Jul 2026· GECCO Companion· pp. 557-560· 0 citations· 18 references
Computer Science
TL;DR
It is found that using synaptic weight as inputs has no effect on rule performance, while utilising either pre-before-post or post-before-pre eligibility trace is better than a trace that combines both.
Abstract
Neuroevolution can indirectly train a neural network by optimising the underlying plasticity rules that adapt the network weights. In Spiking Neural Networks (SNNs), evolvable meta-learning studies have been applied to unsupervised learning settings. In our experiment, we let evolution search for rules that can train an SNN to solve a Reinforcement Learning maze. These rules are encoded as an Artificial Neural Network (ANN), taking as inputs synaptic variables such as weight, reward and eligibility traces. We found that using synaptic weight as inputs has no effect on rule performance, while utilising either pre-before-post or post-before-pre eligibility trace is better than a trace that combines both. Although there is still too much variation in fitness both within individuals and across generations to allow for conclusive results, there is potential for evolving plasticity rules to solve RL tasks in the future.
A biologically inspired training framework that incorporates multiple synergistic plasticity mechanisms for more effective SNN training that enables diverse learning algorithms to cooperatively modulate the accumulation of information, while allowing each mechanism to preserve its own relatively independent update dyna...
These results demonstrate that spiking navigation circuits can learn goal-directed behavior using local plasticity, but robust multi-goal learning benefits from context-specific evidence-based consolidation.
Samuel A Neymotin, Hananel Hazan, Gozde Unal et al.· Research Square· 0 citations
This work presents a Hebbian local learning rule that models synaptic modification as a function of calcium traces tracking neuronal activity and demonstrates how spike timing and rate can be complementary in their role of shaping the connectivity of spiking neural networks.
Willian Soares Girāo, Nicoletta Risi, Caroline Geisler et al.· Neuromorphic Computing and E...· 0 citations
NeuMoSync is introduced, a novel architecture that integrates dynamic, neuron-specific modulation into deep neural networks to enhance their adaptability and plasticity and demonstrates strong performance in retaining plasticity and achieves improvements in both forward and backward adaptation compared with existing me...
The Spiking Actor Network Soft Actor Critic (SANSAC) is proposed to address the use of RL frameworks in continuous environments, designed as a framework that can be implemented on neuromorphic hardware.
J. Hunter, Md. Maruf Hossain Shuvo, Krishna Roy· 0 citations
The Context-modulated Synaptic-states Recurrent Neural Network (CoSyn-RNN), a new continual-learning model inspired by heterogeneous synaptic states and neuro-modulatory control, is introduced, in which protected synaptic states, sparse allocation, and context-dependent modulation support continual learning.
Yuan Gao, S. Mihalas, Denis Turcu· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
