Advanced search

Showing result 6 - 10 of 23 essays matching the above criteria.

  1. 6. Privacy leaks from deep linear networks : Information leak via shared gradients in federated learning systems

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Guangze Shi; [2022]
    Keywords : Federated learning; Gradient share; Deep neural network; Information leak; Privacy and security; Maskininlärning med flera noder; Gradientdelning; Djupt neuralt nätverk; Informationsläcka; Integritetssäkerhet;

    Abstract : The field of Artificial Intelligence (AI) has always faced two major challenges. The first is that data is kept scattered and cannot be collected for more efficiently use. The second is that data privacy and security need to be continuously strengthened. READ MORE

  3. 7. Comparing unsupervised clustering algorithms to locate uncommon user behavior in public travel data : A comparison between the K-Means and Gaussian Mixture Model algorithms

    University essay from Jönköping University/JTH, Datateknik och informatik

    Author : Anton Andrésen; Adam Håkansson; [2020]
    Keywords : Machine learning; clustering; K-Means; Gaussian Mixture Model; expectation-maximum; data analysis; public transport; silhouette analysis; outliers; outlier detection; data; algorithms; experiment;

    Abstract : Clustering machine learning algorithms have existed for a long time and there are a multitude of variations of them available to implement. Each of them has its advantages and disadvantages, which makes it challenging to select one for a particular problem and application. READ MORE

  4. 8. Vintergröna växter – ett komplement till våra lövfällande växter : en studie över de vintergrönas historia och hur de i framtiden kan ta plats i svenska moderna städer

    University essay from SLU/Dept. of Landscape Architecture, Planning and Management (from 130101)

    Author : Linnea Lindblad; [2019]
    Keywords : vintergrön; ståndort; växtmaterial; biologisk mångfald; hälsa; klimatförändring; urban; staden SLU; Sveriges;

    Abstract : Detta arbete syftar till att undersöka hur vintergrönt växtmaterial kan användas i urbana miljöer, som komplement till lövfällande växtmaterial. Arbetet tar upp vilka utmaningar växter ställs inför i hårdgjorda miljöer och vilka förutsättningar det vintergröna växtmaterialet har för att leva där. READ MORE

  5. 9. Superquadrics Augmented Rapidly-exploring Random Trees.

    University essay from KTH/Skolan för industriell teknik och management (ITM)

    Author : YARED EFREM AFEWORK; [2019]
    Keywords : Superquadrics; RRT; GJK; Collision Detection.; Superquadrics; RRT; GJK; Kollisionsdetektering.;

    Abstract : This thesis work investigated the advantages and disadvantages of using superquadrics (SQ) to do the collision-checking part of the Rapidly-exploring Random Trees (RRT) motion planning algorithm for higher Degree of Freedom (DoF) motion planning, comparing it with an established proximity querying method known as the Gilbert-Johnson-Keerthi (GJK) algorithm. In the RRT algorithm, collision detection is the main bottleneck, making this topic interesting to research. READ MORE

  6. 10. Radiation protection measurements in clinical practice - Dosimetry with NaCl pellets

    University essay from Lunds universitet/Sjukhusfysikerutbildningen

    Author : Petter Wilke; [2019]
    Keywords : Physics and Astronomy;

    Abstract : Within the field of medical radiation protection, radiation safety and personal dosimetry, there is a constant pursuit for improving existing methods and evaluating new approaches for measuring and quantifying the radiation doses that hospital staff may be exposed to in their clinical work. There are numerous ways of determining what doses the staff are being exposed to and the most commonly used is based on thermoluminescent dosemeters (TLD) with e. READ MORE