Biologically Inspired AI
Biologically inspired learning
10.2015 - 12.2019
The plasticity property is one of the fundamental property of Biological Neural Networks which allows them to change their configuration over lifetime. In this project, we aim to produce plasticity property in Artificial Neural Networks to allow lifetime leaning inspired by the Biological Neural Networks.
Keywords:
continual learning, lifetime learning, plastic networks
Results
Introducing plasticity property in Artificial Neural Networks to perform local synaptic changes based on neuron activations and reinforcement signals received after every action of the networks.
Based on:
Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions.
Evolutionary Computation. 2020.
DOI: 10.1162/evco_a_00286.
Introducing local heuristics to perform synaptic changes in Artificial Neural Networks based on delayed reinforcement signals.
Based on:
Learning with Delayed Synaptic Plasticity. In Proceedings of the GECCO 2019.