Patents by Inventor Hongxu Yin

Hongxu Yin 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: 11521068
    Abstract: According to various embodiments, a method for generating one or more optimal neural network architectures is disclosed. The method includes providing an initial seed neural network architecture and utilizing sequential phases to synthesize the neural network until a desired neural network architecture is reached. The phases include a gradient-based growth phase and a magnitude-based pruning phase.
    Type: Grant
    Filed: October 25, 2018
    Date of Patent: December 6, 2022
    Assignee: THE TRUSTEES OF PRINCETON UNIVERSITY
    Inventors: Xiaoliang Dai, Hongxu Yin, Niraj K. Jha
  • Publication number: 20220292360
    Abstract: Apparatuses, systems, and techniques to remove one or more nodes of a neural network. In at least one embodiment, one or more nodes of a neural network are removed, based on, for example, whether the one or more nodes are likely to affect performance of the neural network.
    Type: Application
    Filed: March 15, 2021
    Publication date: September 15, 2022
    Inventors: Maying Shen, Pavlo Molchanov, Hongxu Yin, Jose Manuel Alvarez Lopez
  • Publication number: 20220284232
    Abstract: Apparatuses, systems, and techniques to identify one or more images used to train one or more neural networks. In at least one embodiment, one or more images used to train one or more neural networks are identified, based on, for example, one or more labels of one or more objects within the one or more images.
    Type: Application
    Filed: March 1, 2021
    Publication date: September 8, 2022
    Inventors: Hongxu Yin, Arun Mallya, Arash Vahdat, Jose Manuel Alvarez Lopez, Jan Kautz, Pavlo Molchanov
  • Publication number: 20220284283
    Abstract: Apparatuses, systems, and techniques to invert a neural network. In at least one embodiment, one or more neural network layers are inverted and, in at least one embodiment, loaded in reverse order.
    Type: Application
    Filed: March 8, 2021
    Publication date: September 8, 2022
    Inventors: Hongxu Yin, Pavlo Molchanov, Jose Manuel Alvarez Lopez, Xin Dong
  • Publication number: 20220240864
    Abstract: According to various embodiments, a machine-learning based system for diabetes analysis is disclosed. The system includes one or more processors configured to interact with a plurality of wearable medical sensors (WMSs). The processors are configured to receive physiological data from the WMSs and demographic data from a user interface. The processors are further configured to train at least one neural network based on a grow-and-prune paradigm to generate at least one diabetes inference model. The neural network grows at least one of connections and neurons based on gradient information and prunes away at least one of connections and neurons based on magnitude information. The processors are also configured to output a diabetes-based decision by inputting the received physiological data and demographic data into the generated diabetes inference model.
    Type: Application
    Filed: June 16, 2020
    Publication date: August 4, 2022
    Applicant: The Trustees of Princeton University
    Inventors: Hongxu Yin, Bilal Mukadam, Xiaoliang Dai, Niraj K. Jha
  • Publication number: 20220222534
    Abstract: According to various embodiments, a method for generating a compact and accurate neural network for a dataset that has initial data and is updated with new data is disclosed. The method includes performing a first training on the initial neural network architecture to create a first trained neural network architecture. The method additionally includes performing a second training on the first trained neural network architecture when the dataset is updated with new data to create a second trained neural network architecture. The second training includes growing one or more connections for the new data based on a gradient of each connection, growing one or more connections for the new data and the initial data based on a gradient of each connection, and iteratively pruning one or more connections based on a magnitude of each connection until a desired neural network architecture is achieved.
    Type: Application
    Filed: March 20, 2020
    Publication date: July 14, 2022
    Applicant: The Trustees of Princeton University
    Inventors: Xiaoliang DAI, Hongxu YIN, Niraj K. JHA
  • Publication number: 20210182683
    Abstract: According to various embodiments, a method for generating one or more optimal neural network architectures is disclosed. The method includes providing an initial seed neural network architecture and utilizing sequential phases to synthesize the neural network until a desired neural network architecture is reached. The phases include a gradient-based growth phase and a magnitude-based pruning phase.
    Type: Application
    Filed: October 25, 2018
    Publication date: June 17, 2021
    Applicant: The Trustees of Princeton University
    Inventors: Xiaoliang DAI, Hongxu YIN, Niraj K. JHA
  • Publication number: 20210133540
    Abstract: According to various embodiments, a method for generating an optimal hidden-layer long short-term memory (H-LSTM) architecture is disclosed. The H-LSTM architecture includes a memory cell and a plurality of deep neural network (DNN) control gates enhanced with hidden layers. The method includes providing an initial seed H-LSTM architecture, training the initial seed H-LSTM architecture by growing one or more connections based on gradient information and iteratively pruning one or more connections based on magnitude information, and terminating the iterative pruning when training cannot achieve a predefined accuracy threshold.
    Type: Application
    Filed: March 14, 2019
    Publication date: May 6, 2021
    Applicant: The Trustees of Princeton University
    Inventors: Xiaoliang DAI, Hongxu YIN, Niraj K. JHA
  • Publication number: 20200382286
    Abstract: According to various embodiments, an Internet of Things (IoT) sensor architecture is disclosed. The architecture includes one or more IoT sensor components configured to capture data and one or more processors configured to analyze the captured data. The processors include a data compression module configured to convert received data into compressed data, a machine learning module configured to extract features from the received data and classify the extracted features, and an encryption/hashing module configured to encrypt and ensure integrity of resulting data from the machine learning module or the received data.
    Type: Application
    Filed: January 10, 2019
    Publication date: December 3, 2020
    Inventors: Ayten Ozge Akamandor, Hongxu Yin, Niraj Jha
  • Publication number: 20200320395
    Abstract: A method for training a machine learning model, including acquiring an initial machine learning model, updating features of the initial machine learning model, updating dimension of the initial machine learning model based on the updated features of the initial machine learning model and one or more latency hysteresis points obtained based on a hardware profile of an accelerator configured to perform machine learning operations, and generating a final machine learning model based on the updated dimensions.
    Type: Application
    Filed: April 3, 2019
    Publication date: October 8, 2020
    Inventors: Hongxu YIN, Weifeng ZHANG, Guoyang CHEN
  • Publication number: 20190374160
    Abstract: According to various embodiments, a hierarchical health decision support system (HDSS) configured to receive data from one or more wearable medical sensors (WMSs) is disclosed. The system includes a clinical decision support system, which includes a diagnosis engine configured to generate diagnostic suggestions based on the data received from the WMSs. The HDSS is configured with a plurality of tiers to sequentially model general healthcare from daily health monitoring, initial clinical checkup, detailed clinical examination, and postdiagnostic treatment.
    Type: Application
    Filed: December 29, 2017
    Publication date: December 12, 2019
    Applicant: The Trustees of Princeton University
    Inventors: Hongxu Yin, Niraj K. Jha