Search for dissertations about: "Incremental learning"

Showing result 16 - 20 of 53 swedish dissertations containing the words Incremental learning.

  2. 16. Study on Decentralized Machine Learning and Applications to Wireless Caching Networks

    Author : Yu Ye; Ming Xiao; Zhu Han; KTH; []
    Keywords : 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;

    Abstract : 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. READ MORE

  4. 17. On practical machine learning and data analysis

    Author : Daniel Gillblad; Anders Lansner; Finn Jensen; KTH; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Computer science; Datalogi;

    Abstract : This thesis discusses and addresses some of the difficulties associated with practical machine learning and data analysis. Introducing data driven meth- ods in e. g. industrial and business applications can lead to large gains in productivity and efficiency, but the cost and complexity are often overwhelm- ing. READ MORE

  5. 18. Deep learning based simulation for automotive software development

    Author : Dhasarathy Parthasarathy; Chalmers tekniska högskola; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; automotive software testing; latent space arithmetic; generative adversarial networks; explainable AI; sample selection bias;

    Abstract : The automotive industry is in the midst of a new reality where software is increasingly becoming the primary tool for delivering value to customers. While this has vastly improved their product offerings, vehicle manufacturers are increasingly facing the need to continuously develop, test, and deliver functionality, while maintaining high levels of quality. READ MORE

  6. 19. Learning reactive behaviors with constructive neural networks in mobile robotics

    Author : Jun Li; Tom Duckett; Tom Ziemke; Örebro universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Computer science; Datavetenskap; Datalogi; Computer and Systems Science;

    Abstract : This thesis investigates a learning system for acquiring robot behaviors by mapping sensor information directly to motor actions. It addresses the integration of three learning paradigms, namely unsupervised learning (UL), supervised learning (SL), and reinforcement learning (RL). READ MORE

  7. 20. Data management improvements in the electrical grid : a pathway to a smarter cyber-physical system

    Author : Sylvie Evelyne Koziel; Patrik Hilber; Ebrahim Shayesteh; Per Westerlund; Mathaios Panteli; KTH; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; asset management; data management; data analytics; distribution; grid operation and planning; machine learning; cyberinfrastructure upgrade; Electrical Engineering; Elektro- och systemteknik;

    Abstract : The current power system is a network of electrical components forming a physical system. It is experiencing changes, such as the deployment of electric vehicles and distributed energy sources. Meanwhile, cybernetworks are becoming coupled into the physical grid to an increasing degree. READ MORE