Automatic optimization of machine learning algorithms in the presence of target datasets
AssigneeUrugus S.A.
InventorsAlbert Pujol Torras, Pau de Jorge Aranda, Francisco Javier Marin Tur, Marc Romani
Life of this patent
Estimating the term…
Loading patent…
AssigneeUrugus S.A.
InventorsAlbert Pujol Torras, Pau de Jorge Aranda, Francisco Javier Marin Tur, Marc Romani
Estimating the term…
Methods, systems and computer program products for transferring knowledge using machine learning techniques by automatically generating training datasets are provided. New training datasets based on target datasets are automatically generated and used in machine learning techniques to perform tasks on images. One of the main benefits is the possibility to transfer the knowledge learned in one domain to another domain in which extracting data or labeling images would be costly or simply infeasible. The methods and systems also provide image training sets based on image target sets which augments data in a more efficient way and improves the content of the training set and the prediction of the machine learning techniques.
1-31. (canceled)
A method to automatically transfer knowledge in machine learning algorithms, the method comprising:
A system comprising:
Dependencies are inferred from the claim text.