17933473. CERTIFICATION-BASED ROBUST TRAINING BY REFINING DECISION BOUNDARY simplified abstract (International Business Machines Corporation)
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 Unanswered Questions
- 1.11 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 17933473 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 data set of images, image labels, and a perturbation schedule, determining the distance from the decision boundary for the images, applying re-weighting values and modified perturbation magnitudes to the images, calculating a total loss function, and evaluating the confidence level of the classification for certifiable robustness.
- Initializing a neural network model
- Receiving a data set of images, image labels, and a perturbation schedule
- Determining the distance from the decision boundary for the images
- Applying re-weighting values and modified perturbation magnitudes to the images
- 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 autonomous vehicles, medical imaging, security systems, and quality control in manufacturing.
Problems Solved
This technology helps in ensuring the robustness of image classification in neural networks, reducing the risk of misclassification and improving the overall performance of the system.
Benefits
The benefits of this technology include increased accuracy in image classification, enhanced reliability of neural networks, and improved safety in critical applications.
Potential Commercial Applications
Potential commercial applications of this technology include image recognition systems, surveillance systems, medical diagnosis tools, and quality inspection systems.
Possible Prior Art
One possible prior art in this field is the use of adversarial training techniques to improve the robustness of neural networks in image classification tasks.
Unanswered Questions
How does this method compare to existing techniques for certifying the robustness of image classification in neural networks?
The article does not provide a direct comparison with existing techniques, leaving the reader wondering about the specific advantages of this method over others.
What are the limitations of this method in terms of scalability and computational resources?
The article does not address the potential limitations of this method in terms of scalability and computational resources, leaving room for further exploration and analysis.
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.