High efficiency learning network
AssigneeAT&T IPM Corp.
InventorPatrice Y. Simard
Life of this patent
Estimating the term…
Loading patent…
AssigneeAT&T IPM Corp.
InventorPatrice Y. Simard
Estimating the term…
Nodal outputs are discretized to values of S2.sup.n where n is an integer and S is equal to +1 or -1. During forward propagation, this offers the advantage of forming a product of a nodal output and a weight using a simple shift operation rather than a multiply operation. Replacing multiply operations with shift operations through out a neural network improves response times and permits building larger networks that have broader applicability. Training is also improved by increasing the efficiency of backward propagation. The multiplications involved in backward propagation are reduced To shift operations by discretizing the errors associated with each node so that they are represented as 2.sup.n where n is an integer and S is equal to +1 or -1.
A computational network that produces a plurality of network outputs in response to a plurality of network inputs, comprising:
A computational network that produces a plurality of network outputs in response to a plurality of network inputs, comprising:
A method of recognizing a user's input, comprising the steps of:
Dependencies are inferred from the claim text.