Sökning: "Joel Oskarsson"

Hittade 2 uppsatser innehållade orden Joel Oskarsson.

1. 1. Probabilistic Regression using Conditional Generative Adversarial Networks

   Master-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Joel Oskarsson; [2020]
   Nyckelord :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;

   Sammanfattning : 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. LÄS MER

3. 2. Realtidsmultiplayerspel på IoT-backend

   Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

   Författare :Joel Almqvist; Björn Detterfelt; Tim Håkansson; David Kjellström; Axel Löjdquist; Joel Oskarsson; Lieth Wahid; Alexander Wilkens; [2018]
   Nyckelord :iot; internet of things; game; mobile; web; javascript; react; cybercom; sensors; online; multiplayer; internet; mobil; spel; flera spelare;

   Sammanfattning : This report presents a project carried out for the company Cybercom by eight students from Linköping University. The aim of the project has been to develop a real-time multiplayer game using an existing system for communication between different devices. The game has been developed as a web app that contains multiple game modes. LÄS MER