Abstract
Energy-efficiency and computation capability characteristics of analog/mixed-signal spiking neural networks offer capable platform for implementation of cognitive tasks on resource-limited embedded platforms. However, inherent mismatch in analog devices severely influence accuracy and reliability of the computing system. In this paper, we devise efficient algorithm for extracting of heterogeneous activation functions of analog hardware neurons as a set of constraints in an off-line training and optimization process, and examine how compensation of the mismatch effects influence synchronicity and information processing capabilities of the system.
Original language | English |
---|---|
Title of host publication | 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) |
Publisher | IEEE |
Pages | 244-245 |
Number of pages | 2 |
ISBN (Electronic) | 978-1-5386-7884-8 |
ISBN (Print) | 978-1-5386-7885-5 |
DOIs | |
Publication status | Published - 2019 |
Event | 1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 - Hsinchu, Taiwan Duration: 18 Mar 2019 → 20 Mar 2019 |
Conference
Conference | 1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 |
---|---|
Country/Territory | Taiwan |
City | Hsinchu |
Period | 18/03/19 → 20/03/19 |
Keywords
- activation functions
- deep neural network
- extraction
- mismatch
- spiking neural network
- training