Unsupervised learning of visual representations using delay-weight spike-timing-dependent plasticity
| Autor: | Adrien Fois, Horacio Rostro-Gonzalez, Bernard Girau |
|---|---|
| Přispěvatelé: | Bio-Inspired, Situated and Cellular Unconventional Information Technologies (BISCUIT), Department of Complex Systems, Artificial Intelligence & Robotics (LORIA - AIS), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Guanajuato University, ANR-17-CE24-0036,SOMA,Auto-organisation dans les architectures matérielles neuromorphiques(2017) |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | IEEE WCCI 2022-INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) 2022 International Joint Conference on Neural Networks (IJCNN) 2022 International Joint Conference on Neural Networks (IJCNN), Jul 2022, Padua, Italy. ⟨10.1109/IJCNN55064.2022.9892486⟩ |
| DOI: | 10.1109/IJCNN55064.2022.9892486⟩ |
| Popis: | International audience; Unsupervised learning in Spiking Neural Networks (SNN) is performed by adjusting the synaptic parameters with spike-timing-dependent plasticity rules (STDP), that leverage the firing times of neurons. Commonly the targetted parameters are limited to synaptic weights. However, recent empirical evidences suggest that synaptic delays are not fixed, but plastic parametersaffecting the firing time of neurons. The firing times are crucials as biological evidence strongly supports that information is carried in the temporal domain, through precise spike timing. Unlike weights, delays intrinsically operate in the temporal domain.Thus, delays can serve as a meaningful way to compute and learn for living and artificial systems. In this regard, this work proposes novel STDP rules to learn delays and weights in a SNNin order to extract visual representations. These representations are learned from patterns of spikes that encode images in the relative spike timing. One STDP rule adjusts the delays, anotherone the weights. The rules operate locally both in space and time, making them biologically plausible and neuromorphicfriendly. The model is evaluated on natural images. Numerical experimental results demonstrate state-of-the-art performances in terms of reconstruction error. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|