Robust and Generalizable Machine Learning through Generative Models,Adversarial Training, and Physics Priors
abstract: Machine learning has demonstrated great potential across a wide range of applications such as computer vision, robotics, speech recognition, drug discovery, material science, and physics simulation. Despite its current success, however, there are still two major challenges for machine lear...
Other Authors: | Yao, Houpu (Author) |
---|---|
Format: | Doctoral Thesis |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/2286/R.I.54939 |
Similar Items
-
Learning generalizable device placement algorithms for distributed machine learning
by: Addanki, Ravichandra.
Published: (2019) -
Improving the robustness and accuracy of biomedical language models through adversarial training
by: Moradi, M., et al.
Published: (2022) -
Adversarially-trained autoencoders for robust unsupervised new physics searches
by: Andrew Blance, et al.
Published: (2019-10-01) -
Deep learning with physical and power-spectral priors for robust image inversion
by: Deng, Mo,Ph. D.Massachusetts Institute of Technology.
Published: (2020) -
Generalizability of Electronic Health Record-Based Machine Learning Models
by: Wissel, Benjamin D.
Published: (2021)