Sökning: "Learning over networks"

Visar resultat 1 - 5 av 136 avhandlingar innehållade orden Learning over networks.

1. 1. Generalization under Model Mismatch and Distributed Learning

   Författare :Martin Hellkvist; Ayca Özcelikkale; Anders Ahlén; Martin Jaggi; Uppsala universitet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Machine learning; Signal processing; Generalization error; Training error; Double-descent; Double descent; Distributed learning; Distributed optimization; Learning over networks; Model mismatch; Model misspecification; Fake features; Missing features; linear regression; regularization; Machine learning; Maskininlärning;

   Sammanfattning : Machine learning models are typically configured by minimizing the training error over a given training dataset. On the other hand, the main objective is to obtain models that can generalize, i.e., perform well on data unseen during training. LÄS MER

3. 2. Bayesian structure learning in graphical models

   Författare :Felix Leopoldo Rios; Tatjana Pavlenko; Klas Markström; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Bayesian statistics; graphical models; Bayesian networks; Markov networks; structure learning; Tillämpad matematik och beräkningsmatematik; Applied and Computational Mathematics;

   Sammanfattning : This thesis consists of two papers studying structure learning in probabilistic graphical models for both undirected graphs anddirected acyclic graphs (DAGs).Paper A, presents a novel family of graph theoretical algorithms, called the junction tree expanders, that incrementally construct junction trees for decomposable graphs. LÄS MER

4. 3. Learning to Control the Cloud

   Författare :Albin Heimerson; Institutionen för reglerteknik; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Cloud Computing; Reinforcement Learning; Learning-Based Control; Microservices; Datacenter; Autoscaling; Load Balancing; Neural Networks;

   Sammanfattning : With the growth of the cloud industry in recent years, the energy consumption of the underlying infrastructure is a major concern.The need for energy efficient resource management and control in the cloud becomes increasingly important as one part of the solution, where the other is to reduce the energy consumption of the hardware itself. LÄS MER

5. 4. Learning time-varying interaction networks

   Författare :Vinay Jethava; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; probabilistic graphical models; gene microarray expressions; dynamic interactome; time-varying interaction networks;

   Sammanfattning : Most biological systems consist of several subcomponents whichinteract with each other. These interactions govern the overall behaviourof the system; and in turn vary over time and in response to internaland external stress during the course of an experiment. LÄS MER

7. 5. Structured Representations for Explainable Deep Learning

   Författare :Federico Baldassarre; Hossein Azizpour; Josephine Sullivan; Kevin Smith; Hamed Pirsiavash; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Explainable AI; Deep Learning; Self-supervised Learning; Transformers; Graph Networks; Computer Vision; Explainable AI; Deep Learning; Self-supervised Learning; Transformers; Graph Networks; Computer Vision; Datalogi; Computer Science;

   Sammanfattning : Deep learning has revolutionized scientific research and is being used to take decisions in increasingly complex scenarios. With growing power comes a growing demand for transparency and interpretability. The field of Explainable AI aims to provide explanations for the predictions of AI systems. LÄS MER