Sökning: id:"swepub:oai:DiVA.org:kth-216527" >
A multiplication re...
A multiplication reduction technique with near-zero approximation for embedded learning in IoT devices
-
Huan, Y. (författare)
-
Qin, Y. (författare)
-
- You, Yantian (författare)
- KTH
-
visa fler...
-
- Zheng, Lirong (författare)
- KTH,Integrerade komponenter och kretsar,Fudan University, China
-
- Zou, Zhuo (författare)
- KTH,Fudan University, China
-
visa färre...
-
(creator_code:org_t)
- IEEE Computer Society, 2017
- 2017
- Engelska.
-
Ingår i: International System on Chip Conference. - : IEEE Computer Society. - 9781509013661 ; , s. 102-107
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- This paper presents a multiplication reduction technique through near-zero approximation, enabling embedded learning in resource-constrained IoT devices. The intrinsic resilience of neural network and the sparsity of data are identified and utilized. Based on the analysis of leading zero counting and adjustable threshold, intentional approximation is applied to reduce near-zero multiplications. By setting the threshold of the multiplication result to 2-5 and employing ReLU as the neuron activation function, the sparsity of the CNN model can reach 75% with negligible loss in accuracy when recognizing the MNIST data set. Corresponding hardware implementation has been designed and simulated in UMC 65nm process. It can achieve more than 70% improvement of energy efficiency with only 0.37% area overhead of a 256 Multiply-Accumulator array.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering (hsv//eng)
Nyckelord
- Energy efficiency
- Hardware
- Programmable logic controllers
- Area overhead
- CNN models
- Data set
- Embedded learning
- Hardware implementations
- Multiply accumulators
- Neuron activation function
- Reduction techniques
- Internet of things
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas