We study the recognition capability of a Hopfield network, i.e., a neural network where interaction of nodes is determined by the Hebb transform. We present a formally rigorous derivation of an upper bound on the error probability for recognition of randomized objects. It is based on the standard technique of estimating large deviations by the Chebyshev–Chernov method.
Problems of Information Transmission – Springer Journals
Published: Oct 7, 2004
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
All the latest content is available, no embargo periods.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud