CrossRef Open Access 2019 2 sitasi

On neuronal capacity*

Pierre Baldi Roman Vershynin

Lihat Sumber DOI

Abstrak

Abstract We define the capacity of a learning machine to be the logarithm of the number (or volume) of the functions it can implement. We review known results, and derive new results, estimating the capacity of several neuronal models: linear and polynomial threshold gates, linear and polynomial threshold gates with constrained weights (binary weights, positive weights), and ReLU neurons. We also derive some capacity estimates and bounds for fully recurrent networks, as well as feedforward networks.

Penulis (2)

Pierre Baldi

Roman Vershynin

Format Sitasi

APA MLA BibTeX

Baldi, P., Vershynin, R. (2019). On neuronal capacity*. https://doi.org/10.1088/1742-5468/ab3285

Akses Cepat

Lihat di Sumber doi.org/10.1088/1742-5468/ab3285

Informasi Jurnal

Tahun Terbit: 2019
Bahasa: en
Total Sitasi: 2×
Sumber Database: CrossRef
DOI: 10.1088/1742-5468/ab3285
Akses: Open Access ✓