Training-free neural active learning with initialization robustness guarantees
Neural active learning techniques so far have focused on enhancing the predic- tive capabilities of the networks. However, safety-critical applications necessi- tate not only good predictive performance but also robustness to randomness in the model-fitting process. To address this, we present th...
Saved in:
Main Author: | Singh, Jasraj |
---|---|
Other Authors: | Tong Ping |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/166498 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Adversarial robustness of deep reinforcement learning
by: Qu, Xinghua
Published: (2022) -
Towards robust sensing and recognition : from statistical learning to transfer learning
by: Yang, Jianfei
Published: (2020) -
Training deep neural network models for accurate recognition of texts in scenes
by: Lim, Joshen Eng Keat
Published: (2020) -
Attack on training effort of deep learning
by: How, Kevin Kai-Wen
Published: (2021) -
Adversarial training using meta-learning for BERT
by: Low, Timothy Jing Haen
Published: (2022)