Related papers: Trustworthiness of Laser-Induced Breakdown Spectro…
Flaw detection in non-destructive testing, especially in complex signals like ultrasonic data, has thus far relied heavily on the expertise and judgement of trained human inspectors. While automated systems have been used for a long time,…
Deep Learning (DL) methods have emerged as one of the most powerful tools for functional approximation and prediction. While the representation properties of DL have been well studied, uncertainty quantification remains challenging and…
Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…
Existing approaches to predictive uncertainty rely either on multi-hypothesis prediction, which promotes diversity but lacks principled aggregation, or on ensemble learning, which improves accuracy but rarely captures the structured…
3D reconstruction is a useful tool for surgical planning and guidance. However, the lack of available medical data stunts research and development in this field, as supervised deep learning methods for accurate disparity estimation rely…
The widespread adoption of mobile communication technology has led to a severe shortage of spectrum resources, driving the development of cognitive radio technologies aimed at improving spectrum utilization, with spectrum sensing being the…
Disentangled representation learning aims to uncover latent variables underlying the observed data, and generally speaking, rather strong assumptions are needed to ensure identifiability. Some approaches rely on sufficient changes on the…
This paper presents a deep learning-based estimation of the intensity component of MultiSpectral bands by considering joint multiplication of the neighbouring spectral bands. This estimation is conducted as part of the component…
Latent class models are widely used for identifying unobserved subgroups from multivariate categorical data in social sciences, with binary data as a particularly popular example. However, accurately recovering individual latent class…
Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…
Considerable research has been devoted to deep learning-based predictive models for system prognostics and health management in the reliability and safety community. However, there is limited study on the utilization of deep learning for…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…
Fine-Grained Change Detection and Regression Analysis are essential in many applications of ArtificialIntelligence. In practice, this task is often challenging owing to the lack of reliable ground truth information andcomplexity arising…
Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on…
Meta-Learning has emerged as a research direction to better transfer knowledge from related tasks to unseen but related tasks. However, Meta-Learning requires many training tasks to learn representations that transfer well to unseen tasks;…
Ultrafast lasers ($< 500$ fs) have enabled laser-matter interactions at intensities exceeding $10^{18} \rm{Wcm}^{-2}$ with only millijoules of laser energy. However, as pulse durations become shorter, larger spectral bandwidths are…
Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task, by jointly training on a secondary task. This paper introduces…
Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model…
Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…
Data augmentation has emerged as a powerful technique for improving the performance of deep neural networks and led to state-of-the-art results in computer vision. However, state-of-the-art data augmentation strongly distorts training…