Abstract
Recurrent neural networks trained with the backpropagation through time (BPTT) algorithm have led to astounding successes in various temporal tasks. However, BPTT introduces severe limitations, such as the requirement to propagate information backwards through time, the weight symmetry requirement, as well as update-locking in space and time. These problems become roadblocks for AI systems where online training capabilities are vital. Recently, researchers have developed biologically-inspired training algorithms, addressing a subset of those problems. In this work, we propose a novel learning algorithm called online spatio-temporal learning with target projection (OSTTP) that resolves all aforementioned issues of BPTT. In particular, OSTTP equips a network with the capability to simultaneously process and learn from new incoming data, alleviating the weight symmetry and update-locking problems. We evaluate OSTTP on two temporal tasks, showcasing competitive performance compared to BPTT. Moreover, we present a proof-of-concept implementation of OSTTP on a memristive neuromorphic hardware system, demonstrating its versatility and applicability to resource-constrained AI devices.
Original language | English |
---|---|
Title of host publication | AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
ISBN (Electronic) | 9798350332674 |
DOIs | |
Publication status | Published - 2023 |
Event | 5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023 - Hangzhou, China Duration: 11 Jun 2023 → 13 Jun 2023 |
Publication series
Name | AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding |
---|
Conference
Conference | 5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023 |
---|---|
Country/Territory | China |
City | Hangzhou |
Period | 11/06/23 → 13/06/23 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Keywords
- bio-inspired training
- neuromorphic hardware
- Online learning
- phase-change memory
- update locking