CONNECTIVITY IN REAL AND EVOLVED ASSOCIATIVE MEMORIES

摘要

Finding efficient patterns of connectivity in sparse associative memories is a difficult problem. It is, however, one that real neuronal networks, such as the mammalian cortex, must have solved. We have investigated evolved computational models of sparsely connected associative memories and found that some patterns of connectivity produce both good performance and efficient use of resources. This could illuminate how real biological systems solve the problem.