Sökning: id:"swepub:oai:DiVA.org:su-117399" >
Reducing the comput...
Reducing the computational footprint for real-time BCPNN learning
-
- Vogginger, Bernhard (författare)
- Technical University Dresden
-
- Schueffny, Rene (författare)
- Technical University Dresden
-
- Lansner, Anders (författare)
- KTH,Stockholms universitet,Numerisk analys och datalogi (NADA),Royal Institute of Technology (KTH), Sweden,Beräkningsbiologi, CB,Stockholm University, Sweden,Lansner
-
visa fler...
-
- Cederström, Love (författare)
- Technical University Dresden
-
- Partzsch, Johannes (författare)
- Technical University Dresden
-
- Hoeppner, Sebastian (författare)
- Technical University Dresden
-
visa färre...
-
(creator_code:org_t)
- 2015-01-22
- 2015
- Engelska.
-
Ingår i: Frontiers in Neuroscience. - : Frontiers Media SA. - 1662-4548 .- 1662-453X .- 1662-6443. ; 9
- Relaterad länk:
-
https://doi.org/10.3...
-
visa fler...
-
https://www.frontier...
-
https://urn.kb.se/re...
-
https://doi.org/10.3...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- MEDICIN OCH HÄLSOVETENSKAP -- Medicinska och farmaceutiska grundvetenskaper -- Neurovetenskaper (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Basic Medicine -- Neurosciences (hsv//eng)
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Neurologi (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Neurology (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)
Nyckelord
- Bayesian confidence propagation neural network (BCPNN)
- Hebbian learning
- synaptic plasticity
- event-driven simulation
- spiking neural networks
- look-up tables
- fixed-point accuracy
- digital neuromorphic hardware
- Computer Science
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas