Biologically plausible learning in artificial neural networks


Mattia Della Vecchia | Ecole Normale Supérieure, France
Leonardo Agueci | Ecole Normale Supérieure, France


Artificial neural networks have been a crucial tool in neuroscience to understand brain functions, and major advances in artificial intelligence have led to methods that excel in a wide range of specific tasks, sometimes outperforming animal capabilities. Yet these systems do not show characteristic elements of animal intelligence, such as adaptability to new situations, transfer of knowledge across different tasks, or generalization from limited observations. On the other hand, our understanding of how the brain acquires these mechanisms is still limited, and this makes unclear the direction that should be taken moving forward. Some researchers argue that it is important to enrich artificial neural networks with biological components to study the underlying processes in the brain, while others are sceptical, highlighting the differences between the two. The debate revolves around questions like what levels of biological abstraction are possible, why we should take biological plausibility into consideration, or which biological elements are the most important to include. The goal of the workshop is to bring together experts that work on expanding our comprehension of neural computations and learning mechanisms, in order to foster a discussion on how biological constraints in computational models can provide neuroscientists with insights into brain functions, and how these insights could influence future developments of artificial neural networks.

The workshop will be divided into two mini-sessions, each one followed by a panel discussion, which themes will be: Day 1) Plasticity and learning rules Day 2) Biological plausible components in neural network modeling.

Schedule (CEST)

Tuesday, Sept 26


Julijana Gjorgjieva | Technical University of Munich, Germany
Stable and flexible learning with biologically plausible plasticity rules


Guillaume Bellec | Swiss Federal Institute of Technology, Lausanne, Switzerland
Hypothesis: Change prediction error gates plasticity in sensory cortices


Dhruva Raman | University of Sussex, UK 
Neural circuit architectures for learning in unpredictably changing environments: lessons from the mushroom body


30 min coffee break


Cristina Savin | New York University, USA
Normative models of synaptic plasticity


Katharina A. Wilmes (tbc)| University of Bern, Switzerland
Uncertainty-modulated prediction errors in cortical microcircuits


End of first day

Wednesday, Sept 27


Claudia Clopath | Imperial College London, UK
Embedding stochastic dynamics of the environment in spontaneous activity by prediction-based plasticity


Rui Ponte Costa | University of Bristol, UK
AI-driven brain-wide credit assignment


Naoki Hiratani | Harvard University, USA
Exploring simplicity bias and scalability of actor-critic learning in shallow neural network


30 min coffee break


Jonathan Cornford | McGill University, Canada
Learning using brain-inspired geometries


Ida Mommenejad | Microsoft Research, USA
Learning to model-free mechanisms