ELECTRON (Evolutionary LEarning and Compressed TRaining Of Neural networks) is an INRIA Associate Team between the COATI EP at INRIA UniCA and the Algorithms and Data Analysis goup at King’s College London. The team is lead by Emanuele Natale at UniCA and Frederik Mallmann-Trenn at KCL.
The ELECTRON team focuses on understanding the role of topology in neural networks and the principles behind their efficient design. Motivated and inspired by insights from evolutionary neuroscience, on the one hand, and by the goal of improving the efficiency of deep learning techniques, on the other, the team aims to combine theoretical insights on artificial neural network sparsification and compression. To this end, our initial focus is to (i) establish rigorous guarantees for “training-by-pruning” heuristics in the context of the Strong Lottery Ticket Hypothesis, and (ii) investigate evolutionary frameworks for network topology learning. This integrated approach seeks not only to advance the theory of sparse neural architectures but also to catalyze novel interdisciplinary collaborations between computer scientists and neuroscientists.
Team members in Sophia Antipolis
- Emanuele Natale (team leader in France)
- Frederic Giroire
PhD students
Team members in London
- Frederik Mallmann-Trenn (team leader in UK)
- Mattia Jacopo Villani (associate member at J.P. Morgan)
- Frank Hirth
