High-order entropy error functions for neural classifiers
First Claim
Patent Images
1. Artificial neural network classifier comprising:
- a plurality of stages including an input layer, an output layer and at least a hidden layer intermediate said input layer and said output layer, each node comprising a summer, a function system to operate on a sum produced at said node, the function circuit providing an operator of where tj is the value of an error signal at a node j, n is greater than or equal to two and L is the number of layers.
1 Assignment
0 Petitions
Accused Products
Abstract
An automatic speech recognition system comprising a speech decoder to resolve phone and world level information, a vector generator to generate information vectors on which a confidence measure is based by a neural network classifier (ANN). An error signal is designed which is not subject to false saturation or over specialization. The error signal is integrated into an error function which is back propagated through the ANN.
32 Citations
16 Claims
-
1. Artificial neural network classifier comprising:
-
a plurality of stages including an input layer, an output layer and at least a hidden layer intermediate said input layer and said output layer, each node comprising a summer, a function system to operate on a sum produced at said node, the function circuit providing an operator of where tj is the value of an error signal at a node j, n is greater than or equal to two and L is the number of layers. - View Dependent Claims (2, 3, 4, 10)
-
-
5. An automatic speech recognition system comprising:
-
a speech decoder to decode phone level acoustic data and to collect and calculate feature vectors and further comprising feature vectors and adaptive neural network classifier to operate on the normalized feature vectors, said classifier comprising a circuit for transforming inputs thereto by a function - View Dependent Claims (6, 7, 8, 9)
-
-
11. A method to generate an error function neural network classifier producing an output indicative of a confidence level for a decoded word comprising:
deriving an error signal as a linear function with respect to point pairs (tj,1−
tj) and (1−
tj,tj) as δ
jL=(2tj−
1)n=1(tj−
yjL)n, where n=1 for a cross entropy function and raising die value of n to a higher order and back propagating the difference expression through the adaptive neural network classifier.- View Dependent Claims (12, 13)
-
14. A computer program product comprising computer usable medium having computer readable program code embodied in said medium to utilize output of a speech decoder and produce a multiple dimension output vector based on said output;
-
computer readable program code means for causing said computer to operate as a multiple layer perception classifier and computer readable program code means for causing said computer to ply a function to a sum at each node of the multi-layer perceptron of - View Dependent Claims (15, 16)
-
Specification