Introduction

The natural world consists of complex and dynamic sensory environments. Animals learn to navigate in and interact with these environments robustly and seemingly effortlessly, excelling at problems where learning must occur rapidly, computational resources are limited, and the learning problem changes over time. Even 'small'-brained animals like insects show complex learning abilities using very efficient brains of only up to 1 million neurons, 100,000 times fewer than in a human brain. This specialised learning is possible because natural intelligence evolved through brain-body-environment interactions resulting in specialised sensory systems and active behavioural strategies. In this workshop, we will explore how animal brains solve problems, and how AI can take inspiration from biological systems that have evolved specifically to solve problems flexibly and rapidly, and to adapt over the lifetime of an individual, whilst being computation- and energy-efficient. Topics will include computational models to explore how brain circuits can solve problems and how this creates new hypotheses to explore experimentally. We will also examine how this can contribute to solving problems in autonomous robotics and provide inspiration for other AI applications.

Schedule

Wednesday, 24 July 2024, Praiamar Natal Hotel & Convention, Natal Brazil

Room: Cedro V

Time	Speaker	Title
9:00-9:25	Daniel Yasumasa Takahashi	Stochastic dynamical systems model of vocal turn-taking and its development in marmoset monkeys
9:25-9:50	Marcelo Bussotti Reyes	Temporal Decoding Dynamics: Insights from Prefrontal Cortex and Striatum During Rapid Learning
9:50-10:15	Rachael Stentiford	Insect visual navigation in natural scenes: Maintaining head direction estimates with a spiking neural network model of the central complex and active behavioural strategies
10:20-10:50		Coffee Break
10:50-11:15	Renan Moioli	A Neurorobotics Model of the Cerebellar-Basal Ganglia Circuitry: decision making and motor control in healthy and diseased states
11:15-11:40	Thomas Nowotny	Training Spiking Neural Networks for keyword recognition with Eventprop in GeNN
11:40-12:30	All	Questions and Debate
12:30		End of Workshop and Lunch Break