Learning apparatus, learning method, and non-transitory computer readable storage medium
AssigneeYahoo Japan Corporation
InventorRiku TOGASHI
Life of this patent
Estimating the term…
Abstract
According to one aspect of an embodiment a learning apparatus includes a generating unit that generates a model. The model includes an encoder that encodes input information. The model includes a vector generating unit that generates a vector by applying a predetermined matrix to the information encoded by the encoder. The model includes a decoder that generates information corresponding to the information from the vector. The learning apparatus includes a learning unit that, when predetermined input information is input to the model, learns the model such that the model outputs output information corresponding to the input information and the predetermined matrix serves as a dictionary matrix of the input information.
Claims13
A learning apparatus comprising:
- a generating unit that generates a model that includes
- an encoder that encodes input information,
- a vector generating unit that generates a vector by applying a predetermined matrix to the information encoded by the encoder, and
- a decoder that generates information corresponding to the information from the vector;
- and
- a learning unit that, when predetermined input information is input to the model, learns the model such that the model outputs output information corresponding to the input information and the predetermined matrix serves as a dictionary matrix of the input information.
A learning method implemented by a learning apparatus, the learning method comprising:
- generating a model that includes
- an encoder that encodes input information,
- a vector generating unit that generates a vector by applying a predetermined matrix to the information encoded by the encoder, and
- a decoder that generates information corresponding to the information from the vector;
- and
- learning, when predetermined input information is input to the model, the model such that the model outputs output information corresponding to the input information and the predetermined matrix serves as a dictionary matrix of the input information.
A non-transitory computer-readable storage medium having stored therein a learning program that causes a computer to execute:
- generating a model that includes
- an encoder that encodes input information,
- a vector generating unit that generates a vector by applying a predetermined matrix to the information encoded by the encoder, and
- a decoder that generates information corresponding to the information from the vector;
- and
- learning, when predetermined input information is input to the model, the model such that the model outputs output information corresponding to the input information and the predetermined matrix serves as a dictionary matrix of the input information.
A non-transitory computer-readable storage medium having stored therein a program that causes a computer to perform as a model comprising:
- an encoder that encodes input information;
- a vector generating unit that generates a vector by applying a predetermined matrix to the information encoded by the encoder;
- and
- a decoder that generates information corresponding to the information from the vector, wherein
- the model being learned such that when predetermined input information is input, the model outputs output information corresponding to the input information and the predetermined matrix serves as a dictionary matrix of the input information, and
- when predetermined input information is input, the model output a plurality of pieces of output information corresponding to the predetermined input information while gradually changing encoded input information.
Dependencies are inferred from the claim text.