-
公开(公告)号：US11494591B2
公开(公告)日：2022-11-08
申请号：US16245489
申请日：2019-01-11
Applicant: International Business Machines Corporation
Inventor： Yang Zhang , Shiyu Chang , Mo Yu , David S. Kung
Abstract: Techniques regarding a zero-confidence adversarial attack are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise an adversarial component that computes a perturbation that causes misclassification by a neural network classifier. The computer executable components can also comprise a restoration component that determines a normal vector to a constraint contour developed by the neural network classifier. Further, the computer executable components can comprise a projection component that determines a tangential vector to the constraint contour.
-
公开(公告)号：US11416775B2
公开(公告)日：2022-08-16
申请号：US16851221
申请日：2020-04-17
Applicant: International Business Machines Corporation
Inventor： Pin-yu Chen , Sijia Liu , Shiyu Chang , Payel Das , Minhao Cheng
Abstract: Techniques for training robust machine learning models for adversarial input data. Training data for a machine learning (ML) model is received. The training data includes a plurality of labels for data elements. First modified training data is generated by modifying one or more of the plurality of labels in the training data using parameterized label smoothing with a first optimization parameter. The ML model is trained using the first modified training data. The training includes updating a first one or more model weights in the ML model, and generating a second optimization parameter suitable for use in future parameterized label smoothing for future training of the ML model
-
公开(公告)号：US11222395B2
公开(公告)日：2022-01-11
申请号：US17136805
申请日：2020-12-29
Applicant: International Business Machines Corporation
Inventor： Shiyu Chang , Liana L. Fong , Wei Tan
Abstract: Techniques that facilitate matrix factorization associated with graphics processing units are provided. In one example, a computer-implemented method is provided. The computer-implemented method can comprise loading, by a graphics processing unit operatively coupled to a processor, item features from a data matrix into a shared memory. The data matrix can be a matrix based on one or more user features and item features. The computer-implemented method can further comprise tiling and aggregating, by the graphics processing unit, outer products of the data matrix tiles to generate an aggregate value and approximating, by the graphics processing unit, an update to a user feature of the data matrix based on the aggregate value and the loaded item features.
-
公开(公告)号：US20200226425A1
公开(公告)日：2020-07-16
申请号：US16245489
申请日：2019-01-11
Applicant: International Business Machines Corporation
Inventor： Yang Zhang , Shiyu Chang , Mo Yu , David S. Kung
Abstract: Techniques regarding a zero-confidence adversarial attack are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise an adversarial component that computes a perturbation that causes misclassification by a neural network classifier. The computer executable components can also comprise a restoration component that determines a normal vector to a constraint contour developed by the neural network classifier. Further, the computer executable components can comprise a projection component that determines a tangential vector to the constraint contour.
-
公开(公告)号：US20190266699A1
公开(公告)日：2019-08-29
申请号：US16407781
申请日：2019-05-09
Applicant: International Business Machines Corporation
Inventor： Shiyu Chang , Liana L. Fong , Wei Tan
Abstract: Techniques that facilitate matrix factorization associated with graphics processing units are provided. In one example, a computer-implemented method is provided. The computer-implemented method can comprise loading, by a graphics processing unit operatively coupled to a processor, item features from a data matrix into a shared memory. The data matrix can be a matrix based on one or more user features and item features. The computer-implemented method can further comprise tiling and aggregating, by the graphics processing unit, outer products of the data matrix tiles to generate an aggregate value and approximating, by the graphics processing unit, an update to a user feature of the data matrix based on the aggregate value and the loaded item features.
-
Patent Agency Ranking
公开(公告)号：US11645514B2
公开(公告)日：2023-05-09
申请号：US16530457
申请日：2019-08-02
Applicant: International Business Machines Corporation
Inventor： Ming Tan , Dakuo Wang , Mo Yu , Haoyu Wang , Yang Yu , Shiyu Chang , Saloni Potdar
Abstract: A computer-implemented method includes using an embedding network to generate prototypical vectors. Each prototypical vector is based on a corresponding label associated with a first domain. The computer-implemented method also includes using the embedding network to generate an in-domain test vector based on at least one data sample from a particular label associated with the first domain and using the embedding network to generate an out-of-domain test vector based on at least one other data sample associated with a different domain. The computer-implemented method also includes comparing the prototypical vectors to the in-domain test vector to generate in-domain comparison values and comparing the prototypical vectors to the out-of-domain test vector to generate out-of-domain comparison values. The computer-implemented method also includes modifying, based on the in-domain comparison values and the out-of-domain comparison values, one or more parameters of the embedding network.
-
公开(公告)号：US20220147864A1
公开(公告)日：2022-05-12
申请号：US17095688
申请日：2020-11-11
Inventor： Shiyu Chang , Yang Zhang , Mo Yu , Tommi S. Jaakkola
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.
-
公开(公告)号：US11263402B2
公开(公告)日：2022-03-01
申请号：US16404156
申请日：2019-05-06
Applicant: International Business Machines Corporation
Inventor： Ming Tan , Dakuo Wang , Mo Yu , Chuang Gan , Haoyu Wang , Shiyu Chang
IPC: G06F40/30 , G06F40/205 , G06F40/289
Abstract: Techniques facilitating detection of conversation threads in unstructured channels are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an extraction component that employs a model to detect conversation messages based on a defined confidence level and assigns the conversation messages to respective conversation thread categories. The computer executable components also can comprise a model component that trains the model on conversation messages that comprise respective text data, wherein the model is trained to detect the respective text data to the defined confidence level.
-
公开(公告)号：US20210117772A1
公开(公告)日：2021-04-22
申请号：US16658122
申请日：2019-10-20
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Shiyu Chang , Mo Yu , Yang Zhang , Tommi S. Jaakkola
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.
-
公开(公告)号：US10937122B2
公开(公告)日：2021-03-02
申请号：US16407781
申请日：2019-05-09
Applicant: International Business Machines Corporation
Inventor： Shiyu Chang , Liana L. Fong , Wei Tan
Abstract: Techniques that facilitate matrix factorization associated with graphics processing units are provided. In one example, a computer-implemented method is provided. The computer-implemented method can comprise loading, by a graphics processing unit operatively coupled to a processor, item features from a data matrix into a shared memory. The data matrix can be a matrix based on one or more user features and item features. The computer-implemented method can further comprise tiling and aggregating, by the graphics processing unit, outer products of the data matrix tiles to generate an aggregate value and approximating, by the graphics processing unit, an update to a user feature of the data matrix based on the aggregate value and the loaded item features.
-
-
-
-
-
-
-
-
-
Search Results
27
records
(took 0.02 seconds)
