The explorative and iterative nature of developing and operating ML applications leads to a
variety of artifacts, such as datasets, features, models, hyperparameters, metrics, software …

Data drift is a thorny challenge when deploying person re-identification (ReID) models into
real-world devices, where the data distribution is significantly different from that of the …

Predictive machine learning models nowadays are often updated in a stateless and
expensive way. The two main future trends for companies that want to build machine …

Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models
after deployment. To tackle such challenges, we propose a progressive continual learning …

Continuously learning new classes without catastrophic forgetting is a challenging problem
for on-device environmental sound classification given the restrictions on computation …

Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models
after deployment. This problem will be more challenging if KWS models are further required …

Continual learning has recently become a primary paradigm for deep neural network
models in modern artificial intelligence services, where streaming data patterns frequently …

The success of today's AI applications requires not only model training (Model-centric) but
also data engineering (Data-centric). In data-centric AI, active learning (AL) plays a vital role …

Machine Learning Operations (MLOps), derived from DevOps, aims to unify the
development, deployment, and maintenance of machine learning (ML) models. Continuous …

This thesis explores the integration of artificial intelligence (AI) in Otolaryngology–Head and
Neck Surgery, focusing on advancements in computer vision for endoscopy and surgical …