Method for evaluating an artifitial neural network model performance and system using the same
The system addresses NPU commercialization challenges by evaluating neural network models across various processors, providing secure and efficient performance predictions for NPU selection and deployment.
KR1020260131104APending Publication Date: 2026-09-01DEEPX CO LTD
0 Cites 0 Cited by
Patent Information
- Application Number
- KR1020260155655
- Authority / Receiving Office
- KR · KR
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-11-30
- Filing Date
- 2026-08-19
- Publication Date
- 2026-09-01
AI Technical Summary
Technical Problem
The commercialization of neural processing units (NPUs) for artificial neural network models is hindered by the lack of information on processor selection, uncertainty about model compatibility and performance, and difficulty in predicting power consumption and FPS before deployment.
Method used
An artificial neural network model performance evaluation system that includes multiple neural processors and a server, which processes user models, applies evaluation datasets, and generates performance parameters, providing recommendations based on processor selection and compilation options.
Benefits of technology
Enables users to quickly determine NPU compatibility and performance before purchase, ensuring secure and efficient model deployment.
✦ Generated by Eureka AI based on patent content.
Abstract
An artificial neural network model performance evaluation system is disclosed. The ekFMS artificial neural network model performance evaluation system disclosed herein includes a plurality of neural processors, each comprising a first neural processor of a first configuration and a second neural processor of a second configuration different from the first configuration, at least one operating processor, and a memory for storing instructions used by the at least one operating processor. The at least one operating processor receives a first processor selection information for selecting at least one of an artificial neural network model, a first neural processor, and a second neural processor, and compile option information. By compiling the artificial neural network model according to the compile option, the system processes the artificial neural network model used by the neural processor selected by the first processor selection information, applies at least one evaluation data set to the artificial neural network model by the neural processor selected by the first processor selection information, generates at least one first performance parameter related to the performance of the neural processor selected by the first processor selection information, and can report a layer or an operation among a plurality of layers of the artificial neural network model that cannot be processed by the neural processor selected by the first processor selection information.
Need to check novelty before this filing date? Find Prior Art