SenTer: A Reconfigurable Processing-in-Sensor Architecture Enabling Efficient Ternary MLP
Document Type
Conference Proceeding
Publication Date
6-5-2023
Abstract
Recently, Intelligent IoT (IIoT), including various sensors, has gained significant attention due to its capability of sensing, deciding, and acting by leveraging artificial neural networks (ANN). Nevertheless, to achieve acceptable accuracy and high performance in visual systems, a power-delay-efficient architecture is required. In this paper, we propose an ultra-low-power processing in-sensor architecture, namely SenTer, realizing low-precision ternary multi-layer perceptron networks, which can operate in detection and classification modes. Moreover, SenTer supports two activation functions based on user needs and the desired accuracy-energy trade-off. SenTer is capable of performing all the required computations for the MLP's first layer in the analog domain and then submitting its results to a co-processor. Therefore, SenTer significantly reduces the overhead of analog buffers, data conversion, and transmission power consumption by using only one ADC. Additionally, our simulation results demonstrate acceptable accuracy on various datasets compared to the full precision models.
Identifier
85163180170 (Scopus)
ISBN
[9798400701252]
Publication Title
Proceedings of the ACM Great Lakes Symposium on VLSI Glsvlsi
External Full Text Location
https://doi.org/10.1145/3583781.3590225
First Page
497
Last Page
502
Grant
2216772
Fund Ref
National Science Foundation
Recommended Citation
Tabrizchi, Sepehr; Gaire, Rebati; Angizi, Shaahin; and Roohi, Arman, "SenTer: A Reconfigurable Processing-in-Sensor Architecture Enabling Efficient Ternary MLP" (2023). Faculty Publications. 1669.
https://digitalcommons.njit.edu/fac_pubs/1669