Genetic algorithms for genetic neural nets. Research report

Technical Report · Tue Jan 01 00:00:00 EST 1991

OSTI ID:6816557

Sharp, D H; Reinitz, J; Mjolsness, E

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.

• Research Organization: Yale Univ., New Haven, CT (United States). Dept. of Computer Science
• OSTI ID: 6816557
• Report Number(s): AD-A-256223/9/XAB; YALEU/DCS/TR-845; CNN: AFOSR-88-0240
• Resource Relation: Other Information: P
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
59 BASIC BIOLOGICAL SCIENCES
LEARNING
ALGORITHMS
NEURAL NETWORKS
GENETIC MAPPING
BIOLOGY
DIFFERENTIAL EQUATIONS
RECURSION RELATIONS
EQUATIONS
MAPPING
MATHEMATICAL LOGIC
990200* - Mathematics & Computers
550400 - Genetics