Biologically Inspired Continual Learning for Artificial Intelligence

While Machine Learning algorithms have in recent years seen great progress, there are still scenarios in which they fail to be as robust and flexible as animals and humans.

Image may contain: Product, Font, Line, Rectangle, Parallel.

One such scenario is continual or lifelong learning, in which a model experiences a sequential stream of training episodes and needs to adjust to novel tasks while still performing well on the previous ones. The main goal of this project is to draw from mechanisms that enable continual learning in biological agents and use them as an inspiration for novel methods of improving continual learning in artificial neural networks.

Tags: Machine Learning/Artificial Intelligence, Bayesian machine learning, Image Processing, Reinforcement learning, Robotics
Published Jan. 22, 2024 11:59 AM - Last modified Jan. 22, 2024 11:59 AM