Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Reducing the computational footprint for real-time BCPNN learning
Technical University Dresden.
Technical University Dresden.
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB. Stockholm University, Sweden. (Lansner)ORCID iD: 0000-0002-2358-7815
Technical University Dresden.
Show others and affiliations
2015 (English)In: Frontiers in Neuroengineering, ISSN 1662-6443, Vol. 9, no 2, 2Article in journal (Refereed) Published
Abstract [en]

The implementation of synaptic plasticity in neural simulation or neuromorphic hardware is usually very resource-intensive, often requiring a compromise between efficiency and flexibility. A versatile, but computationally-expensive plasticity mechanism is provided by the Bayesian Confidence Propagation Neural Network (BCPNN) paradigm. Building upon Bayesian statistics, and having clear links to biological plasticity processes, the BCPNN learning rule has been applied in many fields, ranging from data classification, associative memory, reward-based learning, probabilistic inference to cortical attractor memory networks. In the spike-based version of this learning rule the pre-, postsynaptic and coincident activity is traced in three low-pass-filtering stages, requiring a total of eight state variables, whose dynamics are typically simulated with the fixed step size Euler method. We derive analytic solutions allowing an efficient event-driven implementation of this learning rule. Further speedup is achieved by first rewriting the model which reduces the number of basic arithmetic operations per update to one half, and second by using look-up tables for the frequently calculated exponential decay. Ultimately, in a typical use case, the simulation using our approach is more than one order of magnitude faster than with the fixed step size Euler method. Aiming for a small memory footprint per BCPNN synapse, we also evaluate the use of fixed-point numbers for the state variables, and assess the number of bits required to achieve same or better accuracy than with the conventional explicit Euler method. All of this will allow a real-time simulation of a reduced cortex model based on BCPNN in high performance computing. More important, with the analytic solution at hand and due to the reduced memory bandwidth, the learning rule can be efficiently implemented in dedicated or existing digital neuromorphic hardware.

Place, publisher, year, edition, pages
2015. Vol. 9, no 2, 2
Keyword [en]
Neuromorphic system, BCPNN, synaptic plasticity
National Category
Computer Systems
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-165947DOI: 10.3389/fnins.2015.00002ISI: 000352944600001PubMedID: 25657618Scopus ID: 2-s2.0-84921746938OAI: oai:DiVA.org:kth-165947DiVA: diva2:809182
Funder
EU, FP7, Seventh Framework Programme, 604102Swedish Research Council, VR-621-2012-3502Swedish e‐Science Research Center
Note

QC 20150506

Available from: 2015-04-30 Created: 2015-04-30 Last updated: 2017-12-04Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textPubMedScopus

Search in DiVA

By author/editor
Lansner, Anders
By organisation
Computational Biology, CB
In the same journal
Frontiers in Neuroengineering
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 141 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf