International business machines corporation (20240096057). CERTIFICATION-BASED ROBUST TRAINING BY REFINING DECISION BOUNDARY simplified abstract
Contents
- 1 CERTIFICATION-BASED ROBUST TRAINING BY REFINING DECISION BOUNDARY
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 CERTIFICATION-BASED ROBUST TRAINING BY REFINING DECISION BOUNDARY - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
CERTIFICATION-BASED ROBUST TRAINING BY REFINING DECISION BOUNDARY
Organization Name
international business machines corporation
Inventor(s)
Lam Minh Nguyen of Ossining NY (US)
Wang Zhang of Cambridge MA (US)
Subhro Das of Cambridge MA (US)
Pin-Yu Chen of White Plains NY (US)
Alexandre Megretski of Acton MA (US)
Luca Daniel of Cambridge MA (US)
CERTIFICATION-BASED ROBUST TRAINING BY REFINING DECISION BOUNDARY - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240096057 titled 'CERTIFICATION-BASED ROBUST TRAINING BY REFINING DECISION BOUNDARY
Simplified Explanation
The abstract describes a computer-implemented method for certifying the robustness of image classification in a neural network. The method involves initializing a neural network model, receiving a dataset of images and labels, determining the distance from the decision boundary for the images, applying re-weighting values and perturbation magnitudes, calculating a total loss function, and evaluating the confidence level of the classification for certifiable robustness.
- Initializing a neural network model
- Receiving a dataset of images, labels, and a perturbation schedule
- Determining the distance from the decision boundary for the images
- Applying re-weighting values and modified perturbation magnitudes
- Calculating a total loss function for the images
- Evaluating the confidence level of the classification for certifiable robustness
Potential Applications
This technology can be applied in various fields such as:
- Image recognition systems
- Autonomous vehicles
- Medical imaging
Problems Solved
This technology helps in:
- Improving the robustness of image classification in neural networks
- Enhancing the accuracy of image recognition systems
- Increasing the reliability of autonomous systems
Benefits
The benefits of this technology include:
- Enhanced security in image classification
- Improved performance in real-world scenarios
- Increased trust in neural network models
Potential Commercial Applications
This technology can be commercially applied in:
- Security systems
- Surveillance technology
- Healthcare diagnostics
Possible Prior Art
One possible prior art for this technology could be research papers or patents related to improving the robustness of neural networks in image classification tasks.
Unanswered Questions
How does this method compare to existing techniques for certifying robustness in image classification neural networks?
This article does not provide a direct comparison with existing techniques for certifying robustness in image classification neural networks. Further research or a comparative study would be needed to address this question.
What are the computational requirements of implementing this method in real-world applications?
The article does not delve into the computational requirements of implementing this method in real-world applications. A detailed analysis or case study would be necessary to answer this question.
Original Abstract Submitted
a computer implemented method for certifying robustness of image classification in a neural network is provided. the method includes initializing a neural network model. the neural network model includes a problem space and a decision boundary. a processor receives a data set of images, image labels, and a perturbation schedule. images are drawn from the data set in the problem space. a distance from the decision boundary is determined for the images in the problem space. a re-weighting value is applied to the images. a modified perturbation magnitude is applied to the images. a total loss function for the images in the problem space is determined using the re-weighting value. a confidence level of the classification of the images in the data set is evaluated for certifiable robustness.