Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Attribution Robustness Of Neural Networks, Sunanda Gamage
Attribution Robustness Of Neural Networks, Sunanda Gamage
Electronic Thesis and Dissertation Repository
While deep neural networks have demonstrated excellent learning capabilities, explainability of model predictions remains a challenge due to their black box nature. Attributions or feature significance methods are tools for explaining model predictions, facilitating model debugging, human-machine collaborative decision making, and establishing trust and compliance in critical applications. Recent work has shown that attributions of neural networks can be distorted by imperceptible adversarial input perturbations, which makes attributions unreliable as an explainability method. This thesis addresses the research problem of attribution robustness of neural networks and introduces novel techniques that enable robust training at scale.
Firstly, a novel generic framework …
Modeling Thermosyphon And Heat Pipe Performance For Mold Cooling Applications, Dwaipayan Sarkar
Modeling Thermosyphon And Heat Pipe Performance For Mold Cooling Applications, Dwaipayan Sarkar
Electronic Thesis and Dissertation Repository
Thermosyphons are enhanced heat transfer devices that can continuously transfer very large amounts of heat rapidly over long distances with small temperature differences. The high heat transfer rate is achieved through simultaneous boiling and condensation of the working fluid and the continuous heat transfer is achieved through recirculation of the working fluid in its liquid and vapor phase. A potentially important application of the thermosyphons has been towards reducing the cycle times of the mold cooling processes which would provide economic incentives to the automotive industry.
Different operational and geometrical parameters such as the input heating power, fill ratio (FR), …