Providing a hybrid neural network architecture
AssigneeInternational Business Machines Corporation
InventorsAaron K. Baughman, Kavitha Hassan Yogaraj, Arjun Kashyap, GURURAJA HEBBAR, Rukhsan Ul Haq, Sudeep Ghosh
Life of this patent
Estimating the term…
Abstract
Providing a hybrid neural network architecture by training a plurality of models using a set of training data, the plurality comprising quantum models and classical models, evaluating each model using a common test data set, assigning one or more evaluation metrics to each model according to the evaluation, generating a plurality of networks, each network comprising a combination of the models, evaluating a flow of each network, selecting a network according to the flow, and providing the selected network to a user.
Claims20
A computer implemented method for providing a hybrid neural network architecture, the method comprising:
- training, by one or more computer processors, a plurality of models using a set of training data, the plurality comprising quantum models and classical models;
- evaluating, by the one or more computer processors, each model using a common test data set;
- assigning, by the one or more computer processors, one or more evaluation metrics to each model according to the evaluation;
- generating, by the one or more computer processors, a plurality of networks, each network comprising a combination of the models;
- evaluating, by the one or more computer processors, a flow of each network;
- selecting, by the one or more computer processors, a first network according to the flow;
- and
- providing, by the one or more computer processors, the first network to a user.
A computer program product for providing a hybrid neural network architecture, the computer program product comprising one or more computer readable storage media and collectively stored program instructions on the one or more computer readable storage media, the stored program instructions comprising:
- program instructions to train a plurality of models using a set of training data, the plurality comprising quantum models and classical models;
- program instructions to evaluate each model using a common test data set;
- program instructions to assign one or more evaluation metrics to each model according to the evaluation;
- program instructions to generate a plurality of networks, each network comprising a combination of the models;
- program instructions to evaluate a flow of each network;
- program instructions to select a first network according to the flow;
- and
- program instructions to provide the first network to a user.
A computer system for providing a hybrid neural network architecture, the computer system comprising:
- one or more computer processors;
- one or more computer readable storage devices;
- and
- stored program instructions on the one or more computer readable storage devices for execution by the one or more computer processors, the stored program instructions comprising:
- program instructions to train a plurality of models using a set of training data, the plurality comprising quantum models and classical models;
- program instructions to evaluate each model using a common test data set;
- program instructions to assign one or more evaluation metrics to each model according to the evaluation;
- program instructions to generate a plurality of networks, each network comprising a combination of the models;
- program instructions to evaluate a flow of each network;
- program instructions to select a first network according to the flow;
- and
- program instructions to provide the first network to a user.
Dependencies are inferred from the claim text.