Optimisation of digital learning networks when applied to pattern recognition of mass spectra
T.J. Stonham, Igor Aleksander · Electronics Letters · 1974
A pattern classifier employing n-tuple sampling digital learning networks is analysed to show that redundancy can occur both due to the common occurrence of sets of n-tuples of the sample pattern and invariant points in the patterns. Some experimental results are given for a mass-spectrum classifier, where the system has been optimised by reconnection to reduce this redundancy.