지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 대한전자공학회 IEIE Transactions on Smart Processing & Computing IEIE Transactions on Smart Processing & Computing Vol.9 No.3
- 발행연도
- 2020.6
- 수록면
- 252 - 259 (8page)
- DOI
- 10.5573/IEIESPC.2020.9.3.252
이용수
초록· 키워드
오류제보하기
Inherent error resilience in neuromorphic computing allows remarkable power and energy savings by exploiting approximate computing. This paper presents approximate digital leaky integrate-and-fire (LIF) neurons that leverage the approximate adders for energy efficient spiking neural networks (SNNs). Various approximate adder architectures were assessed and adopted in designing a digital LIF neuron. To demonstrate the performance of the approximate LIF neurons, a two-layer SNN with more than 1,000 digital neurons were used with the approximate adders. The results showed that the approximation errors of the lower-part OR adder (LOA) and optimized lower-part constant OR adder (OLOCA) do not affect the neuron’s spiking activities of the network significantly. In addition, they showed good power and energy efficiency. The results suggest that the LOA and OLOCA are more suitable for SNNs to achieve power- and energyefficient neuromorphic computing than the other approximate adders.
목차
Abstract
1. Introduction
2. Approximate Adders
3. Performance of Approximate Adders
4. Approximate Digital LIF Neuron
5. Experimental Results
6. Conclusion
References
참고문헌 (30)
참고문헌 신청
Y. Chen / 2018 / Neuromorphic Computing's Yesterday, Today, and Tomorrow – an Evolutional View / Integr., the VLSI J 61:49~61
F. Akopyan / 2015 / TrueNorth : Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip / IEEE Trans. Comput. -Aided Design of Integr. Circuits Syst 34:1537~1557
Y. Kim / 2015 / A Reconfigurable Digital Neuromorphic Processor with Memristive Synaptic Crossbar for Cognitive Computing / ACM J. Emerg. Technol. Comput. Syst 11(4):38:1~38:25
S. Mittal / 2016 / A Survey of Techniques for Approximate Computing / ACM Comput. Survey 48(4):62:1~62:33
M. Pashaeifar / 2018 / Approximate Reverse Carry Propagation Adder for Energy-Efficient DSP Applications / IEEE Trans. Very Large Scale. Integr. (VLSI)Syst 26(11):2530~2541
F. Akopyan / 2015 / TrueNorth : Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip / IEEE Trans. Comput. -Aided Design of Integr. Circuits Syst 34:1537~1557
Y. Kim / 2015 / A Reconfigurable Digital Neuromorphic Processor with Memristive Synaptic Crossbar for Cognitive Computing / ACM J. Emerg. Technol. Comput. Syst 11(4):38:1~38:25
S. Mittal / 2016 / A Survey of Techniques for Approximate Computing / ACM Comput. Survey 48(4):62:1~62:33
M. Pashaeifar / 2018 / Approximate Reverse Carry Propagation Adder for Energy-Efficient DSP Applications / IEEE Trans. Very Large Scale. Integr. (VLSI)Syst 26(11):2530~2541
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
정확도를 높인 Approximate Adder 설계
대한전자공학회 학술대회
2020 .08
-
Comparison of Approximate Computing with Sobel Edge Detection
IEIE Transactions on Smart Processing & Computing
2021 .08
-
An Accuracy Enhanced Error Tolerant Adder with Carry Prediction for Approximate Computing
IEIE Transactions on Smart Processing & Computing
2019 .08
-
Design of an Approximate Adder based on Modified Full Adder and Nonzero Truncation for Machine Learning
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
2023 .04
-
저전력 Approximate Floating Point Adder 설계
대한전자공학회 학술대회
2020 .08
-
Design and Analysis of a Low-cost Approximate Adder with OR and Zero Truncation
IEIE Transactions on Smart Processing & Computing
2021 .08
-
AND 기반의 캐리 예측 신호를 활용한 근사 가산기 설계
대한전자공학회 학술대회
2021 .06
-
Novel XNOR-based Approximate Computing for Energy-efficient Image Processors
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
2018 .10
-
활성화 함수를 시간적으로 근사하기 위한 스파이킹 뉴런 모델의 노이즈 주입에 따른 학습 성능 분석
대한전자공학회 학술대회
2024 .06
-
Spiking Neural Network(SNN)를 위한 Leaky Integrate and Fire(LIF) 모델의 뉴런을 모사한 180nm CMOS 아날로그 회로 구현
대한전자공학회 학술대회
2023 .06
-
근사 캐리 예측 기반의 오차 허용 가산기의 최근 연구 동향
전자공학회논문지
2021 .06
-
Analysis on Full Adder with Restoring Function in Nominal and Low Supply Voltage
대한전자공학회 학술대회
2017 .01
-
오류 감소 유닛을 적용한 새로운 8비트 근사 덧셈기와 이를 활용한 곱셈기 및 이미지 처리 응용
대한전자공학회 학술대회
2024 .11
-
A Novel Approximate Adder with Enhanced Low-cost Carry Prediction for Error Tolerant Computing
IEIE Transactions on Smart Processing & Computing
2019 .12
-
A Fast (7, 3)-adder Circuit for High-speed Multiplier Design
IEIE Transactions on Smart Processing & Computing
2022 .08
-
Design Optimization of a 4-2 Compressor for Low-cost Approximate Multipliers
IEIE Transactions on Smart Processing & Computing
2022 .12
-
Probabilistic based CMOS Adder for High Speed Communication Systems
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
2021 .04
-
Hardware Implementation of Integration-and-Fire Neuron Circuit on FPGA and Performance Evaluation for Applications in Spiking Neural Network
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
2025 .04
-
대형 Adder Tree 구조에 최적화된 덧셈기를 위한 효율적인 XOR 논리 회로 연구
대한전자공학회 학술대회
2021 .11
-
Neuron-Aware Training for IF neurons with non-linearity in Spiking Neural Networks
대한전자공학회 학술대회
2022 .06
이 논문의 저자 정보
이 논문과 함께 이용한 논문
LIF/IF Model을 활용한 SNN/CNN Accumulator의 H/W 구현
홍윤표
,
김희탁
,
전석훈
외 1명
전자공학회논문지
2022
.01
Brain Inspired Computing을 위한 Analog 회로 기반 Spiking Neural Network
오광일
,
이재진
전자공학회지
2020
.07
Hardware Implementation of the Simplified Digital Spiking Neural Network on FPGA
Kyungpil Lee
,
Youngmin Kim
IEIE Transactions on Smart Processing & Computing
2019
.10
하드웨어 기반 스파이킹 뉴럴 네트워크를 이용한 강화 학습 검증에 대한 연구
오민혜
,
장지수
,
박병국
대한전자공학회 학술대회
2018
.06
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2020-569-000684277