Invention Grant
- Patent Title: Method and system for enhancing training data and improving performance for neural network models
-
Application No.: US16702442Application Date: 2019-12-03
-
Publication No.: US11645500B2Publication Date: 2023-05-09
- Inventor: Dileep Panjwani
- Applicant: Robust Machines, Inc.
- Applicant Address: US CA San Jose
- Assignee: Robust Machines, Inc.
- Current Assignee: Robust Machines, Inc.
- Current Assignee Address: US CA San Jose
- Agent Dileep Panjwani
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06N3/04 ; G06N3/08 ; G06F17/18 ; G06N5/02

Abstract:
The present disclosure provides a system for improving performance of a neural network model. The system receives the neural network model and a training data associated with the neural network model. In addition, the system examines a first plurality of neuron activations inside the neural network model for the training data. The system examines the first plurality of neurons for creating a statistical profile of the first plurality of neuron activations. Further, the system receives a new set of data samples to improve the neural network model. Furthermore, the system examines a second plurality of neuron activations of each new sample of the new set of data samples. Moreover, the system extracts one or more data samples from the new set of data samples with largest novelty measurements. Also, the system adds the extracted one or more samples to the training data for re-training of the neural network model.
Public/Granted literature
- US20210166105A1 METHOD AND SYSTEM FOR ENHANCING TRAINING DATA AND IMPROVING PERFORMANCE FOR NEURAL NETWORK MODELS Public/Granted day:2021-06-03
Information query