Unsupervised learning and clustered connectivity enhance reinforcement learning in spiking neural networks
bioRxiv (Cold Spring Harbor Laboratory)
Abstract
ABSTRACT Reinforcement learning is a learning paradigm that can account for how organisms learn to adapt their behavior in complex environments with sparse rewards. However, implementations in spiking neuronal networks typically rely on input architectures involving place cells or receptive fields. This is problematic, as such approaches either scale badly as the environment grows in size or complexity, or presuppose knowledge on how the environment should be partitioned. Here, we propose a learning architecture that combines unsupervised learning on the input projections with clustered connectivity within the representation layer. This combination allows input features to be mapped to clusters; thus the network self-organizes to produce task-relevant activity patterns that can serve as the basis for reinforcement learning on the output projections. On the basis of the MNIST and Mountain Car tasks, we show that our proposed model performs better than either a comparable unclustered network or a clustered network with static input projections. We conclude that the combination of unsupervised learning and clustered connectivity provides a generic representational substrate suitable for further computation.
Authors 3
-
RWTH Aachen University · Forschungszentrum Jülich · Jülich Aachen Research Alliance
Affiliation as printed
Computer Science 3 - Software Engineering RWTH Aachen, Germany
Institute for Advanced Simulation (IAS-6) & Institute of Neuroscience and Medicine (INM-6) & JARA-Institute Brain Structure Function Relationship (JBI 1 / INM-10). Research Centre Jülich, Jülich, Germany
Institute for Advanced Simulation (IAS-6) & Institute of Neuroscience and Medicine (INM-6) & JARA-Institute Brain Structure Function Relationship (JBI / INM-0). Research Centre Jülich, Jülich, Germany
-
Renato Duarte corresponding
Forschungszentrum Jülich · Jülich Aachen Research Alliance
Affiliation as printed
Institute for Advanced Simulation (IAS-6) & Institute of Neuroscience and Medicine (INM-6) & JARA-Institute Brain Structure Function Relationship (JBI 1 / INM-10). Research Centre Jülich, Jülich, Germany
Institute for Advanced Simulation (IAS-6) & Institute of Neuroscience and Medicine (INM-6) & JARA-Institute Brain Structure Function Relationship (JBI / INM-0). Research Centre Jülich, Jülich, Germany
-
RWTH Aachen University · Forschungszentrum Jülich · Jülich Aachen Research Alliance
Affiliation as printed
Computer Science 3 - Software Engineering RWTH Aachen, Germany
Institute for Advanced Simulation (IAS-6) & Institute of Neuroscience and Medicine (INM-6) & JARA-Institute Brain Structure Function Relationship (JBI 1 / INM-10). Research Centre Jülich, Jülich, Germany
Simulation Laboratory Neuroscience – Bernstein Facility for Simulation and Database Technology
Institute for Advanced Simulation (IAS-6) & Institute of Neuroscience and Medicine (INM-6) & JARA-Institute Brain Structure Function Relationship (JBI / INM-0). Research Centre Jülich, Jülich, Germany
Cited by 1 stored of 1
1 result
No patents citing this paper on Lens.org (checked 2026-10-06).