公开(公告)号：US20210383497A1

公开(公告)日：2021-12-09

申请号：US16894343

申请日：2020-06-05

Applicant: International Business Machines Corporation ,  Rensselaer Polytechnic Institute

Inventor： Ao Liu ,  Sijia Liu ,  Abhishek Bhandwaldar ,  Chuang Gan ,  Lirong Xia ,  Qi Cheng Li

IPC: G06T1/00 ,  G06T5/00 ,  G06T5/20 ,  G06T5/50 ,  G06N3/02

Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.

公开(公告)号：US20210271956A1

公开(公告)日：2021-09-02

申请号：US16805019

申请日：2020-02-28

Applicant: International Business Machines Corporation

Inventor： Dakuo Wang ,  Chuang Gan ,  Ming Tan ,  Arunima Chaudhary ,  Lin Ju

IPC: G06N3/04 ,  G06N3/08 ,  G06K9/62

Abstract: In accordance with an embodiment of the invention, a method is provided for personalizing machine learning models for users of an automated machine learning system, the machine learning models being generated by an automated machine learning system. The method includes obtaining a first set of datasets for training first, second, and third neural networks, inputting the training datasets to the neural networks, tuning hyperparameters for the first, second, and third neural networks for testing and training the neural networks, inputting a second set of datasets to the trained neural networks and the third neural network generating a third output data including a relevance score for each of the users for each of the machine learning models, and displaying a list of machine learning models associated with each of the users, with each of the machine learning models showing the relevance score.

公开(公告)号：US11039043B1

公开(公告)日：2021-06-15

申请号：US16744471

申请日：2020-01-16

Applicant: International Business Machines Corporation

Inventor： Yang Zhang ,  Chuang Gan ,  Dakuo Wang

IPC: H04N5/04 ,  G06N3/08 ,  G10L25/57

Abstract: Embodiments herein describe an audio forwarding regularizer and an information bottleneck that are used when training a machine learning (ML) system. The audio forwarding regularizer receives audio training data and identifies visually irrelevant and relevant sounds in the training data. By controlling the information bottleneck, the audio forwarding regularizer forwards data to a generator that is primarily related to the visually irrelevant sounds, while filtering out the visually relevant sounds. The generator also receives data regarding visual objects from a visual encoder derived from visual training data. Thus, when being trained, the generator receives data regarding the visual objects and data regarding the visually irrelevant sounds (but little to no data regarding the visually relevant sounds). Thus, during an execution stage, the generator can generate sounds that are relevant to the visual objects while not adding visually irrelevant sounds to the videos.

公开(公告)号：US20210110266A1

公开(公告)日：2021-04-15

申请号：US16597937

申请日：2019-10-10

Applicant: International Business Machines Corporation

Inventor： Dakuo Wang ,  Ming Tan ,  Mo Yu ,  Haoyu Wang ,  Yupeng Gao ,  Chuang Gan

IPC: G06N3/08 ,  G06N20/00 ,  G06N3/04 ,  H04L12/58

Abstract: A computer system identifies threads in a communication session. A feature vector is generated for a message in a communication session, wherein the feature vector includes elements for features and contextual information of the message. The message feature vector and feature vectors for a plurality of threads are processed using machine learning models each associated with a corresponding thread to determine a set of probability values for classifying the message into at least one thread, wherein the threads include one or more pre-existing threads and a new thread. A classification of the message into at least one of the threads is indicated based on the set of probability values. Classification of one or more prior messages is adjusted based on the message's classification. Embodiments of the present invention further include a method and program product for identifying threads in a communication session in substantially the same manner described above.

公开(公告)号：US20210064785A1

公开(公告)日：2021-03-04

申请号：US16559161

申请日：2019-09-03

Applicant: International Business Machines Corporation

Inventor： Sijia Liu ,  Quanfu Fan ,  Gaoyuan Zhang ,  Chuang Gan

IPC: G06F21/71 ,  G06F21/57 ,  G06N20/00

Abstract: An illustrative embodiment includes a method for protecting a machine learning model. The method includes: determining concept-level interpretability of respective units within the model; determining sensitivity of the respective units within the model to an adversarial attack; identifying units within the model which are both interpretable and sensitive to the adversarial attack; and enhancing defense against the adversarial attack by masking at least a portion of the units identified as both interpretable and sensitive to the adversarial attack.

公开(公告)号：US20210064666A1

公开(公告)日：2021-03-04

申请号：US16551021

申请日：2019-08-26

Applicant: International Business Machines Corporation

Inventor： Dakuo Wang ,  Ming Tan ,  Chuang Gan ,  Haoyu Wang ,  Mo Yu

IPC: G06F16/9032 ,  G06N5/04

Abstract: An artificial intelligence (AI) interaction method, system, and computer program product include selecting an artificial intelligence model to respond to a query to generating a response to the query using the selected artificial intelligence model, and receiving the response to the query from the selected artificial intelligence model.

公开(公告)号：US20200242507A1

公开(公告)日：2020-07-30

申请号：US16257965

申请日：2019-01-25

Applicant: International Business Machines Corporation

Inventor： Chuang Gan ,  Quanfu Fan ,  Sijia Liu ,  Rogerio Schmidt Feris

IPC: G06N20/00 ,  H04N21/4402 ,  H04N21/439 ,  G06N3/08

Abstract: A computing system is configured to learn data-augmentations from unlabeled media. The system includes an extracting unit and an embedding unit. The extracting unit is configured to receive media data that includes moving images of an object and audio generated by the object. The extracting unit extracts an image frame of the object among the moving images and extracts an audio segment from the audio. The embedding unit is configured to generate first embeddings of the image frame and second embeddings of the audio segment, and to concatenate the first and second embeddings together to generate concatenated embeddings. The computing system labels the media data based at least in part on the concatenated embeddings.

公开(公告)号：US20240412074A1

公开(公告)日：2024-12-12

申请号：US18331211

申请日：2023-06-08

Applicant: International Business Machines Corporation ,  National Tsing Hua University

Inventor： Pin-Yu Chen ,  I-Hsin Chung ,  Bo Wu ,  Chuang Gan ,  Lei Hsiung ,  Yun-Yun Tsai ,  Tsung-Yi Ho

IPC: G06N3/094

Abstract: Some embodiments of the present disclosure are directed to systems, computer-readable media, and computer-implemented methods for neural network training. Some embodiments are directed to determining an attack order schedule for the data sample that includes a plurality of adversarial perturbation attacks associated with the data sample, and performing a composite adversarial attack process against the data set using the determined attack order schedule to generate a perturbed data sample for the data sample. Other embodiments may be disclosed or claimed.

公开(公告)号：US20240404106A1

公开(公告)日：2024-12-05

申请号：US18327608

申请日：2023-06-01

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Bo Wu ,  Chuang Gan ,  YADA ZHU ,  Pin-Yu Chen

IPC: G06T7/77 ,  G06T7/11 ,  G06V20/70

Abstract: Provided are a computer program product, system, and method for training a pose estimation model to determine anatomy keypoints in images. A teacher network, implementing machine learning, processes images representing anatomies to produce heatmaps representing keypoints of the anatomies. An anatomy parsing network, implementing machine learning, processes the images to produce segmentation representations labeling anatomies represented in the images. The segmentation representations from the anatomy parsing network and the heatmaps from the teacher network are concatenated to produce mixed heatmaps. A pose estimation model, implementing machine learning, is trained to process the images to output predicted heatmaps to minimize a loss function of the output predicted heatmaps from the pose estimation model and the mixed heatmaps.

公开(公告)号：US12087064B2

公开(公告)日：2024-09-10

申请号：US18230775

申请日：2023-08-07

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Bo Wu ,  Chuang Gan ,  Yang Zhang ,  Dakuo Wang

IPC: G06V20/58 ,  G06V30/194

CPC classification number: G06V20/584 ,  G06V30/194

Abstract: A vehicle light signal detection and recognition method, system, and computer program product include bounding, using a coarse attention module, one or more regions of an image of an automobile including at least one of a brake light and a signal light generated by automobile signals which include illuminated sections to generate one or more bounded region, removing, using a fine attention module, noise from the one or more bounded regions to generate one or more noise-free bounded regions, and identifying the at least one of the brake light and the signal light from the one or more noise-free bounded regions.