Hebbian Learning Meets Deep Convolutional Neural Networks
@inproceedings{Amato2019HebbianLM, title={Hebbian Learning Meets Deep Convolutional Neural Networks}, author={Giuseppe Amato and Fabio Carrara and Fabrizio Falchi and Claudio Gennaro and Gabriele Lagani}, booktitle={ICIAP}, year={2019} }
Neural networks are said to be biologically inspired since they mimic the behavior of real neurons. However, several processes in state-of-the-art neural networks, including Deep Convolutional Neural Networks (DCNN), are far from the ones found in animal brains. One relevant difference is the training process. In state-of-the-art artificial neural networks, the training process is based on backpropagation and Stochastic Gradient Descent (SGD) optimization. However, studies in neuroscience… CONTINUE READING
References
Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES
Learning Multiple Layers of Features from Tiny Images
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL
Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL
Hebbian learning algorithms for training convolutional neural networks
VIEW 1 EXCERPT
Hebbian learning algorithms for training convolutional neural networks - project
VIEW 1 EXCERPT
Neural Networks and Learning Machines
VIEW 3 EXCERPTS