Sökning: "Multi-Task Learning"

Hittade 5 avhandlingar innehållade orden Multi-Task Learning.

1. 1. Sharing to learn and learning to share : Fitting together metalearning and multi-task learning

   Författare :Richa Upadhyay; Marcus Liwicki; Ronald Phlypo; Rajkumar Saini; Atsuto Maki; Luleå tekniska universitet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Multi-task learning; Meta learning; transfer learning; knowledge sharing algorithms; Machine Learning; Maskininlärning;

   Sammanfattning : This thesis focuses on integrating learning paradigms that ‘share to learn,’ i.e., Multitask Learning (MTL), and ‘learn (how) to share,’ i.e. LÄS MER

3. 2. Advancing Clinical Decision Support Using Machine Learning & the Internet of Medical Things : Enhancing COVID-19 & Early Sepsis Detection

   Författare :Mahbub Ul Alam; Rahim Rahmani; Jaakko Hollmén; Sadok Ben Yahia; Stockholms universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Internet of Medical Things; Patient-Centric Healthcare; Clinical Decision Support System; Predictive Modeling in Healthcare; Health Informatics; Healthcare analytics; COVID-19; Sepsis; COVID-19 Detection; Early Sepsis Detection; Lung Segmentation Detection; Medical Data Annotation Scarcity; Medical Data Sparsity; Medical Data Heterogeneity; Medical Data Security Privacy; Practical Usability Enhancement; Low-End Device Adaptability; Medical Significance; Interpretability; Visualization; LIME; SHAP; Grad-CAM; LRP; Electronic Health Records; Thermal Image; Tabular Medical Data; Chest X-ray; Machine Learning; Deep Learning; Federated Learning; Semi-Supervised Machine Learning; Multi-Task Learning; Transfer Learning; Multi-Modality; Natural Language Processing; ClinicalBERT; GAN; data- och systemvetenskap; Computer and Systems Sciences;

   Sammanfattning : This thesis presents a critical examination of the positive impact of Machine Learning (ML) and the Internet of Medical Things (IoMT) for advancing the Clinical Decision Support System (CDSS) in the context of COVID-19 and early sepsis detection.It emphasizes the transition towards patient-centric healthcare systems, which necessitate personalized and participatory care—a transition that could be facilitated by these emerging fields. LÄS MER

4. 3. Study on Decentralized Machine Learning and Applications to Wireless Caching Networks

   Författare :Yu Ye; Ming Xiao; Zhu Han; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Distributed multi-task learning; decentralized optimization; ADMM; mobility-aware wireless caching; Distribuerat lärande med flera uppgifter; decentraliserad optimering; ADMM; mobilitetsmedveten trådlös cache; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : To promote the development of distributed machine learning, it is crucial to provide efficient models and training algorithms. This thesis is devoted to the design of distributed multi-task learning and decentralized algorithms, as well as the application of distributed machine learning in wireless caching networks. LÄS MER

5. 4. Source Code Representations of Deep Learning for Program Repair

   Författare :Zimin Chen; Martin Monperrus; Benoit Baudry; Zhendong Su; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Code Representation; Deep Learning; Program Repair; Datalogi; Computer Science;

   Sammanfattning : Deep learning, leveraging artificial neural networks, has demonstrated significant capabilities in understanding intricate patterns within data. In recent years, its prowess has been extended to the vast domain of source code, where it aids in diverse software engineering tasks such as program repair, code summarization, and vulnerability detection. LÄS MER

7. 5. Efficient Exploration and Robustness in Controlled Dynamical Systems

   Författare :Alessio Russo; Alexandre Proutiere; Henrik Sandberg; Marcello Restelli; Nikolai Matni; Jana Tumova; Mikael Asplund; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; reinforcement learning; efficient exploration; bandit algorithms; adversarial attacks; conformal prediction; data posioning; markov decision processes; attack detectability; optimal control; adaptive control; Electrical Engineering; Elektro- och systemteknik; Datalogi; Computer Science; Mathematical Statistics; Matematisk statistik;

   Sammanfattning : In this thesis, we explore two distinct topics. The first part of the thesis delves into efficient exploration in  multi-task bandit models and model-free exploration in large Markov decision processes (MDPs). LÄS MER