Patents by Inventor Pin Yu Chen
Pin Yu Chen 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).
-
Publication number: 20240136117Abstract: A multi-phase coupled inductor includes a first iron core, a second iron core, and a plurality of coil windings. The first iron core includes a first body and a plurality of first core posts. The plurality of first core posts are connected to the first body. The second iron core is opposite to the first iron core. The second iron core and the first body are spaced apart from each other by a gap. The plurality of coil windings wrap around the plurality of first core posts, respectively. Each of the coil windings has at least two coils.Type: ApplicationFiled: October 1, 2023Publication date: April 25, 2024Inventors: HUNG-CHIH LIANG, PIN-YU CHEN, HANG-CHUN LU, YA-WEN YANG, YU-TING HSU, WEI-ZHI HUANG
-
Publication number: 20240096057Abstract: A computer implemented method for certifying robustness of image classification in a neural network is provided. The method includes initializing a neural network model. The neural network model includes a problem space and a decision boundary. A processor receives a data set of images, image labels, and a perturbation schedule. Images are drawn from the data set in the problem space. A distance from the decision boundary is determined for the images in the problem space. A re-weighting value is applied to the images. A modified perturbation magnitude is applied to the images. A total loss function for the images in the problem space is determined using the re-weighting value. A confidence level of the classification of the images in the data set is evaluated for certifiable robustness.Type: ApplicationFiled: September 19, 2022Publication date: March 21, 2024Inventors: Lam Minh Nguyen, Wang Zhang, Subhro Das, Pin-Yu Chen, Alexandre Megretski, Luca Daniel
-
Publication number: 20240065765Abstract: A method of orthopedic treatment includes steps of: by using a computer aided design (CAD) tool based on profile data that is related to a to-be-treated part of a bone of a patient, obtaining a model of a preliminary instrument that substantially fits the to-be-treated part; by using the CAD tool, obtaining a model of a patient specific instrument (PSI) based on the model of the preliminary instrument; producing the PSI based on the model of the PSI, the PSI being adjustable; performing medical operation on the to-be-treated part, and then attaching the PSI to the to-be-treated part; after attaching the PSI to the to-be-treated part, adjusting the PSI such that the PSI is adapted to real conditions of the to-be-treated part.Type: ApplicationFiled: August 22, 2023Publication date: February 29, 2024Inventors: Alvin Chao-Yu CHEN, Yi-Sheng CHAN, Chi-Pin HSU, Shang-Chih LIN, Chin-Ju WU, Jeng-Ywan JENG
-
Publication number: 20240045974Abstract: 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.Type: ApplicationFiled: October 20, 2023Publication date: February 8, 2024Inventors: Pin-Yu Chen, Sijia Liu, Lingfei Wu, Chia-Yu Chen
-
Publication number: 20240037940Abstract: A computer vision temporal action localization (TAL) computing tool and operations are provided. The TAL computing tool receives a coarse temporal bounding box, having a first start point and a first end point, for an action in the input video data, and a first set of logits, where each logit corresponds to a potential classification of the action in the input video data. The TAL computing tool executes a first engine on the coarse temporal bounding box to generate a second set of logits, and a second engine on the first set of logits to generate a refined temporal bounding box having a second start point and a second end point. The TAL computing tool performs the computer vision temporal action localization operation based on the second set of logits and the refined temporal bounding box to specify a temporal segment of the input video data corresponding to an action represented in the input video data, and a corresponding classification of the action represented in the temporal segment.Type: ApplicationFiled: July 28, 2022Publication date: February 1, 2024Inventors: Bo Wu, Chuang Gan, Pin-Yu Chen, Yang Zhang, Xin Zhang
-
Patent number: 11880765Abstract: A processor training a reinforcement learning model can include receiving a first dataset representing an observable state in reinforcement learning to train a machine to perform an action. The processor receives a second dataset. Using the second dataset, the processor trains a machine learning classifier to make a prediction about an entity related to the action. The processor extracts an embedding from the trained machine learning classifier, and augments the observable state with the embedding to create an augmented state. Based on the augmented state, the processor trains a reinforcement learning model to learn a policy for performing the action, the policy including a mapping from state space to action space.Type: GrantFiled: October 19, 2020Date of Patent: January 23, 2024Assignees: International Business Machines Corporation, University of Illinois at Urbana-ChampaignInventors: Pin-Yu Chen, Yada Zhu, Jinjun Xiong, Kumar Bhaskaran, Yunan Ye, Bo Li
-
Publication number: 20240001198Abstract: A method, a device, and a computer readable storage medium for improving the physical performance of the user are provided. The method includes: determining a reference value of the physical performance of the user in a first reference time point of a physical activity duration and a final target value of the physical performance corresponding to a final target time; determining a plurality of middle target values of the physical performance arranged in increasing order in the physical activity duration based on the reference value, the final target value, and the final target time, wherein the plurality of middle target values of the physical performance respectively corresponds to a plurality middle target times; and providing a physical activity suggestion to gradually meet the target values of the physical performance.Type: ApplicationFiled: June 30, 2022Publication date: January 4, 2024Inventors: PIN-YU CHEN, CHUNG-YEN WU
-
Patent number: 11853713Abstract: Techniques that facilitate graph similarity analytics are provided. In one example, a system includes an information component and a similarity component. The information component generates a first information index indicative of a first entropy measure for a first graph-structured dataset associated with a machine learning system. The information component also generates a second information index indicative of a second entropy measure for a second graph-structured dataset associated with the machine learning system. The similarity component determines similarity between the first graph-structured dataset and the second graph-structured dataset based on a graph similarity computation associated with the first information index and the second information index.Type: GrantFiled: April 17, 2018Date of Patent: December 26, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Pin-Yu Chen, Lingfei Wu, Chia-Yu Chen, Yada Zhu
-
Patent number: 11853702Abstract: Generate, for each of the words of a common vocabulary of first and second text corpora, a first word embedding vector in the first text corpus and a second word embedding vector in the second text corpus. Generate, for each word in a random sample of non-landmark words, an artificially shifted word embedding vector by modifying the first word embedding vector for that word. Train a machine learning classifier to predict whether an artificial shift has been injected for a given word, based on the artificially shifted word embedding vector and the second word embedding vector for the given word. Predict semantic shifts for at least a plurality of the words of the common vocabulary by providing the first word embedding vectors and the second word embedding vectors for at least the plurality of the words of the common vocabulary as input to the trained machine learning classifier.Type: GrantFiled: January 29, 2021Date of Patent: December 26, 2023Assignees: International Business Machines Corporation, RENSSELAER POLYTECHNIC INSTITUTEInventors: Pin-Yu Chen, MaurĂcio Gruppi, Sibel Adali
-
Publication number: 20230409898Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include training a neural network and predicting structural feature sets with the neural network. The operations may include producing predicted structures with the neural network using the structural feature sets, converting the predicted structures into predicted graphs with predicted edges, and comparing predicted graphs to training graphs and predicted edges to training edges to obtain a comparison. The operations may include training a model with the comparison, constructing a graph with the neural network using a node feature set, and reducing missing edges in the graph with the model.Type: ApplicationFiled: June 17, 2022Publication date: December 21, 2023Inventors: Pin-Yu Chen, Siyu Huo, Tengfei Ma, Lingfei Wu, Kai Guo, Federica Rigoldi, Benedetto Marelli, Markus Jochen Buehler
-
Publication number: 20230401435Abstract: 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.Type: ApplicationFiled: June 13, 2022Publication date: December 14, 2023Inventors: Pin-Yu Chen, Tejaswini Pedapati, Bo Wu, Chuang Gan, Chunheng Jiang, Jianxi Gao
-
Patent number: 11839456Abstract: The present invention discloses a method for determining a maximum value of a heart rate data of a user performing a physical activity. Acquire first heart rate data in a first duration of the physical activity performed by the user. Acquire motion data in the first duration of the physical activity performed by the user. Calculate second heart rate data based on the motion data in the first duration of the physical activity performed by the user by a mathematical model and estimate the maximum value of the heart rate data of the user based on a comparison between the first first heart rate data and the second heart rate data.Type: GrantFiled: July 14, 2021Date of Patent: December 12, 2023Assignee: BOMDIC INC.Inventors: Szu-Hong Chen, Pin-Yu Chen, Tai-Yu Huang, Yu-Ting Liu
-
Patent number: 11836256Abstract: An adversarial robustness testing method, system, and computer program product include testing a robustness of a black-box system under different access settings via an accelerator.Type: GrantFiled: January 24, 2019Date of Patent: December 5, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Pin-Yu Chen, Sijia Liu, Lingfei Wu, Chia-Yu Chen
-
Publication number: 20230368529Abstract: One or more computer processors improve action recognition by removing inference introduced by visual appearances of objects within a received video segment. The one or more computer processors extract appearance information and structure information from a received video segment. The one or more computer processors calculate a factual inference (TE) for the received video segment utilizing the extracted appearance information and structure information. The one or more computer processors calculate a counterfactual debiasing inference (NDE) for the received video segment. The one or more computer processors calculate a total indirect effect (TIE) by subtracting the calculated counterfactual debiased inference from the calculated factual inference. The one or more computer processors action recognize the received video segment by selecting a classification result associated with a highest calculated TIE.Type: ApplicationFiled: May 10, 2022Publication date: November 16, 2023Inventors: Bo Wu, Chuang Gan, Pin-Yu Chen, Zhenfang Chen, Dakuo Wang
-
Publication number: 20230368510Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include receiving an input, extracting features from the input, and mining object relations using the features. The operations may include determining feature vectors using the object relations and generating, using the feature vectors, an output indicating a target region, wherein the target region corresponds to the input.Type: ApplicationFiled: May 13, 2022Publication date: November 16, 2023Inventors: Zhenfang Chen, Chuang Gan, Bo Wu, Pin-Yu Chen
-
Publication number: 20230360364Abstract: 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.Type: ApplicationFiled: May 5, 2022Publication date: November 9, 2023Inventors: Bo Wu, Chuang Gan, Pin-Yu Chen, Xin Zhang
-
Patent number: 11800633Abstract: An inductor and a power module are respectively provided. The inductor includes an insulating body and a conductive body. The insulating body has a top surface and a bottom surface. The conductive body includes two pin parts and a heat dissipation part. A portion of each of the pin parts is exposed outside the bottom surface. The portions of the two pin parts exposed outside the insulating body are configured to fix to a circuit board. The heat dissipation part is connected to the two pin parts, the heat dissipation part is exposed outside the top surface, and the heat dissipation part is configured to connect to an external heat dissipation member. When the inductor is fixed to the circuit board through the two pin parts exposed outside the bottom surface, the two pin parts and the bottom surface jointly define an accommodating space for accommodating a chip.Type: GrantFiled: November 10, 2021Date of Patent: October 24, 2023Assignee: CHILISIN ELECTRONICS CORP.Inventors: Hung-Chih Liang, Pin-Yu Chen, Hsiu-Fa Yeh, Hang-Chun Lu, Ya-Wan Yang, Yu-Ting Hsu
-
Publication number: 20230325469Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to classifying accuracy of analytical model, such as a neural network. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise an accessing component that accesses an analytical model, a deviation component that generates combined results of the analytical model in response to a set of inputs that vary in degree of perturbation of a set of test data, and an analysis component that compares a range of the combined results to a range of the ideal results.Type: ApplicationFiled: April 7, 2022Publication date: October 12, 2023Inventors: Yair Zvi Schiff, Brian Leo Quanz, Payel Das, Pin-Yu Chen
-
Publication number: 20230214705Abstract: An input transformation function that transforms input data for a second machine learning system is learned using a first machine learning system, the learning being based on minimizing a summation of a task loss and a post-activation density loss. The input data is transformed using the learned input transformation function to alter the post-activation density to reduce an amount of energy consumed for an inferencing task and the inferencing task is carried out on the transformed input data using the second machine learning system.Type: ApplicationFiled: December 30, 2021Publication date: July 6, 2023Inventors: Pin-Yu Chen, Nandhini Chandramoorthy, Karthik V Swaminathan, Jinjun Xiong, Devansh Paresh Shah, Bo Li
-
Patent number: 11640532Abstract: 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.Type: GrantFiled: December 3, 2021Date of Patent: May 2, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam