摘要 |
An artificial neuron includes inputs and dendrites (700), a respective one of which is associated with a respective one of the inputs (710). A respective dendrite includes a respective power series of weights (730). The weights in a given power of the power series represent a maximal projection. A respective power also may include at least one switch, to identify holes in the projections. By providing maximal projections, linear scaling may be provided for the maximal projections, and quasi-linear scaling may be provided for the artificial neuron, while allowing a lossless compression of the associations. Accordingly, hetero-associative and/or auto-associative recall may be accommodated for large numbers of inputs, without requiring geometric scaling as a function of input.
|
申请人 |
SAFFRON TECHNOLOGY, INC.;CABANA, DAVID, R.;APARICIO, IV, MANUEL;FLEMING, JAMES, S. |
发明人 |
CABANA, DAVID, R.;APARICIO, IV, MANUEL;FLEMING, JAMES, S. |