Search for dissertations about: "learning technique"
Showing result 1 - 5 of 181 swedish dissertations containing the words learning technique.
-
1. Bridging the boundaries between D&T education and working life : A study of views on knowledge and skills in product development
Abstract : In Sweden upper secondary school education is organised in programmes. One of these programmes is the Technology programme that covers five orientations, one of which is Design and Product Development. READ MORE
-
2. On Deep Machine Learning Based Techniques for Electric Power Systems
Abstract : This thesis provides deep machine learning-based solutions to real-time mitigation of power quality disturbances such as flicker, voltage dips, frequency deviations, harmonics, and interharmonics using active power filters (APF). In an APF the processing delays reduce the performance when the disturbance to be mitigated is tima varying. READ MORE
-
3. Reliable and Efficient Distributed Machine Learning
Abstract : With the ever-increasing penetration and proliferation of various smart Internet of Things (IoT) applications, machine learning (ML) is envisioned to be a key technique for big-data-driven modelling and analysis. Since massive data generated from these IoT devices are commonly collected and stored in a distributed manner, ML at the networks, e.g. READ MORE
-
4. Balancing structure and flexibility in the ambulance service : the pursuit of professional judgement in caring and learning
Abstract : The overall aim of this thesis was to describe the conditions for learning inthe ambulance service during clinical practice, and to develop an understanding of how to support the professional development of caring in this context.The findings of this thesis are based on four qualitative interview studies. READ MORE
-
5. Information-Theoretic Generalization Bounds: Tightness and Expressiveness
Abstract : Machine learning has achieved impressive feats in numerous domains, largely driven by the emergence of deep neural networks. Due to the high complexity of these models, classical bounds on the generalization error---that is, the difference between training and test performance---fail to explain this success. READ MORE