Towards Hardware Optimal Neural Network Selection with Multi-Objective Genetic Search
Name:
ISCAS2020_netwrok_selection_genetic.pdf
Size:
5.903Mb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionElectrical Engineering Program
Sensors Lab
Date
2020-09-29Online Publication Date
2020-09-29Print Publication Date
2020-10Permanent link to this record
http://hdl.handle.net/10754/665484
Metadata
Show full item recordAbstract
The selection of hyperparameters and circuit components for optimum hardware implementation of a neural network is a challenging task, which has not been automated yet. This work proposes the method for the selection of optimum neural network architecture and hyperparameters using genetic algorithm based on the hardware-related performance metrics, such an on-chip area, power consumption, processing time and robustness to hardware non-idealities, and focus on memristor-based analog network architecture. The experimental results show that the proposed approach allows to select the optimum architecture based on the designers' preferences.Citation
Krestinskaya, O., Salama, K., & James, A. P. (2020). Towards Hardware Optimal Neural Network Selection with Multi-Objective Genetic Search. 2020 IEEE International Symposium on Circuits and Systems (ISCAS). doi:10.1109/iscas45731.2020.9180514Conference/Event name
2020 IEEE International Symposium on Circuits and Systems (ISCAS)ISBN
978-1-7281-3321-8Additional Links
https://ieeexplore.ieee.org/document/9180514/https://ieeexplore.ieee.org/document/9180514/
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9180514
ae974a485f413a2113503eed53cd6c53
10.1109/ISCAS45731.2020.9180514