Talks and presentations

Synaptic Plasticity Dynamics for Deep Continuous Local Learning

October 02, 2019

Talk, Computational and Systems Neuroscience (Cosyne), Lisbon, Portugal

Understanding and deriving neural and synaptic plasticity rules that can enable hidden weights to learn is an ongoing quest in neuroscience and neuromorphic engineering. From a machine learning perspective, locality and differentiability are key issues of the spiking neuron model operations. In this poster presentation, it is shown that deep learning algorithms that locally approximate the gradient backpropagation updates using locally synthesized gradients overcome this challenge.

Neurorobotics: an artificial body for an artificial brain

May 14, 2018

Talk, Pint of Science, Le Shadok, Strasbourg

The goal of pint of science is to explain and discuss the latest scientific results with the public. In this set of talks dedicated to intelligence, I explained artificial neural networks in Layman’s terms and their use in robotics.

Learning Movements by Imitation from Event-Based Visual Prediction

February 15, 2018

Talk, 2nd HBP Student Conference, Central Post Office, Ljubljana, Slovenia

In this talk, I introduce a new method for robots to learn movements from visual prediction. The method consists of two phases: learning a visual prediction model for a given movement, then minimizing the visual prediction error. The visual prediction model is learned from a single demonstration of the movement where only visual input is sensed.