Pattern capacity of a perceptron for sparse discrimination

Vladimir Itskov, L. F. Abbott

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


We evaluate the capacity and performance of a perceptron discriminator operating in a highly sparse regime where classic perceptron results do not apply. The perceptron is constructed to respond to a specified set of q stimuli, with only statistical information provided about other stimuli to which it is not supposed to respond. We compute the probability of both false-positive and false-negative errors and determine the capacity of the system for not responding to nonselected stimuli and for responding to selected stimuli in the presence of noise. If q is a sublinear function of N, the number of inputs to the perceptron, these capacities are exponential in N/q.

Original languageEnglish (US)
Article number018101
JournalPhysical review letters
Issue number1
StatePublished - Jun 30 2008

All Science Journal Classification (ASJC) codes

  • General Physics and Astronomy


Dive into the research topics of 'Pattern capacity of a perceptron for sparse discrimination'. Together they form a unique fingerprint.

Cite this