A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks

Open Access

Peer-reviewed

Research Article

Alireza Alemi ,

* E-mail: alireza.alemi@hugef-torino.it, alireza.alemi@gmail.com

Affiliations Human Genetics Foundation (HuGeF), Turin, Italy, DISAT, Politecnico di Torino, Turin, Italy
⨯
Carlo Baldassi,

Affiliations Human Genetics Foundation (HuGeF), Turin, Italy, DISAT, Politecnico di Torino, Turin, Italy
⨯
Nicolas Brunel,

Affiliation Departments of Statistics and Neurobiology, University of Chicago, Chicago, Illinois, United States of America
⨯
Riccardo Zecchina

Affiliations Human Genetics Foundation (HuGeF), Turin, Italy, DISAT, Politecnico di Torino, Turin, Italy
⨯

Reader Comments (0)

Neurons
Is the Subject Area "Neurons" applicable to this article?

Thanks for your feedback.
Learning
Is the Subject Area "Learning" applicable to this article?

Thanks for your feedback.
Neural networks
Is the Subject Area "Neural networks" applicable to this article?

Thanks for your feedback.
Synapses
Is the Subject Area "Synapses" applicable to this article?

Thanks for your feedback.
Perceptrons
Is the Subject Area "Perceptrons" applicable to this article?

Thanks for your feedback.
Memory
Is the Subject Area "Memory" applicable to this article?

Thanks for your feedback.
Recurrent neural networks
Is the Subject Area "Recurrent neural networks" applicable to this article?

Thanks for your feedback.
Synaptic plasticity
Is the Subject Area "Synaptic plasticity" applicable to this article?

Thanks for your feedback.