Sökning: onr:"swepub:oai:DiVA.org:kth-310721" >
Approximate computa...
Approximate computation of post-synaptic spikes reduces bandwidth to synaptic storage in a model of cortex
-
- Stathis, Dimitrios (författare)
- KTH,Elektronik och inbyggda system
-
- Yang, Yu (författare)
- KTH,Elektronik och inbyggda system
-
- Hemani, Ahmed, 1961- (författare)
- KTH,Elektronik och inbyggda system
-
visa fler...
-
- Lansner, Anders, Professor, 1949- (författare)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST),Stockholm University
-
visa färre...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2021
- 2021
- Engelska.
-
Ingår i: PROCEEDINGS OF THE 2021 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2021). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 685-688
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.2...
-
visa färre...
Abstract
Ämnesord
Stäng
- The Bayesian Confidence Propagation Neural Network (BCPNN) is a spiking model of the cortex. The synaptic weights of BCPNN are organized as matrices. They require substantial synaptic storage and a large bandwidth to it. The algorithm requires a dual access pattern to these matrices, both row-wise and column-wise, to access its synaptic weights. In this work, we exploit an algorithmic optimization that eliminates the column-wise accesses. The new computation model approximates the post-synaptic spikes computation with the use of a predictor. We have adopted this approximate computational model to improve upon the previously reported ASIC implementation, called eBrainII. We also present the error analysis of the approximation to show that it is negligible. The reduction in storage and bandwidth to the synaptic storage results in a 48% reduction in energy compared to eBrainII. The reported approximation method also applies to other neural network models based on a Hebbian learning rule.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- 3D DRAM
- Approximate computing
- ASIC
- Bandwidth optimization
- Neuromorphic Hardware
- Backpropagation
- Bandwidth
- Computation theory
- Matrix algebra
- Access patterns
- Algorithmic optimization
- Approximate computation
- Approximation methods
- Computation model
- Computational model
- Hebbian learning
- Neural network model
- Neural networks
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)