Robust learning with probabilistic relaxation using hypothesis-test-based sampling
In recent years, deep learning has been a vital tool in various tasks. The performance of a neural network is usually evaluated by empirical risk minimization. However, robustness issues have gained great concern which can be fatal in safety-critical applications. Adversarial training can mitigate t...
Saved in:
Main Author: | WANG, Zilin |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/etd_coll/668 https://ink.library.smu.edu.sg/context/etd_coll/article/1666/viewcontent/GPIS_AY2022_MbR_Wang_Zilin.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Steganographic passport: an owner and user verifiable credential for deep model IP protection without retraining
by: Cui, Qi, et al.
Published: (2025) -
Reimagining education with AI
by: PAGANI, Margherita, et al.
Published: (2024) -
Mapping generative AI regulation in finance and bridging regulatory gaps
by: REMOLINA LEON, Nydia
Published: (2025) -
Understanding human-centred artificial intelligence in the banking sector
by: OBUCHETTIAR, Krishnaraj Arul, et al.
Published: (2023) -
Artificial intelligence (AI) ethics: Ethics of AI and ethical AI
by: SIAU, Keng, et al.
Published: (2020)