公开(公告)号：US20250004725A1

公开(公告)日：2025-01-02

申请号：US18216671

申请日：2023-06-30

Applicant: International Business Machines Corporation

Inventor： Tsuyoshi Ide ,  Pin-Yu Chen

IPC: G06F7/74 ,  G06F17/14

Abstract: In a method of machine learning inferencing, access, via a computer, raw data including data elements; and produce, via the computer, a respective positional encoding vector for each of the data elements. The producing includes computing coefficients using a discrete functional transform on a sequence of the data elements in the raw data. Produce, via the computer, one or more representational encoding vectors based upon the positional encoding vectors and that represent the raw data. Input via the computer, the one or more representational encoding vectors into a neural network. In response to the inputting, receive, via the computer, output from the neural network. The output includes an inference related to the raw data.

公开(公告)号：US12182274B2

公开(公告)日：2024-12-31

申请号：US18382107

申请日：2023-10-20

Applicant: International Business Machines Corporation

Inventor： Pin-Yu Chen ,  Sijia Liu ,  Lingfei Wu ,  Chia-Yu Chen

IPC: G06F21/57 ,  G06N3/04 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82

Abstract: An adversarial robustness testing method, system, and computer program product include testing, via an accelerator, a robustness of a black-box system under different access settings, where the testing includes tearing down the robustness testing to a subtask of a predetermined size.

公开(公告)号：US20240045974A1

公开(公告)日：2024-02-08

申请号：US18382107

申请日：2023-10-20

Applicant: International Business Machines Corporation

Inventor： Pin-Yu Chen ,  Sijia Liu ,  Lingfei Wu ,  Chia-Yu Chen

IPC: G06F21/57 ,  G06N3/04 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06F21/577 ,  G06N3/04 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06F2221/034

Abstract: An adversarial robustness testing method, system, and computer program product include testing, via an accelerator, a robustness of a black-box system under different access settings, where the testing includes tearing down the robustness testing to a subtask of a predetermined size.

公开(公告)号：US20230401435A1

公开(公告)日：2023-12-14

申请号：US17838722

申请日：2022-06-13

Applicant: International Business Machines Corporation ,  RENSSELAER POLYTECHNIC INSTITUTE

Inventor： Pin-Yu Chen ,  Tejaswini Pedapati ,  Bo Wu ,  Chuang Gan ,  Chunheng Jiang ,  Jianxi Gao

IPC: G06N3/063 ,  G06N3/08 ,  G01R27/26

CPC classification number: G06N3/0635 ,  G06N3/08 ,  G01R27/2605

Abstract: An output layer is removed from a pre-trained neural network model and a neural capacitance probe unit with multiple layers is incorporated on top of one or more bottom layers of the pre-trained neural network model. The neural capacitance probe unit is randomly initialized and a modified neural network model is trained by fine-tuning the one or more bottom layers on a target dataset for a maximum number of epochs, the modified neural network model comprising the neural capacitance probe unit incorporated with multiple layers on top of the one or more bottom layers of the pre-trained neural network model. An adjacency matrix is obtained from the initialized neural capacitance probe unit and a neural capacitance metric is computed using the adjacency matrix. An active model is selected using the neural capacitance metric and a machine learning system is configured using the active model.

公开(公告)号：US20230360364A1

公开(公告)日：2023-11-09

申请号：US17737535

申请日：2022-05-05

Applicant: International Business Machines Corporation

Inventor： Bo Wu ,  Chuang Gan ,  Pin-Yu Chen ,  Xin Zhang

IPC: G06V10/764 ,  G06V10/774 ,  G06V10/80

CPC classification number: G06V10/764 ,  G06V10/7753 ,  G06V10/806

Abstract: Mechanisms are provided for performing machine learning (ML) training of a ML action recognition computer model which involves processing an original input dataset to generate an object feature bank comprising object feature data structures for a plurality of different objects. For an input video, a verb data structure and an original object data structure are generated and a candidate object feature data structure is selected from the object feature bank for generation of pseudo composition (PC) training data. The PC training data is generated based on the selected candidate object feature data structure and comprises a combination of the verb data structure and the candidate object feature data structure. The PC training data represents a combination of an action and an object not represented in the original input dataset. ML training of the ML action recognition computer model is performed based on an unseen combination comprising the PC training data.

公开(公告)号：US20220092360A1

公开(公告)日：2022-03-24

申请号：US17541480

申请日：2021-12-03

Applicant: International Business Machines Corporation

Inventor： Ronny Luss ,  Pin-Yu Chen ,  Amit Dhurandhar ,  Prasanna Sattigeri ,  Karthikeyan Shanmugam

IPC: G06K9/62 ,  G06N3/08

Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

公开(公告)号：US20220012572A1

公开(公告)日：2022-01-13

申请号：US16926407

申请日：2020-07-10

Applicant: International Business Machines Corporation ,  Rensselaer Polytechnic Institute

Inventor： Pin-Yu Chen ,  Payel Das ,  Igor Melnyk ,  Prasanna Sattigeri ,  Rongjie Lai ,  Norman Tatro

IPC: G06N3/063 ,  G06N3/04 ,  G06N3/08

Abstract: With at least one hardware processor, obtain data specifying: two trained neural network models; and alignment data. With the at least one hardware processor, carry out neuron alignment on the two trained neural network models using the alignment data to obtain two aligned models. With the at least one hardware processor, train a minimal loss curve between the two aligned models. With the at least one hardware processor, select a new model along the minimal loss curve that maximizes accuracy on adversarially perturbed data.

公开(公告)号：US20210117771A1

公开(公告)日：2021-04-22

申请号：US16657263

申请日：2019-10-18

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Chia-Yu Chen ,  Pin-Yu Chen ,  Mingu Kang ,  Jintao Zhang

IPC: G06N3/08 ,  G06N3/063

Abstract: Methods, systems, and circuits for training a neural network include applying noise to a set of training data across wordlines using a respective noise switch on each wordline. A neural network is trained using the noise-applied training data to generate a classifier that is robust against adversarial training.

公开(公告)号：US20210098074A1

公开(公告)日：2021-04-01

申请号：US16585679

申请日：2019-09-27

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  MIT Massachusetts Institute of Technology

Inventor： Lingfei Wu ,  Siyu Huo ,  Tengfei Ma ,  Pin-Yu Chen ,  Zhao Qin ,  Eugene Jungsup Lim ,  Francisco Javier Martin-Martinez ,  Hui Sun ,  Benedetto Marelli ,  Markus Jochen Buehler

IPC: G16B5/00 ,  G06N3/08 ,  G06N3/04 ,  G16B15/20 ,  G16B40/00

Abstract: A method, computer system, and a computer program product for designing one or more folded structural proteins from at least one raw amino acid sequence is provided. The present invention may include computing one or more character embeddings based on the at least one raw amino acid sequence by utilizing a multi-scale neighborhood-based neural network (MNNN) model. The present invention may then include refining the computed one or more character embeddings with at least one set of sequence neighborhood information. The present invention may further include predicting one or more dihedral angles based on the refined one or more character embeddings.

公开(公告)号：US20240386989A1

公开(公告)日：2024-11-21

申请号：US18319441

申请日：2023-05-17

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Payel Das ,  Devleena Das ,  Pin-Yu Chen ,  Inkit Padhi ,  Amit Dhurandhar ,  Igor Melnyk ,  Enara C. Vijil

IPC: G16B5/20 ,  G06N20/00

Abstract: A first language vector can be generated by performing a first linear projection on a partial amino acid sequence vector. A second language vector can be generated by performing natural language processing on the first language vector. A predicted amino acid sequence vector can be generated by performing a second linear projection on the second language vector. A complete amino acid sequence listing can be output based on the predicted amino acid sequence vector.