no code implementations • 10 Feb 2023 • Ravi Srinivasan, Francesca Mignacco, Martino Sorbaro, Maria Refinetti, Avi Cooper, Gabriel Kreiman, Giorgia Dellaferrera
"Forward-only" algorithms, which train neural networks while avoiding a backward pass, have recently gained attention as a way of solving the biologically unrealistic aspects of backpropagation.
no code implementations • 8 Dec 2022 • Francesco Lässig, Pau Vilimelis Aceituno, Martino Sorbaro, Benjamin F. Grewe
We evaluate the new sparse-recurrent version of DFC on the split-MNIST computer vision benchmark and show that only the combination of sparsity and intra-layer recurrent connections improves CL performance with respect to standard backpropagation.
1 code implementation • 6 Oct 2021 • Julian Büchel, Gregor Lenz, Yalun Hu, Sadique Sheik, Martino Sorbaro
Event-based dynamic vision sensors provide very sparse output in the form of spikes, which makes them suitable for low-power applications.
2 code implementations • 3 Dec 2019 • Martino Sorbaro, Qian Liu, Massimo Bortone, Sadique Sheik
We demonstrate first that quantization-aware training of CNNs leads to better accuracy in SNNs.