Pattern recognition apparatus, method and medium
AssigneeNEC Corporation
InventorsShivangi MAHTO, Hitoshi YAMAMOTO, Takafumi KOSHINAKA
Life of this patent
Estimating the term…
Abstract
A pattern recognition apparatus according to the present invention includes: a memory; and at least one processor coupled to the memory, the processor performing operations, the operations comprising: transforming noisy feature vectors into denoised feature vectors; classifying the denoised feature vectors into related classes and estimated classes; calculating a cost by using the denoised feature vectors, clean feature vectors, the estimated classes, and feature vector labels; and updating parameters for transforming the noisy feature vectors according to the cost.
Claims10
A pattern recognition apparatus comprising:
- a memory;
- and
- at least one processor coupled to the memory,
- the processor performing operations, the operations comprising:
- transforming noisy feature vectors into denoised feature vectors;
- classifying the denoised feature vectors into related classes and estimated classes;
- calculating a cost by using the denoised feature vectors, clean feature vectors, the estimated classes, and feature vector labels;
- and
- updating parameters for transforming the noisy feature vectors according to the cost.
A pattern recognition method comprising:
- transforming noisy feature vectors into denoised feature vectors;
- classifying the denoised feature vectors into related classes and estimated classes;
- calculating a cost by using the denoised feature vectors, clean feature vectors, the estimated classes, and feature vector labels;
- and
- updating parameters for transforming the noisy feature vector according to the cost.
A non-transitory computer readable medium embodying a program, the program causing a pattern recognition apparatus to perform a method, the method comprising:
- transforming noisy feature vectors into denoised feature vectors;
- classifying the denoised feature vectors into related classes and estimated classes;
- calculating a cost by using the denoised feature vectors, clean feature vectors, the estimated classes, and feature vector labels;
- and
- updating parameters for transforming the noisy feature vector according to the cost.
Dependencies are inferred from the claim text.