Search Results for author: Isabella Pozzi

Found 4 papers, 2 papers with code

Gating out sensory noise in a spike-based Long Short-Term Memory network

no code implementations ICLR 2018 Davide Zambrano, Isabella Pozzi, Roeland Nusselder, Sander Bohte

These adaptive spiking neurons implement an adaptive form of sigma-delta coding to convert internally computed analog activation values to spike-trains.

A Biologically Plausible Learning Rule for Deep Learning in the Brain

1 code implementation5 Nov 2018 Isabella Pozzi, Sander Bohté, Pieter Roelfsema

Researchers have proposed that deep learning, which is providing important progress in a wide range of high complexity tasks, might inspire new insights into learning in the brain.

Image Classification reinforcement-learning +1

DeepAGREL: Biologically plausible deep learning via direct reinforcement

no code implementations25 Sep 2019 Isabella Pozzi, Sander M. Bohte, Pieter R. Roelfsema

While much recent work has focused on biologically plausible variants of error-backpropagation, learning in the brain seems to mostly adhere to a reinforcement learning paradigm; biologically plausible neural reinforcement learning frameworks, however, were limited to shallow networks learning from compact and abstract sensory representations.

Image Classification reinforcement-learning +1

Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagation

1 code implementation NeurIPS 2020 Isabella Pozzi, Sander Bohte, Pieter Roelfsema

We show how the new learning scheme – Attention-Gated Brain Propagation (BrainProp) – is mathematically equivalent to error backpropagation, for one output unit at a time.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.