公开(公告)号：US20240273265A1

公开(公告)日：2024-08-15

申请号：US18620453

申请日：2024-03-28

Applicant: Intel Corporation

Inventor： Souvik Kundu ,  Sharath Nittur Sridhar ,  Anahita Bhiwandiwalla

IPC: G06F30/27

CPC classification number: G06F30/27

Abstract: Methods, apparatus, systems, and articles of manufacture design and test electronics using artificial intelligence are disclosed. An example apparatus includes programmable circuitry to instantiate: use a first trained artificial intelligence (AI)-based model to generate verification code based on an input design; execute the verification code to generate a verifiability score for the input design; and based on the verifiability score, use a second trained AI-model to adjust the input design.

公开(公告)号：US20220335285A1

公开(公告)日：2022-10-20

申请号：US17853518

申请日：2022-06-29

Applicant: Intel Corporation

Inventor： Sairam Sundaresan ,  Souvik Kundu

IPC: G06N3/063

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve performance of an artificial intelligence based (AI-based) model on datasets having different distributions. An example apparatus includes interface circuitry to access data, computer readable instructions, and processor circuitry to at least one of instantiate or execute the computer readable instructions to implement adversarial evaluation circuitry, convolution circuitry, and output control circuitry. The example adversarial evaluation circuitry is to determine whether the data is to be processed as adversarial data. The example convolution circuitry is to, based on whether the data is to be processed as the adversarial data, determine a convolution of an input tensor and (1) a parameter tensor corresponding to a layer of the AI-based model or (2) a noisy parameter tensor generated based on the parameter tensor. The example output control circuitry is to output a classification of the data based on the convolution.

公开(公告)号：US20220036194A1

公开(公告)日：2022-02-03

申请号：US17504282

申请日：2021-10-18

Applicant: Intel Corporation

Inventor： Sairam Sundaresan ,  Souvik Kundu

IPC: G06N3/08 ,  G06N3/04

Abstract: The present disclosure is related to techniques for optimizing artificial intelligence (AI) and/or machine learning (ML) models to reduce resource consumption while maintaining or improving AI/ML model performance. A sparse distillation framework (SDF) is provided for producing a class of parameter and compute efficient AI/ML models suitable for resource constrained applications. The SDF simultaneously distills knowledge from a compute heavy teacher model while also pruning a student model in a single pass of training, thereby reducing training and tuning times considerably. A self-attention mechanism may also replace CNNs or convolutional layers of a CNN to have better translational equivariance. Other embodiments may be described and/or claimed.

公开(公告)号：US20220036123A1

公开(公告)日：2022-02-03

申请号：US17506161

申请日：2021-10-20

Applicant: Intel Corporation

Inventor： Daniel J. Cummings ,  Juan Pablo Munoz ,  Souvik Kundu ,  Sharath Nittur Sridhar ,  Maciej Szankin

IPC: G06K9/62 ,  G06N20/00

Abstract: The present disclosure is related to machine learning model swap (MLMS) framework for that selects and interchanges machine learning (ML) models in an energy and communication efficient way while adapting the ML models to real time changes in system constraints. The MLMS framework includes an ML model search strategy that can flexibly adapt ML models for a wide variety of compute system and/or environmental changes. Energy and communication efficiency is achieved by using a similarity-based ML model selection process, which selects a replacement ML model that has the most overlap in pre-trained parameters from a currently deployed ML model to minimize memory write operation overhead. Other embodiments may be described and/or claimed.