1 citations · 1 across the 3 of their papers we have counts for
4 papers
Deep Features for CBIR with Scarce Data using Hebbian Learning
Gabriele Lagani, Davide Bacciu, Claudio Gallicchio +3
Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR). In recent work, biologically inspired \…
Hebbian Semi-Supervised Learning in a Sample Efficiency Setting
Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro +1
We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gra…
Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulation
Gabriele Lagani, Raffaele Mazziotti, Fabrizio Falchi +5
Previous work has shown that it is possible to train neuronal cultures on Multi-Electrode Arrays (MEAs), to recognize very simple patterns. However, this work was mainly focused to…
Training Convolutional Neural Networks With Hebbian Principal Component Analysis
Gabriele Lagani, Giuseppe Amato, Fabrizio Falchi +1
Recent work has shown that biologically plausible Hebbian learning can be integrated with backpropagation learning (backprop), when training deep convolutional neural networks. In…