Skip to main content

CNS*2025 Workshop "Brains and AI"

Introduction

Advances in neuroscience techniques have dramatically increased the volume of data we can now collect from animal and human brains. However, this surge in data has introduced new challenges in extracting meaningful insights. Fortunately, these developments have coincided with breakthroughs in artificial intelligence (AI), which holds the potential to transform how we analyze and utilize scientific information. While there is significant potential here, we are just starting to figure out how to apply modern AI models to interpret and process scientific data, and significant challenges remain. The trend of applying AI to better understand the brain concurs with another reviving trend: applying knowledge from neuroscience to developing new AI. Indeed, despite the tremendous progress, the existing generation of AI shows significant limitations, including a lack of continual learning, poor generalization, dependence on enormous amounts of data for training, bias, and safety problems. These are features where the biological brain excels, highlighting the strong need to learn once more from neuroscience how to develop the next generation of AI. The proposed workshop will combine these two complementary trends, bringing experts from the field together to discuss how AI can facilitate new scientific discoveries and how knowledge of the brain can help improve AI.

Schedule

Wednesday, 9 July 2025, Florence, Italy

Room: TBD

Time
Speaker Title
9:00-9:30 Fleur Zeldenrust Heterogeneity, non-linearity and dimensionality: how neuron and network properties shape computation
9:30-10:00 Vassilis Cutsuridis Synapse strengthening in bistratified cells leads to super memory retrieval in the hippocampus
10:00-10:30 Spyridon Chavlis Dendrites as nature's blueprint for a more efficient AI
10:30-11:00 Coffee Break
11:00-11:30 Andreas Tolias Foundation models and digital twins of the brain (online)
11:30-12:00 Robert Legenstein Spatio-Temporal Processing with Dynamics-enhanced Spiking Neural Networks
12:00-12:30 Max Garagnani Concept superposition and learning in standard and brain-constrained deep neural networks
12:30-14:00 Lunch
14:00-14:30 Martin Trefzer Motifs, Modules, and Mutations: Building Brain-like Networks
14:30-15:00 Julian Göltz From biology to silicon substrates: neural computation with physics
15:00-15:30 Maxim Bazhenov Do Neural Networks Dream of Electric Sheep?
15:30-16:00 Coffee Break
16:00-16:30 Dhireesha Kudithipudi Temporal Chunking Enhances Recognition of Implicit Sequential Patterns
16:30-17:00 Thomas Nowotny Auto-adjoint method for gradient descent in spiking neural networks
17:00-18:00 All Questions and Debate
18:00 End of Workshop