Loading patent…
AssigneeMicrosoft Technology Licensing, LLC
InventorsSen ZHOU, Dansong ZHANG, Yan ZHANG, Hongyi SHI, Tong ZHOU, Anastasiya KARPOVICH, Yunsong MENG, Tie WANG
Estimating the term…
Embodiments of the disclosed technologies receive, for a first machine learning task, a first set of raw features arranged according to a first schema, and, for a second machine learning task, a second set of raw features arranged according to a second schema different than the first schema. A multi-task raw feature set is created by storing, in a data store arranged according to a common schema, the first and second sets of raw features. A common feature that is common to both the first and second sets of raw features is identified. A multi-task transformed feature set and a model bundle are created. The multi-task transformed feature set is separated into first and second sets of transformed features. The first and second sets of transformed features and the model bundle can be used to create a trained multi-task machine learning model.
A method comprising:
A method comprising:
A system comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
Backward citations are indexed for grants only.
Architecture, e.g. interconnection topology: combinations of networks
Machine learning: ensemble learning
AI and machine learning
Term end not estimated
A technical field to which the present disclosure relates is multi-task machine learning. Another technical field to which this disclosure relates is the training of multi-task machine learning models. Yet another technical field to which this disclosure relates is the generation of training data sets for multi-task models using heterogeneous data.
Machine learning is a category of artificial intelligence. In machine learning, a model is created using a machine learning algorithm. A machine learning algorithm is a mathematical and/or logical expression of a relationship between inputs to and outputs of the machine learning model. The model is trained by applying the machine learning algorithm to training data.
A trained model can be applied to new instances of input data. In response to a new instance of input data, a machine learning model can output a prediction, a score, a classification, or an inference. Application systems can use the output of a trained machine learning model to determine downstream execution decisions.
The disclosure will be understood more fully from the detailed description given below and from the accompanying drawings of various embodiments of the disclosure. The drawings, however, should not be taken to limit the disclosure to the specific embodiments, but are for explanation and understanding only.
FIG. 1 illustrates an example computing system that includes a multi-task learning system in accordance with some embodiments of the present disclosure.
FIG. 2 is an example of an application system that includes a multi-task learning system in accordance with some embodiments of the present disclosure.
User-facing functionality of an application system can be supported by machine learning models. For example, output of a machine learning model can be used to select search suggestions to be displayed by an application system in a search portion of a user interface. Output of another machine learning model can be used to control the order in which search results are displayed on a user interface. Output of still other machine learning models can be used to select recommendations to display in a feed or recommendation portion of a user interface, such as a news feed or a “people you may know,” “jobs you may be interested in,” “organizations you may be interested in,” or “products you may be interested in” section of the user interface.
A multi-task machine learning model is a machine learning model that is trained for multiple different but related machine learning tasks. Machine learning tasks can be considered related, even if they are in different domains or serve different downstream applications, if the tasks have at least some training data, features, machine learning model parameters and/or coefficients in common.
As used herein, machine learning task can refer to a data processing task that is implemented using machine learning or which uses the output of a machine learning model to perform another task. An example of a data processing task that can be implemented using machine learning is smart search suggestions.