Abstract

Biological neural networks excel at adapting and learning across diverse behavioural contexts. Artificial intelligence (AI) has drawn on neurobiological principles to address complex challenges. Yet, despite its success in specific tasks, AI lacks the flexibility and adaptability of biological cognition.

This symposium will integrate computational and experimental advancements to deepen our understanding of biological and artificial intelligence. This symposium brings together a diverse panel of scientists to synthesise how insights from biological intelligence can inspire next-generation AI. A panel discussion will examine how neuroscience can shape future AI development.

S. Chavlis will discuss how bioinspired artificial networks with dendritic features may address AI’s learning and efficiency challenges.

R. Cusack will highlight neurodevelopmental principles in AI for robust, human-like learning.

Y. Sandamirskaya will present brain-inspired architectures for neuromorphic hardware, enabling adaptive real-world tasks.

Together, these talks provide complementary perspectives, fostering dialogue to overcome key challenges in NeuroAI. This synergy between experiments and theory will catalyse next-generation NeuroAI and inform experimental neuroscience with innovative computational hypotheses, advancing both fields.