Stoop R, Buchli J, Keller G, Steeb WH. Stochastic resonance in pattern recognition by a holographic neuron model.
Phys Rev E Stat Nonlin Soft Matter Phys 2003;
67:061918. [PMID:
16241272 DOI:
10.1103/physreve.67.061918]
[Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/06/2002] [Indexed: 05/04/2023]
Abstract
The recognition rate of holographic neural synapses, performing a pattern recognition task, is significantly higher when applied to natural, rather than artificial, images. This shortcoming of artificial images can be largely compensated for, if noise is added to the input pattern. The effect is the result of a trade-off between optimal representation of the stimulus (for which noise is favorable) and keeping as much as possible of the stimulus-specific information (for which noise is detrimental). The observed mechanism may play a prominent role for simple biological sensors.
Collapse