Patents by Inventor Tommi S. Jaakkola

Tommi S. Jaakkola has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11657271
    Abstract: A method and system of determining an output label rationale are provided. A first generator receives a first class of data and selects one or more input features from the first class of data. A first predictor receives the one or more selected input features from the first generator and predicts a first output label. A second generator receives a second class of data and selects one or more input features from the second class of data. A second predictor receives the one or more selected input features from the second generator and predicts a second output label. A discriminator receives the first and second output labels and determines whether the selected one or more input features from the first class of data or the selected features of the one or more input features from the second class of data, more accurately represents the first output label.
    Type: Grant
    Filed: October 20, 2019
    Date of Patent: May 23, 2023
    Assignees: INTERNATIONAL BUSINESS MACHINES CORPORATION, MASSACHUSETTS INSTITUTE OF TECHNOLOGY
    Inventors: Shiyu Chang, Mo Yu, Yang Zhang, Tommi S. Jaakkola
  • Patent number: 11551000
    Abstract: A method and system of training a natural language processing network are provided. A corpus of data is received and one or more input features selected therefrom by a generator network. The one or more selected input features from the generator network are received by a first predictor network and used to predict a first output label. A complement of the selected input features from the generator network are received by a second predictor network and used to predict a second output label.
    Type: Grant
    Filed: October 20, 2019
    Date of Patent: January 10, 2023
    Assignees: INTERNATIONAL BUSINESS MACHINES CORPORATION, MASSACHUSETTS INSTITUTE OF TECHNOLOGY
    Inventors: Shiyu Chang, Mo Yu, Yang Zhang, Tommi S. Jaakkola
  • Publication number: 20220147864
    Abstract: To improve actual labels that are produced by a black box computer classifier system from inputs, identify, using an environment-aware predictor and an environment-agnostic predictor, a subset of the inputs. The subset of the inputs has a stable correlation with the actual labels across a plurality of environments. Identify the subset of the inputs as an explanatory rationale for the actual labels. Display the explanatory rationale with the actual labels to a consumer of the actual labels. Optionally, in response to the explanatory rationale failing a rubric established by the consumer, generate revised inputs by removing the explanatory rationale from the inputs; and produce revised labels by processing the revised inputs with the environment-agnostic predictor.
    Type: Application
    Filed: November 11, 2020
    Publication date: May 12, 2022
    Inventors: Shiyu Chang, Yang Zhang, Mo Yu, Tommi S. Jaakkola
  • Publication number: 20210117772
    Abstract: A method and system of determining an output label rationale are provided. A first generator receives a first class of data and selects one or more input features from the first class of data. A first predictor receives the one or more selected input features from the first generator and predicts a first output label. A second generator receives a second class of data and selects one or more input features from the second class of data. A second predictor receives the one or more selected input features from the second generator and predicts a second output label. A discriminator receives the first and second output labels and determines whether the selected one or more input features from the first class of data or the selected features of the one or more input features from the second class of data, more accurately represents the first output label.
    Type: Application
    Filed: October 20, 2019
    Publication date: April 22, 2021
    Inventors: Shiyu Chang, Mo Yu, Yang Zhang, Tommi S. Jaakkola
  • Publication number: 20210117508
    Abstract: A method and system of training a natural language processing network are provided. A corpus of data is received and one or more input features selected therefrom by a generator network. The one or more selected input features from the generator network are received by a first predictor network and used to predict a first output label. A complement of the selected input features from the generator network are received by a second predictor network and used to predict a second output label.
    Type: Application
    Filed: October 20, 2019
    Publication date: April 22, 2021
    Inventors: Shiyu Chang, Mo Yu, Yang Zhang, Tommi S. Jaakkola
  • Patent number: 10622098
    Abstract: Techniques for predicting a chemical reaction that includes a set of input molecules. The techniques may include obtaining input molecule information identifying the set of input molecules and predicting at least one chemical reaction that include a transformation between the set of input molecules and a set of output molecules by modifying at least one reaction center of the set of input molecules. The predicting of the at least one chemical reaction may be performed at least in part by using the input molecule information and at least one statistical model relating properties of atoms outside a region of a molecule to reactivity of the molecule at the region to identify the at least one reaction center. The techniques further include outputting information indicating the set of output molecules.
    Type: Grant
    Filed: August 29, 2018
    Date of Patent: April 14, 2020
    Assignee: Massachusetts Institute of Technology
    Inventors: Connor Wilson Coley, Klavs F. Jensen, Regina Barzilay, Tommi S. Jaakkola, Wengong Jin
  • Publication number: 20200027528
    Abstract: Techniques for predicting a chemical reaction that includes a set of input molecules. The techniques may include obtaining input molecule information identifying the set of input molecules and predicting at least one chemical reaction that include a transformation between the set of input molecules and a set of output molecules by modifying at least one reaction center of the set of input molecules. The predicting of the at least one chemical reaction may be performed at least in part by using the input molecule information and at least one statistical model relating properties of atoms outside a region of a molecule to reactivity of the molecule at the region to identify the at least one reaction center. The techniques further include outputting information indicating the set of output molecules.
    Type: Application
    Filed: August 29, 2018
    Publication date: January 23, 2020
    Applicant: Massachusetts Institute of Technology
    Inventors: Connor Wilson Coley, Klavs F. Jensen, Regina Barzilay, Tommi S. Jaakkola, Wengong Jin
  • Publication number: 20180271435
    Abstract: A method for tracking a sleep stage of a subject takes as input a sequence of observations sensed over an observation time period. The sequence of observation values is processed to yield a corresponding sequence of encoded observations using a first artificial neural network (ANN) and the sequence of encoded observation values is processed to yield a sequence of sleep stage indicators using a second artificial network. Each observation may correspond to an interval of the observation period (e.g., at least 30 seconds). The first ANN may be configured to reduce information representing a source of the sequence of observations in the encoded observations.
    Type: Application
    Filed: March 23, 2018
    Publication date: September 27, 2018
    Inventors: Mingmin Zhao, Shichao Yue, Dina Katabi, Tommi S. Jaakkola