公开(公告)号：US20250094810A1

公开(公告)日：2025-03-20

申请号：US18823282

申请日：2024-09-03

Applicant: SRI International

Inventor： Zachary A. DANIELS ,  Jun HU ,  Michael R. LOMNITZ ,  Philip MILLER ,  Aswin NADAMUNI RAGHAVAN ,  Yuzheng ZHANG ,  Michael PIACENTINO ,  David C. ZHANG ,  Michael ISNARDI ,  Saurabh FARKYA

IPC: G06N3/084

Abstract: Method and apparatus for processing input information using an adaptable and continually learning neural network architecture comprising an encoder, at least one adaptor and at least one reconfigurator. The encoder, at least one reconfigurator and at least one adaptor determine whether the input information is out-of-distribution or in-distribution. If the input information is in distribution, the architecture extracts features from the input information, creates hyperdimensional vectors representing the features and classifies the hyperdimensional vectors. If the input information is out of distribution, the architecture creates at least one adaptor to operate with the encoder and the at least one reconfigurator to extract features from the input information, create hyperdimensional vectors representing the features and classify the hyperdimensional vectors.

公开(公告)号：US20250156762A1

公开(公告)日：2025-05-15

申请号：US18944744

申请日：2024-11-12

Applicant: SRI International

Inventor： Aswin NADAMUNI RAGHAVAN ,  David Chao ZHANG ,  Saurabh FARKYA ,  Zachary Alan DANIELS ,  Michael PIACENTINO ,  Gooitzen S. VAN DER WAL ,  Philip MILLER ,  Michael Richard LOMNITZ ,  Abrar Abdullah RAHMAN ,  Edison MUCLLARI ,  Muhammad Shahir RAHMAN

IPC: G06N20/00

Abstract: A method, apparatus, and system for efficient machine learning with query-based knowledge assistance includes determining a state of data captured by a sensor in communication with a first edge device to determine if the captured data includes data that is out of distribution based on a trained inference model of the first edge device, if it is identified that an amount of out of distribution data in the captured data is preventing the trained inference model from making an accurate prediction, communicating a request for resources to a second edge device or a server to elicit a response from the second edge device or the server including resources required to update the trained inference model, receiving the requested resources, updating the trained inference model using the received resources, and making a prediction for the received captured data using the updated, trained inference model.

公开(公告)号：US20250069356A1

公开(公告)日：2025-02-27

申请号：US18815217

申请日：2024-08-26

Applicant: SRI International

Inventor： Aswin NADAMUNI RAGHAVAN ,  Jun HU ,  David C. ZHANG ,  Michael R. LOMNITZ ,  Yuzheng ZHANG ,  Michael PIACENTINO ,  Philip MILLER ,  Zachary A. DANIELS ,  Saurabh FARKYA ,  Abrar A. RAHMAN ,  Abdelrahman SHARAFELDIN

IPC: G06V10/25 ,  G06V10/74

Abstract: A method, apparatus, and system for object detection on an edge device include projecting a hyperdimensional vector of a query request for an image received at the edge device into a hyperdimensional embedding space to identify at least one exemplar in the hyperdimensional embedding space having a predetermined measure of similarity to the query request using a network trained to: generate a respective hyperdimensional image vector and a respective hyperdimensional text vector for the image and received text descriptions of the image, generate a hyperdimensional query text vector of the query request, combine and embed respective ones of the hyperdimensional image vectors and the hyperdimensional text vectors into a hyperdimensional embedding space to generate respective exemplars, project the hyperdimensional query text vector into the hyperdimensional embedding space, and determine a similarity measure between the hyperdimensional query text vector and at least one of the respective exemplars.

公开(公告)号：US20240185591A1

公开(公告)日：2024-06-06

申请号：US18282049

申请日：2022-03-24

Applicant: SRI INTERNATIONAL

Inventor： Aswin NADAMUNI RAGHAVAN ,  Michael R. PIACENTINO ,  Michael A. ISNARDI ,  Indhumathi KANDASWAMY ,  Saurabh FARKYA ,  David Chao ZHANG ,  Gooitzen S. VAN DER WAL ,  Zachary DANIELS ,  Yuzheng ZHANG

IPC: G06V10/82 ,  G06N3/0442 ,  G06V10/764

CPC classification number: G06V10/82 ,  G06N3/0442 ,  G06V10/764

Abstract: Method and apparatus for processing data using a reconfigurable, hyperdimensional neural network architecture comprising a feature extractor and a classifier. The feature extractor comprises a neural network for encoding input information into hyperdimensional (HD) vectors and extracting at least one particular HD vector representing at least one feature within the input information, wherein the neural network comprises no more than one multiply and accumulate operator. The classifier is coupled to the feature extractor for classifying the at least one particular HD vector to produce an indicium of classification for the at least one particular HD vector and wherein the classifier does not comprise any multiply and accumulate operators.