Neuromorphic and Deep Neural Networks
Eugenio Culurciello

SSNs can be trained with approximate back-propagation algorithms. This one shows how to do it event-based, real-time, embedded without using a single multiplication. Check it out here:

We have a digital platform for this for the moment, but mixed signal would work too.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.