Sökning: "machine learning"
Visar resultat 1 - 5 av 1564 uppsatser innehållade orden machine learning.
1. An approach to automate accident scenario generation using recurrent neural networks
Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : There is a need to improve the test procedure of Active Safety Systems through the automation of scenario generation, especially accident scenarios that are critical for testing. The purpose of this thesis is to provide an approach to automate the test generation process using machine learning. LÄS MER
2. City Safety Event Classification using Machine Learning
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : City safety technology aims to reduce vehicle collisions using activated warningsand braking based on automated detection of environmental threats. However, automaticdetection of tentative collisions may differ from driver perception, leadingto false positive activations. LÄS MER
3. Machine Learning for Suicide Risk Assessment on Depressed Patients
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Suicide is a global phenomena and the leading cause of death in some countriesand age groups, accounting for nearly 1 million deaths and 10 million attempts peryear. It costs society a substantial amount of money both directly and indirectly notto mention the tremendous amount of emotional distress and pain for families andfriends. LÄS MER
4. Department of Computer Science and Engineering UNIVERSITY OF GOTHENBURG CHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2018 Statistical Model Update Optimization in Industrial Practice
Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : This thesis presents a study done on optimizing machine learning model updates. The department of Quality and Functionality in a multinational telecommunication company is searching for an optimal solution to the problem of when, and how, to trigger a training cycle of a statistical model on their test execution dataset. LÄS MER
5. Elaborate Operational Requirements to Address Reward Hacking in Reinforcement Learning Agents
Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Autonomous agents, in recent times have been used to addressseveral problems, but these agents in their course of achievingtheir task also emit side effects to the environment in which theyoperate. Paramount of these side effects is reward hacking. Inthis report, we try to address reward hacking using elaborateoperational requirements. LÄS MER
