If you are looking for recordings of previous talks, visit this website instead.

You will need to login with a Mila account to access the recordings.

Upcoming Talks

To be announced!

Previous Talks

December 1, 2023

Serotonin predictively encodes value

Speaker: Emerson Harkin


November 6, 2023

Human cortical cultures and artificial models: Understanding individuals with epilepsy

Speaker: Chris Currin


October 27, 2023

Principles of Network Plasticity in Neocortical Microcircuits

Speaker: Michael Reimann


August 25, 2023

Linking body and mind: the MyoChallenge 2023 (A NeurIPS 2023 Competition)

Speaker: Guillaume Durandau


August 18, 2023

Geometry of neural networks with biological structure: Randomness vs. structure and learning

Speaker: Kameron Decker Harris


August 11, 2023

Semantic scene descriptions as an objective of human vision

Speaker: Adrien Doerig


June 23, 2023

A theory of representation learning gives a deep generalisation of kernel methods, and implications for the brain

Speaker: Laurence Aitchison


June 2, 2023

Architectural foundations of flexible, robust and efficient cognitive motor control

Speaker: Laureline Logiaco


May 12, 2023

Network inference via process motifs for lagged correlation in linear stochastic processes 

Speaker: Alice Schwarze


April 28, 2023

Deep Active Inference

Speaker: Noor Sajid


February 24, 2023

Representational Dissimilarity Metric Spaces for Stochastic Neural Networks

Speaker: Lyndon Duong


January 27, 2023

α-ReQ: Assessing Representation Quality in Self-Supervised Learning by measuring eigenspectrum decay

Speaker: Arna Ghosh


November 18, 2022

AI for neuroscience: data-driven models of information processing and learning

Speaker: Guillaume Bellec


November 11, 2022

Dopaminergic Reinforcement Learning Models for High-Dimensional Tasks

Speaker: Rachel Lee


October 28, 2022

AI for brain interfaces: challenges and opportunities (Special talk organized with support from UNIQUE)

Speaker: Philip Sabes


October 21, 2022

Modelling neural control of motion stabilization using recurrent neural networks

Speaker: Olivier Codol


October 14, 2022

Biological reinforcement learning in hippocampus

Speaker: Tom George


October 7, 2022

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules

Speaker: Helena Liu


September 16, 2022

Multi-Object Representation and Prediction in the Primate Brain

Speaker: Nicholas Watters


September 9, 2022

Characterizing Mental Representations using Deep Image Synthesis and Behavior

Speaker: Laurent Caplette


April 22, 2022

Neural representations of active vision

Speaker: Elliott Abe


April 8, 2022

System 2 GFlowNets and System 2 Cognitive Neuroscience

Speaker: Yoshua Bengio


February 11, 2022

When to retrieve and encode episodic memories: a neural network model of hippocampal-cortical interaction

Speaker: Qihong Lu


February 4, 2022

On biological plausibility of weight sharing

Speaker: Roman Pogodin


January 28, 2022

Learning Hierarchical Temporal Representations through Dynamic Predictive Coding

Speaker: Preston Jiang 


January 21, 2022

Welcome Event, Winter 2022

Speakers: Blake Richards, Doina Precup, Guillaume Lajoie, Irina Rish, Karim Jerbi, Eilif Muller, Guillaume Dumas, Pouya Bashivan


November 19, 2021

Lifelong Learning: Theory and Practice 

Speaker:  Joshua T. Vogelstein


November 12, 2021

Structure, Function, and Learning in Distributed Neuronal Networks

Speaker:  SueYeon Chung


October 15, 2021

Distributed TD Learning in a Heterogeneous Dopamine System

Speaker:  Pablo Tano


October 1, 2021

The story of a recurrent neural network’s training from initialization to task mastery

Speaker:  Owen Marschall


September 17, 2021

Visual Routines in brains and machines

Speaker:  Drew Linsley


June 25, 2021

A rapid and efficient learning rule for biological neural circuits

Speaker:  Agnieszka Grabska-Barwińska


June 4, 2021

Vision as Bayesian inference: promise and pitfalls

Speaker:  Richard Lange

May 21, 2021

Creative memory semantization through adversarial dreaming

Speaker:  Nicolas Deperrois


May 7, 2021

The computational origin of human representation

Speaker:  Steven Piantadosi


April 23, 2021

A unique coding of memories in the human brain

Speaker:  Rodrigo Quian Quiroga


April 9, 2021

Context-gated Feature Representations for Multi-Task Learning in Humans and Neural Networks.

Speaker:  Timo Flesch


March 26, 2021

Impression learning: online predictive coding with synaptic plasticity

Speaker:  Colin Bredenberg


March 12, 2021

What songbirds can tell us about reinforcement learning

Speaker:  Anja Zai


February 5, 2021

Temporal credit assignment with eligibility traces and predictions

Speaker: Guillaume Bellec


January 22, 2021

A diversity of discounting horizons explains ramping diversity in dopamine-based reinforcement learning

Speaker: Paul Masset


January 15, 2021

Reward prediction errors shape memory during reinforcement learning

Speaker: Nina Rouhani


November 20, 2020

Inferring implicit inference (III)

Speaker: Xaq Pitkow


November 13, 2020

Exploring the Cognitive-Motor Interface

Speaker: John Krakauer


November 6, 2020

Unsupervised deep learning identifies semantic disentanglement in single inferotemporal face patch neurons

Speaker:  Irina Higgins


October 30, 2020

The Temporal Dynamics of Opportunity Costs: A Normative Account of Cognitive Fatigue and Boredom

Speaker: Mayank Agrawal


October 2, 2020

Replay slows down with experience

Speaker: Alice Berners-Lee


September 25, 2020

Behavioral algorithms: flexible, robust, and generalizable behavior in the natural world

Speaker: Andrew Hein


September 18, 2020

Prioritized experience replay supports planning and non-local learning

Speaker: Marcelo Mattar


September 11, 2020

Continual Reinforcement Learning with Memory at Multiple Timescales

Speaker: Christos Kaplanis


July 24, 2020

Computational mechanisms of selective attention during human reinforcement learning

Speaker: Angela Radulescu


July 10, 2020

Evidence for hierarchically-structured reinforcement learning in humans

Speaker: Maria Ekstein


July 3, 2020

The role of the hippocampus in memory and problem solving

Speaker: Signy Sheldon


June 25, 2020

Dynamic resource allocation during reinforcement learning accounts for ramping and phasic dopamine activity

Speaker: Minryung Song


June 19, 2020

Probabilistic successor representations allow for flexible behaviour

Speaker: Jesse Geerts


May 29, 2020

Prioritization of mental simulations for planning

Speaker: Emma Krause


May 15, 2020

Temporal and state abstractions for efficient learning, transfer and composition in humans 

Speaker: Jimmy Xia


May 8, 2020

Speaker: Samuel Nataste


April 24, 2020

How, when and why do we make reflective versus reflexive choices

Speaker: Ross Otto


March 27, 2020

NeuroQuery: predictive meta-analysis of the neuroimaging literature

Speaker: Jérôme Dockès


February 28, 2020

Towards New AI: Feeling Machines, Homeostatically Motivated Intelligence and Scale-free Cognition

Speaker: Irina Rish


February 14, 2020

A reductionist approach to interpreting neural networks that learn

Speaker: Matthew Farrell


January 31, 2020

Speaker: Maximilian Puelma Touzel


January 31, 2020

Half-Day Workshop on Neural Backpropagation

Speakers: Blake Richards, Irina Rish, Gaël Varoquaux, Yoshua Bengio


November 8, 2019

Inhibitory microcircuits for top-down plasticity of sensory representations

Speaker: Katharina Wilmes


November 1, 2019

Synergy between AI and Neuroscience

Speaker: Irina Rish


October 25, 2019

Dynamics of information transformation within a cortical circuit

Speaker: Arjun Bharioke


October 4, 2019

Amplifying the Neural Power Spectrum

Speaker: Andrew Doyle


September 20, 2019

Continuation of Biological and Artificial RL

Speaker: Raymond Chua


August 16, 2019

Neural population control via deep image synthesis

Speaker: Leila Wehbe


Reach out to us at neuralai.montreal@gmail.com if you have any questions!© 2023 The Mila Neural-AI Reading Group. The placeholder images were generated using Stable Diffusion.