| Description: |
Augmentation is an important part of training deep neural nets these days. Whereas convolutional neural networks typically use spatial augmentation techniques such as rotation, shifting and other affine transforms, data for spiking neural networks often has an important temporal component. I'd be interested in exploring specifically temporal augmentation techniques on spikes. The tooling for that is already in a very mature state in the form of Tonic, please check it out here:
https://tonic.readthedocs.io/en/latest/ |