Search for dissertations about: "learning with error"

Showing result 1 - 5 of 151 swedish dissertations containing the words learning with error.

2. 1. Adding Challenge to a Teachable Agent in a Virtual Learning Environment

   Author : Camilla Kirkegaard; Agneta Gulz; Annika Silvervarg; Björn Johansson; Lena Pareto; Linköpings universitet; []
   Keywords : SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; educational technology; educational software; teachable agents; learning;

   Abstract : The topic of this thesis concerns what happens when challenging behavior is added to a teachable agent in a virtual learning environment. The aim of adding challenging behavior to teachable agents is to encourage students to engage in learning behaviors, improve their motivation and engagement, which may result in a deeper level of comprehension and an improved learning experience. READ MORE

4. 2. Generalization under Model Mismatch and Distributed Learning

   Author : Martin Hellkvist; Ayca Özcelikkale; Anders Ahlén; Martin Jaggi; Uppsala universitet; []
   Keywords : 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;

   Abstract : 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. READ MORE

5. 3. Environmental Modelling : Learning from Uncertainty

   Author : John M. Juston; Per-Erik Jansson; Jens Christian Refsgaard; KTH; []
   Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Models; data; error; uncertainty; hydrology; soil carbon; wetlands; phosphorus;

   Abstract : Environmental models are important tools; however uncertainty is pervasive in the modeling process.   Current research has shown that under­standing and representing these uncertainties is critical when decisions are expected to be made from the modeling results. READ MORE

6. 4. Machine Learning for Wireless Link Adaptation : Supervised and Reinforcement Learning Theory and Algorithms

   Author : Vidit Saxena; Joakim Jaldén; Mats Bengtsson; Hugo Tullberg; Jakob Hoydis; KTH; []
   Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Wireless Communications; Reinforcement Learning; Multi-Armed Bandits; Thompson Sampling; Convex Optimization; Deep Learning; Electrical Engineering; Elektro- och systemteknik;

   Abstract : Wireless data communication is a complex phenomenon. Wireless links encounter random, time-varying, channel effects that are challenging to predict and compensate. Hence, to optimally utilize the channel, wireless links adapt the data transmission parameters in real time. READ MORE

7. 5. Facing the Illusion Piece by Piece : Face Recognition for Persons with Learning Disability

   Author : Henrik Danielsson; Jerker Rönnberg; Jan Andersson; Erland Hjelmquist; Linköpings universitet; []
   Keywords : SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Face recognition; Memory conjunction error; Binding; Working memory; Learning disability; Witness psychology; Ansiktsigenkänning; Falska minnen; Bindning; Arbetsminne; Utvecklingsstörning; Vittnespsykologi; Disability research; Handikappsforskning;

   Abstract : Avhandlingens övergripande syfte var att undersöka ansiktsigenkänning för personer med och utan utvecklingsstörning. Tre specifika forskningsfrågor undersöktes:1. Hur ser interaktionen ut mellan familjaritet med ansikten och familjaritet med miljöer när det gäller bildigenkänning för personer med utvecklingsstörning?2. READ MORE