Accession Number : AD0429107


Title :   A NET TO SIMULATE MORSE-CODE LEARNING,


Corporate Author : RAND CORP SANTA MONICA CALIF


Personal Author(s) : Barr,Irwin


Report Date : Jan 1964


Pagination or Media Count : 33


Abstract : The design of a neural net which can learn and recall six letters of Morse Code is presented. The net, called MCN, can learn these coded equivalents in any order. By cascading the MCN with a sequence-recall net, a new net is created, called I, which is able to encode words after being taught the individual letter codes. The method of combining these two nets and a modification of the referenced sequence-recall net are also discussed. (Author)


Descriptors :   *NERVES , *BIONICS , *LEARNING , NETS , NERVE CELLS , SIMULATION , ANATOMICAL MODELS , MATHEMATICAL MODELS , CODING , MEMORY(PSYCHOLOGY)


Distribution Statement : APPROVED FOR PUBLIC RELEASE