Print Email Facebook Twitter Online Spatio-Temporal Learning with Target Projection Title Online Spatio-Temporal Learning with Target Projection Author Ortner, Thomas (Zurich Lab) Pes, Lorenzo (Zurich Lab) Gentinetta, Joris (Zurich Lab; ETH Zürich) Frenkel, C. (TU Delft Electronic Instrumentation) Pantazi, Angeliki (Zurich Lab) Date 2023 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. Subject bio-inspired trainingneuromorphic hardwareOnline learningphase-change memoryupdate locking To reference this document use: http://resolver.tudelft.nl/uuid:451c0573-a37d-477e-b97e-f9a6e329ea2c DOI https://doi.org/10.1109/AICAS57966.2023.10168623 Publisher IEEE Embargo date 2024-01-08 ISBN 9798350332674 Source AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding Event 5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023, 2023-06-11 → 2023-06-13, Hangzhou, China Series AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding 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-care Otherwise 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. Part of collection Institutional Repository Document type conference paper Rights © 2023 Thomas Ortner, Lorenzo Pes, Joris Gentinetta, C. Frenkel, Angeliki Pantazi Files PDF Online_Spatio_Temporal_Le ... ection.pdf 1.36 MB Close viewer /islandora/object/uuid:451c0573-a37d-477e-b97e-f9a6e329ea2c/datastream/OBJ/view