Exploring Probabilistic Models for Semi-supervised Learning
It addresses safety-critical AI applications, but appears incremental as it builds on existing probabilistic methods in semi-supervised learning.
This thesis tackles the problem of improving safety in AI systems through probabilistic models for semi-supervised learning, achieving competitive performance with reliable uncertainty estimates for applications like autonomous driving and medical imaging.
This thesis studies advanced probabilistic models, including both their theoretical foundations and practical applications, for different semi-supervised learning (SSL) tasks. The proposed probabilistic methods are able to improve the safety of AI systems in real applications by providing reliable uncertainty estimates quickly, and at the same time, achieve competitive performance compared to their deterministic counterparts. The experimental results indicate that the methods proposed in the thesis have great value in safety-critical areas, such as the autonomous driving or medical imaging analysis domain, and pave the way for the future discovery of highly effective and efficient probabilistic approaches in the SSL sector.