Sökning: WFRF:(Osipov E)
> Wiklund Urban >
Density Encoding En...
Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks
-
- Kleyko, Denis (författare)
- RISE,Datavetenskap,Redwood Center for Theoretical Neuroscience, University of California at Berkeley, CA, Berkeley, United States; Intelligent Systems Lab, Research Institutes of Sweden, Kista, Sweden,Redwood Center for Theoretical Neuroscience, University of California at Berkeley, Berkeley, CA 94720 USA; Intelligent Systems Lab, Research Institutes of Sweden, 164 40 Kista, Sweden
-
- Kheffache, Mansour (författare)
- Netlight Consulting AB, 111 53 Stockholm, Sweden
-
- Frady, E Paxon (författare)
- Redwood Center for Theoretical Neuroscience, University of California at Berkeley, CA, Berkeley, United States,Redwood Center for Theoretical Neuroscience, University of California at Berkeley, Berkeley, CA 94720 USA
-
visa fler...
-
- Wiklund, Urban (författare)
- Umeå universitet,Radiofysik,Department of Radiation Sciences, Biomedical Engineering, Umeå University, 901 87 Umeå, Sweden
-
- Osipov, Evgeny (författare)
- Luleå tekniska universitet,Datavetenskap
-
visa färre...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers Inc. 2021
- 2021
- Engelska.
-
Ingår i: IEEE Transactions on Neural Networks and Learning Systems. - : Institute of Electrical and Electronics Engineers Inc.. - 2162-237X .- 2162-2388. ; 32:8, s. 3777-3783
- Relaterad länk:
-
https://arxiv.org/ab...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- The deployment of machine learning algorithms on resource-constrained edge devices is an important challenge from both theoretical and applied points of view. In this brief, we focus on resource-efficient randomly connected neural networks known as random vector functional link (RVFL) networks since their simple design and extremely fast training time make them very attractive for solving many applied classification tasks. We propose to represent input features via the density-based encoding known in the area of stochastic computing and use the operations of binding and bundling from the area of hyperdimensional computing for obtaining the activations of the hidden neurons. Using a collection of 121 real-world data sets from the UCI machine learning repository, we empirically show that the proposed approach demonstrates higher average accuracy than the conventional RVFL. We also demonstrate that it is possible to represent the readout matrix using only integers in a limited range with minimal loss in the accuracy. In this case, the proposed approach operates only on small ${n}$ -bits integers, which results in a computationally efficient architecture. Finally, through hardware field-programmable gate array (FPGA) implementations, we show that such an approach consumes approximately 11 times less energy than that of the conventional RVFL.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Density-based encoding
- hyperdimensional computing
- random vector functional link (RVFL) networks
- Encoding (symbols)
- Field programmable gate arrays (FPGA)
- Learning algorithms
- Machine learning
- Network coding
- Stochastic systems
- Classification tasks
- Computationally efficient
- Field-programmable gate array implementations
- Functional links
- Hidden neurons
- Resource-efficient
- Stochastic computing
- UCI machine learning repository
- Neural networks
- Dependable Communication and Computation Systems
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas