6. LightOn AI Meetup: Learning without Feedback

LightOn is a DeepTech company creating hardware for new AI applications requiring massive amount of data (molecular dynamics, fraud detection, conversational AI ...) . We gather experts, engineers, researchers, who are shaping the world of tomorrow. We are back for our 6th edition!

Our meetups will happen online in order to keep our attendees safe until further notice.

This event takes place at 16:00, Paris time (GTM +02:00)

A Zoom link will be provided prior to the meetup.

---
Agenda

16:00 – Introduction by LightOn

---

16:10 – "Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks"
by Charlotte Frenkel, Postdoctoral researcher @ Institute of Neuroinformatics, UZH and ETH Zürich and Martin Lefebvre, Teaching assistant and PhD student @ Institute of Information and Communication Technologies, Electronics and Applied Mathematics, Université catholique de Louvain.

Abstract: While the back-propagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of low-cost adaptive smart sensors at the edge, as they severely constrain memory accesses and entail buffering overhead. In this work, we show that the one-hot-encoded labels provided in supervised classification problems, denoted as targets, can be viewed as a proxy for the error sign. Therefore, their fixed random projections enable a layerwise feedforward training of the hidden layers, thus solving the weight transport and update locking problems while relaxing the computational and memory requirements. Based on these observations, we propose the direct random target projection algorithm and demonstrate that it provides a tradeoff between accuracy and computational cost that is suitable for adaptive edge computing devices.

16:30 - Q&A

---
During the event, you can share content using #LightOn & @LightOnIO

After the meet-up:

• the slides will be available on our Medium page : https://medium.com/@LightOnIO
• the video of the presentation will be available on our Youtube Channel : https://www.youtube.com/channel/UCE6xfSWQaCk1hqu7pCISK1w