Large-Scale Optimization with Small-Scale Data
| 项目名称： | Large-Scale Optimization with Small-Scale Data |
| 摘要： | All levels of autonomy in vehicles face a critical problem due to the fragility and lack of robustness of state of the art image classifiers to perturbations in the input image. Specifically, it has been repeatedly shown that classifiers that enjoy extremely high accuracy on test sets and challenge sets, are remarkably susceptible to misclassifying images that have small, but planted, perturbations. Stop signs can be misclassified as yield signs, with modifications that are imperceptible to the casual human observer. Many researchers have identified this as a critical problem for neural networks. The research team's approach grows directly out of a previously funded D-STOP project. In that work, the team has been working on developing fast stochastic gradient descent (SGD)-based algorithms for large scale inference. The research team's preliminary experiments have demonstrated that those ideas can in fact be used to defend against these so-called adversarial attacks. The research team's proposal is to study how the natural exploration of the sample space that is drive by their SGD approach can be mapped to implicitly define the natural manifold of images. The research team conjectures that this is the critical concept for defending against adversarial attacks. |
| 状态： | Active |
| 资助组织： | Office of the Assistant Secretary for Research and Technology |
| 项目负责人： | Bhat, Chandra R |
| 执行机构： | Data-Supported Transportation Operations and Planning Center |
| 主要研究人员： | Caramanis, Constantine |
| 开始时间： | 20180901 |
| 预计完成日期： | 20200831 |
| 实际结束时间： | 0 |
相关文献
- An Automated System for Large-Scale Intersection Marking Data Collection and Condition Assessment
- Diesel-Electric Locomotive Energy Recovery and Conversion
- Large-Scale Laboratory Testing of Geosynthetics in Roadway Applications
- Construction of Three Large-Scale Robots Capable of Constructing UHPC Shell, Repair of Culvert and Automated MFL
- Techno-Economic Analyses of Large-Scale Electric Vehicle Systems
- Socio-economic Implications of Large-scale Electric Vehicle Systems
检索历史
应用推荐
