Search: onr:"swepub:oai:DiVA.org:kth-6240" >
Implementing Plasti...
Implementing Plastic Weights in Neural Networks using Low Precision Arithmetic
-
- Johansson, Christopher (author)
- KTH,Numerisk Analys och Datalogi, NADA,Beräkningsbiologi, CB
-
- Lansner, Anders (author)
- KTH,Beräkningsbiologi, CB
-
(creator_code:org_t)
- Elsevier BV, 2009
- 2009
- English.
-
In: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 72:4-6, s. 968-972
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- In this letter, we develop a fixed-point arithmetic, low precision, implementation of an exponentially weighted moving average (EWMA) that is used in a neural network with plastic weights. We analyze the proposed design both analytically and experimentally, and we also evaluate its performance in the application of an attractor neural network. The EWMA in the proposed design has a constant relative truncation error, which is important for avoiding round-off errors in applications with slowly decaying processes, e.g. connectionist networks. We conclude that the proposed design offers greatly improved memory and computational efficiency compared to a naive implementation of the EWMA's difference equation, and that it is well suited for implementation in digital hardware.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- Exponentially weighted moving average
- Fixed-point arithmetic
- Leaky integrator
- Low precision variables
- Neural networks
- Plastic weights
- Computer science
- Datalogi
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database