Essays about: "maximum mean discrepancy"

Found 5 essays containing the words maximum mean discrepancy.

  1. 1. Improving Image Classification using Domain Adaptation for Autonomous Driving : A Master Thesis in Collaboration with Scania

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

    Author : Mikael Westlund; [2023]
    Keywords : Autonomous driving; Deep Learning; Domain Adaptation; Image classification; LiDAR; Transfer Learning; Självkörande fordon; Djupinlärning; Domain Adaptation; Bildklassificering; LiDAR; Överföringsinlärning;

    Abstract : Autonomous driving is a rapidly changing industry and has recently become a heavily focused research topic for vehicle producing companies and research organizations. These autonomous vehicles are typically equipped with sensors such as Light Detection and Radar (LiDAR) in order to perceive their surroundings. READ MORE

  3. 2. Probabilistic Regression using Conditional Generative Adversarial Networks

    University essay from Linköpings universitet/Statistik och maskininlärning

    Author : Joel Oskarsson; [2020]
    Keywords : machine learning; ml; regression; probabilistic; distribution; cgan; gan; conditional gan; adversarial networks; neural network; deep learning; f-gan; f-cgan; f-divergence; adversarial training; bimodal; heteroskedastic; mmd; maximum mean discrepancy; gmmn; generative moment matching network; conditional gmmn; ipm; kde; cgan evaluation; cgan regression; gan regression; cgan-regression; regression using gan; deep; nn; implicit; generative; conditional; model; complex noise; aleatoric; uncertainty; dctd; mdn; heteroskedastic regression; gp;

    Abstract : Regression is a central problem in statistics and machine learning with applications everywhere in science and technology. In probabilistic regression the relationship between a set of features and a real-valued target variable is modelled as a conditional probability distribution. READ MORE

  4. 3. Learning from noisy labelsby importance reweighting: : a deep learning approach

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

    Author : Tongtong Fang; [2019]
    Keywords : noisy label; importance reweighting; deep learning; domain adaptation; annoterad data; omviktning; djupt lärande; domänanpassning;

    Abstract : Noisy labels could cause severe degradation to the classification performance. Especially for deep neural networks, noisy labels can be memorized and lead to poor generalization. READ MORE

  5. 4. Effects of Wildfire Burn on Permafrost Landcover and Catchment Hydrology in Manitoba, Canada

    University essay from Uppsala universitet/Institutionen för geovetenskaper

    Author : Andreas Andersson; [2019]
    Keywords : wildfire; permafrost; catchment hydrology;

    Abstract : Permafrost is a strongly controlling factor on Arctic hydrology due to its effect on ground permeability, and thus surface and ground water flow paths. As wildfires are increasing in occurrence and magnitude in permafrost regions, they may alter the hydrological regime via permafrost thaw and degradation that increases ground permeability. READ MORE

  6. 5. Application of the eddy-covariance method under the canopy at a boreal forest site in central Sweden

    University essay from Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskap

    Author : Vlad Pirvulescu; [2013]
    Keywords : closed-path system; open-path system; soil chambers; latent heat flux; carbon dioxide flux; sensible heat flux; Physical Geography and Ecosystem Analysis; eddy-covariance; Norunda; Earth and Environmental Sciences;

    Abstract : The eddy-covariance (EC) method was applied at 1.5 m height, for the period 2007-2010 at Norunda, central Sweden, for calculating energy (sensible and latent heat) and carbon dioxide (CO2) fluxes. The aim of this study was to assess the applicability of EC method above the forest floor. READ MORE