Sökning: id:"swepub:oai:DiVA.org:mdh-48126" >
Multi-level Binariz...
Multi-level Binarized LSTM in EEG Classification for Wearable Devices
-
- Nazari, N. (författare)
- University of Tehran, School of Electrical and Computer Engineering, Tehran, Iran
-
- Sinaei, Sima (författare)
- University of Tehran, School of Electrical and Computer Engineering, Tehran, Iran,Malardalen University, Division of Intelligent Future Technologies, Vasteras, Sweden
-
- Sinaei, Sima (författare)
- Malardalen University, Division of Intelligent Future Technologies, Vasteras, Sweden
-
visa fler...
-
- Salehi, M. E. (författare)
- University of Tehran, School of Electrical and Computer Engineering, Tehran, Iran
-
- Daneshtalab, Masoud (författare)
- Mälardalens högskola,Inbyggda system,Mälardalen University, Sweden
-
visa färre...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers Inc. 2020
- 2020
- Engelska.
-
Ingår i: Proceedings - 2020 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2020. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728165820 ; , s. 175-181
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Long Short-Term Memory (LSTM) is widely used in various sequential applications. Complex LSTMs could be hardly deployed on wearable and resourced-limited devices due to the huge amount of computations and memory requirements. Binary LSTMs are introduced to cope with this problem, however, they lead to significant accuracy loss in some applications such as EEG classification which is essential to be deployed in wearable devices. In this paper, we propose an efficient multi-level binarized LSTM which has significantly reduced computations whereas ensuring an accuracy pretty close to full precision LSTM. By deploying 5-level binarized weights and inputs, our method reduces area and delay of MAC operation about 31× and 27× in 65nm technology, respectively with less than 0.01% accuracy loss. In contrast to many compute-intensive deep-learning approaches, the proposed algorithm is lightweight, and therefore, brings performance efficiency with accurate LSTM-based EEG classification to realtime wearable devices.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorteknik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Engineering (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Nyckelord
- Binarization
- Embedded Systems
- Long Short -Term Memory (LSTM)
- Deep learning
- Wearable technology
- 65-nm technologies
- EEG classification
- Learning approach
- Limited devices
- Memory requirements
- Performance efficiency
- Sequential applications
- Wearable devices
- Long short-term memory
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas