CNS*2022 Workshop on Bio-inspired active AI
Introduction
Recent advances in AI and notably in deep learning, have proven incredibly successful in creating solutions to specific complex problems (e.g. beating the best human players at Go, and driving cars through cities). But as we learn more about these approaches, their limitations are becoming more apparent in terms of high energy consumption, fragility, and lack of transferability between tasks.
These limitations are particularly apparent when contrasted with naturally evolved intelligence. While no animals can play Go or drive cars, they are incredibly good at doing what they have evolved to do. For instance, ants learn how to forage effectively despite their tiny brains and minimal exploration of their world. We argue this difference comes about because natural intelligence is a property of closed-loop brain-body-environment interactions. Evolved innate behaviours in concert with specialised sensors and neural circuits extract and encode task-relevant information with maximal efficiency, aided by mechanisms of selective attention that focus learning on task-relevant features.
In this workshop, we will explore how we can learn from mini-brains, and computational models to better understand intelligence and pave the pathway to building better AI.
Schedule
Wednesday, 20 July 2022 , Melbourne Convention Centre
Room: TBD