	Minimal spiking neuron for solving multi-label classification tasks (PDF)
Title	Minimal spiking neuron for solving multi-label classification tasks
described by	https://demo.openlinksw.com/about/id/entity/https/www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3 https://demo.openlinksw.com/about/id/entity/https/raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
Date	2020-06-05
Creator	Dominique Chu Jakub Fil
status	peer reviewed published
Publisher	MIT Press
abstract	The Multi-Spike Tempotron (MST) is a powerful single spiking neuron model that can solve complex supervised classification tasks. While powerful, it is also internally complex, computationally expensive to evaluate, and not suitable for neuromorphic hardware. Here we aim to understand whether it is possible to simplify the MST model, while retaining its ability to learn and to process information. To this end, we introduce a family of Generalised Neuron Models (GNM) which are a special case of the Spike Response Model and much simpler and cheaper to simulate than the MST. We find that over a wide range of parameters the GNM can learn at least as well as the MST. We identify the temporal autocorrelation of the membrane potential as the single most important ingredient of the GNM which enables it to classify multiple spatio-temporal patterns. We also interpret the GNM as a chemical system, thus conceptually bridging computation by neural networks with molecular information processing. We conclude the paper by proposing alternative training approaches for the GNM including error trace learning and error backpropagation.
Is Part Of	Neural Computation https://kar.kent.ac.uk/id/repository
list of authors	https://kar.kent.ac.uk/id/eprint/80477#authors
issue	7
volume	32
is topic of	https://www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3 https://raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
is primary topic of	HTML Summary of #80477 Minimal spiking neuron for solving multi-label classification tasks

Faceted Search & Find service v1.17_git150 as of Jan 20 2025

Alternative Linked Data Documents: iSPARQL | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3332 as of Jan 29 2025, on Linux (x86_64-generic-linux-glibc25), Single-Server Edition (378 GB total memory, 37 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software