4 papers
Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics
Jie Mei, Alejandro Rodriguez-Garcia, Daigo Takeuchi +4
Continuous, adaptive learning, the ability to adapt to the environment and keep improving performance, is a hallmark of natural intelligence. Biological organisms excel in acquirin…
Dynamic gain neuromodulation attenuates the stability gap under joint training
Alejandro Rodriguez-Garcia, Anindya Ghosh, Srikanth Ramaswamy
Recent work in continual learning has highlighted the stability gap -- a temporary performance drop on previously learned tasks when new ones are introduced. This phenomenon reflec…
Augmenting learning in neuro-embodied systems through neurobiological first principles
Alejandro Rodriguez-Garcia, Anindya Ghosh, Jie Mei +1
Recent progress in artificial intelligence (AI) has been driven by insights from physics and neuroscience, particularly through the development of artificial neural networks (ANNs)…
The role of gain neuromodulation in layer-5 pyramidal neurons
Alejandro Rodriguez-Garcia, Christopher J. Whyte, Brandon R. Munn +3
Biological and artificial learning systems alike confront the plasticity-stability dilemma. In the brain, neuromodulators such as acetylcholine and noradrenaline relieve this tensi…