Implementing a classification model for recognition processing
First Claim
1. A method for learning a recognition model for recognition processing, the method comprising:
- preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label, the input segment and the additional segment being extracted from an original training data;
training a classification model, using a processor, using the input segment and the additional segment in the examples to initialize parameters of the classification model to provide initialized parameters so that extended segments, including the input segment and the additional segment, are reconstructed from the input segment without use of further segments to provide reconstructed extended segments; and
tuning the classification model to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters, at least a portion of the classification model being included in the recognition model.
1 Assignment
0 Petitions
Accused Products
Abstract
A method, system, and computer program product for learning a recognition model for recognition processing. The method includes preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label. The input segment and the additional segment are extracted from an original training data. A classification model is trained, using the input segment and the additional segment in the examples, to initialize parameters of the classification model so that extended segments including the input segment and the additional segment are reconstructed from the input segment. Then, the classification model is tuned to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters. At least a portion of the obtained classification model is included in the recognition model.
25 Citations
24 Claims
-
1. A method for learning a recognition model for recognition processing, the method comprising:
-
preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label, the input segment and the additional segment being extracted from an original training data; training a classification model, using a processor, using the input segment and the additional segment in the examples to initialize parameters of the classification model to provide initialized parameters so that extended segments, including the input segment and the additional segment, are reconstructed from the input segment without use of further segments to provide reconstructed extended segments; and tuning the classification model to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters, at least a portion of the classification model being included in the recognition model. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A computer system for learning a recognition model for recognition processing by executing program instructions tangibly stored in a memory, the computer system comprising:
-
a processor in communication with the memory, wherein the computer system is configured to; prepare one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label, the input segment and the additional segment being extracted from an original training data; train a classification model, using the input segment and the additional segment in the examples to initialize parameters of the classification model to provide initialized parameters so that extended segments, including the input segment and the additional segment, are reconstructed from the input segment without use of further segments to provide reconstructed extended segments; and tune the classification model to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters, at least a portion of the classification model being included in the recognition model. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19)
-
-
20. A computer program product for learning a recognition model for recognition processing, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
-
preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label, the input segment and the additional segment being extracted from an original training data; training a classification model, using a processor, using the input segment and the additional segment in the one or more examples to initialize parameters of the classification model to provide initialized parameters so that extended segments, including the input segment and the additional segment, are reconstructed from the input segment without use of further segments to provide reconstructed extended segments; and tuning the classification model to predict a target label, using the input segment and the assigned label in the one or more examples, based on the initialized parameters, at least a portion of the classification model being included in the recognition model. - View Dependent Claims (21, 22)
-
-
23. A method for learning a feature extraction model for recognition processing, the method comprising:
-
preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label, the input segment and the additional segment being extracted from an original training data; training a classification model, using a processor, using the input segment and the additional segment in the examples to initialize parameters of the classification model to provide initialized parameters so that extended segments, including the input segment and the additional segment, are reconstructed from the input segment to provide reconstructed extended segments, wherein the training includes; optimizing forward mapping parameters and reverse mapping parameters of a layer in the classification model such that a discrepancy between the extended segments and the reconstructed extended segments from the input segment is minimized, the reverse mapping parameters being discarded in response to stacking the layer within the classification model, wherein a regularization term is added to a loss function measuring the discrepancy, the regularization term penalizing larger values of the reverse mapping parameters so as to subsume more information into the forward mapping parameters than the reverse mapping parameters; tuning the classification model, using the input segment and the assigned label in the examples; and storing at least a portion of the classification model as the feature extraction model for a feature extractor, the feature extractor outputting, based on input, estimated target probabilities or activations of an internal layer of the classification model as features for a post-stage recognition model.
-
-
24. A method for learning a classification model for recognition processing, the method comprising:
-
preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label, the input segment and the additional segment being extracted from an original training data; training the classification model, using a processor, using the input segment and the additional segment in the examples to initialize parameters of the classification model to provide initialized parameters so that extended segments, including the input segment and the additional segment, are reconstructed from the input segment without use of further segments to provide reconstructed extended segments; tuning the classification model to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters; and storing the classification model, the classification model estimating, based on input, posterior probabilities over targets.
-
Specification