Computing with physics: from biological to artificial intelligence and back again
AI/Machine Learning/Deep Learning
Post Moore’s Law Computing
TimeTuesday, June 18th4:25pm - 4:45pm
DescriptionNeural networks are, once again, in the focus of both the artificial and the biological intelligence communities. Originally inspired by the dynamics and architecture of cortical networks, they have increasingly strayed away from their biological archetypes, prompting questions about their relevance for understanding the brain. However, their recent hardware-fueled dominance has motivated renewed efforts to align them with biologically more plausible models. In my talk, I will discuss some intriguing ideas about the physical instantiation of information processing in biologically inspired hierarchical neural networks and possible benefits that can be derived therefrom.