Learning device and learning method
AssigneeNEC Corporation
InventorsTomoya SAKAI, Yasuhiro SOGAWA
Life of this patent
Estimating the term…
Abstract
A learning device 100 includes correspondence inference unit which calculates outputs of predictors, which have learned for seen tasks or seen classes, for test input data, and infers correspondences between the calculated outputs and attribute information corresponding to an unseen task or an unseen class, and prediction unit which calculates a prediction output for the attribute information corresponding to the unseen task or the unseen class, using the inferred correspondences.
Claims15
A learning device comprising:
- a memory storing a software component;
- and
- at least one processor configured to execute the software component to perform:
- calculating outputs of predictors, which have learned for seen tasks or seen classes, for test input data, and inferring correspondences between the calculated outputs and attribute information corresponding to an unseen task or an unseen class, and
- calculating a prediction output for the attribute information corresponding to the unseen task or the unseen class, using the inferred correspondences.
A computer-implemented learning method comprising:
- calculating outputs of predictors, which have learned for seen tasks or seen classes, for test input data,
- inferring correspondences between the calculated outputs and attribute information corresponding to an unseen task or an unseen class, and
- calculating a prediction output for the attribute information corresponding to the unseen task or the unseen class, using the inferred correspondences.
A non-transitory computer readable recording medium storing a learning program which, when executed by a processor, performs:
- calculating outputs of predictors, which have learned for seen tasks or seen classes, for test input data,
- inferring correspondences between the calculated outputs and attribute information corresponding to an unseen task or an unseen class, and
- calculating a prediction output for the attribute information corresponding to the unseen task or the unseen class, using the inferred correspondences.
Dependencies are inferred from the claim text.