Sökning: "Random projections"

Hittade 5 uppsatser innehållade orden Random projections.

  1. 1. Validation of basal area growth functions for larch in Heureka DSS

    Master-uppsats, SLU/Southern Swedish Forest Research Centre

    Författare :Sebastian Carlzon; [2022]
    Nyckelord :validation; Heureka; Larix; Larix sibirica; Larix sukaczewii; Larix decidua; Larix x eurolepis; Siberian larch; European larch; hybrid larch; growth model validation; Heureka DSS; basal area growth;

    Sammanfattning : Larch is getting more common in Sweden. This highlights the need of reliable growth models for larch species in Heureka DSS. Precise and accurate growth models are essential for long-term forest planning. LÄS MER

  3. 2. Random projections in a distributed environment for privacy-preserved deep learning

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Malcolm Bagger Toräng; [2021]
    Nyckelord :Random projections; Generative adversarial networks; Privacy metrics; Deep learning; Obfuscation.; Slumpmässiga projektioner; Generativa kontroversiella nätverk; Privatiserings-mått; Djupinlärning; Obfuskering.;

    Sammanfattning : The field of Deep Learning (DL) only over the last decade has proven useful for increasingly more complex Machine Learning tasks and data, a notable milestone being generative models achieving facial synthesis indistinguishable from real faces. With the increased complexity in DL architecture and training data, follows a steep increase in time and hardware resources required for the training task. LÄS MER

  4. 3. Weighing Machine Learning Algorithms for Accounting RWISs Characteristics in METRo : A comparison of Random Forest, Deep Learning & kNN

    Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

    Författare :Jesper Landmér Pedersen; [2019]
    Nyckelord :machine learning; neural network; random forest; k-nearest neighbour; model of the environment and temperature of roads;

    Sammanfattning : The numerical model to forecast road conditions, Model of the Environment and Temperature of Roads (METRo), laid the foundation of solving the energy balance and calculating the temperature evolution of roads. METRo does this by providing a numerical modelling system making use of Road Weather Information Stations (RWIS) and meteorological projections. LÄS MER

  5. 4. Image analysis to estimate the fractal dimension of soot aggregates

    Master-uppsats, Lunds universitet/Förbränningsfysik; Lunds universitet/Fysiska institutionen

    Författare :Adrian Roth; [2018]
    Nyckelord :soot; aggregates; fractal; dimension; image; analysis; Technology and Engineering;

    Sammanfattning : Examensarbetet har utvecklat en metod för att estimera den fraktala dimensionen från Transmissions Elektron Mikroskop (TEM) bilder av sot aggregat som skapats med hjälp av en mini-CAST sotgenerator. Det är ett underbestämt problem att estimera den fraktala dimensionen, en 3D egenskap, från 2D bilder. LÄS MER

  7. 5. Predicting Internal Migration on Individual level in Sweden Using Micro Data : A Performance Comparison of Logistic Regression and Neural Networks

    Magister-uppsats, Umeå universitet/Nationalekonomi

    Författare :Anders Lindström; [2017]
    Nyckelord :Neural networks; Logistic regression; Prediction; Machine Learning; Migration; Performance Comparison.;

    Sammanfattning : To know in advance who, how many, and to what destination people will migrate is importantto provide robust population projections. As migration prediction model comparisons inthe literature are limited, this study compares the predictive performance of Logistic regressionand Neural networks. LÄS MER