Issue No. 08 - August (1993 vol. 42)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/12.238491
<p>A geometrical expansion learning algorithm for multilayer neural networks using unipolar binary neurons with integer connection weights, which guarantees convergence for any Boolean function, is introduced. Neurons in the hidden layer develop as necessary without supervision. In addition, the computational amount is much less than that of the backpropagation algorithm.</p>
geometrical learning algorithm; multilayer neural networks; binary field; unipolar binary neurons; integer connection weights; Boolean function; hidden layer; Boolean functions; feedforward neural nets; learning (artificial intelligence).
J. Kim and S. Park, "Geometrical Learning Algorithm for Multilayer Neural Networks in a Binary Field," in IEEE Transactions on Computers, vol. 42, no. , pp. 988-992, 1993.