Methods and apparatus for unsupervised neural component replay by referencing a pattern in neuron outputs

摘要

Aspects of the present disclosure support techniques for unsupervised neural component replay. A pattern in a plurality of afferent neuron outputs can be first referenced with one or more referencing neurons. One or more relational aspects can be matched, with one or more relational aspect neurons, between the pattern and an output of the one or more referencing neurons. One or more of the plurality of afferent neurons can be induced to output a pattern that is substantially the same as the referenced pattern by the one or more referencing neurons.