Accession Number : ADA256223


Title :   Genetic Algorithms for Genetic Neural Nets.


Descriptive Note : Research rept.,


Corporate Author : YALE UNIV NEW HAVEN CT DEPT OF COMPUTER SCIENCE


Personal Author(s) : Sharp, David H ; Reinitz, John ; Mjolsness, Eric


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a256223.pdf


Report Date : Jan 1991


Pagination or Media Count : 11


Abstract : In contrast to most synthetic neural nets, biological neural networks have a strong component of genetic determination which acts before and during experiential learning. Three broad levels of phenomena are present: long-term evolution, involving crossover as well as point mutation; a developmental process mapping genetic information to a set of cells and their internal states of gene expression (genotype to phenotype); and the subsequent synaptogenesis. We describe a very simple mathematical idealization of these three levels which combines the crossover search method of genetic algorithms with the developmental models used in our previous work on 'genetic' or 'recursively generated' artificial neural nets (and elaborated into a connectionist model of biological development. Despite incorporating all three levels (evolution on genes; development of cells; synapse formation) the model may actually be far cheaper to compute with than a comparable search directly in synaptic weight space.


Descriptors :   *NEURAL NETS , *LEARNING , *GENETIC MAPPING , CELLS(BIOLOGY) , SYNAPSE , MOTOR NEURONS


Subject Categories : Biology
      Anatomy and Physiology


Distribution Statement : APPROVED FOR PUBLIC RELEASE