activity
20182022
collaborators

6 papers

cs.NE2022

Bio-Inspired, Task-Free Continual Learning through Activity Regularization

Francesco Lässig, Pau Vilimelis Aceituno, Martino Sorbaro +1

The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To a…

cs.NE2019

Optimizing the energy consumption of spiking neural networks for neuromorphic applications

Martino Sorbaro, Qian Liu, Massimo Bortone +1

In the last few years, spiking neural networks have been demonstrated to perform on par with regular convolutional neural networks. Several works have proposed methods to convert a…

q-bio.NC2018

Statistical models of neural activity, criticality, and Zipf's law

Martino Sorbaro, J. Michael Herrmann, Matthias H. Hennig

In this overview, we discuss the connections between the observations of critical dynamics in neuronal networks and the maximum entropy models that are often used as statistical mo…

q-bio.NC2018

Scaling Spike Detection and Sorting for Next Generation Electrophysiology

Matthias H. Hennig, Cole Hurwitz, Martino Sorbaro

Reliable spike detection and sorting, the process of assigning each detected spike to its originating neuron, is an essential step in the analysis of extracellular electrical recor…

q-bio.NC2018

Local learning rules to attenuate forgetting in neural networks

Michael Deistler, Martino Sorbaro, Michael E. Rule +1

Hebbian synaptic plasticity inevitably leads to interference and forgetting when different, overlapping memory patterns are sequentially stored in the same network. Recent work on…

q-bio.NC2018

Optimal encoding in stochastic latent-variable Models

M. E. Rule, M. Sorbaro, M. H. Hennig

In this work we explore encoding strategies learned by statistical models of sensory coding in noisy spiking networks. Early stages of sensory communication in neural systems can b…