Deep learning model fairness improvement system and method based on adversarial disturbance
A technology for deep learning and system improvement, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as limiting real-world applications, and achieve the effect of improving fairness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0035] In order to make the purpose, technical scheme and advantages of the invention more clear, the invention is further described in detail through specific embodiments in combination with the accompanying drawings of the description. It should be understood that the specific embodiments described herein are only used to explain the invention and are not used to limit the invention.
[0036] Figure 1 It is the framework diagram of the fairness improvement system of the deep learning model based on antagonistic disturbance proposed by the invention, including the deployment model, disturbance generator and discriminator. The deployment model includes the feature extractor and label predictor. The disturbance generator is connected with the feature extractor, and the feature extractor is respectively connected with the label predictor and discriminator. The input of the feature extractor is an image, and the image is represented by the hidden space through the feature extractor,...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap