Sökning: "deterministic methods"

Visar resultat 16 - 20 av 106 uppsatser innehållade orden deterministic methods.

1. 16. Finding duplicate offers in the online marketplace catalogue using transformer based methods : An exploration of transformer based methods for the task of entity resolution

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

   Författare :Robert-Andrei Damian; [2022]
   Nyckelord :Transformers; Language Models; Deep Neural Networks; Entity Resolution; Duplicate Detection; Entity Matching; Record Linkage; Contrastive Learning; e-commerce; Transformers; Modèles de langage; Apprentisage en profondeur; Résolution d’entité; Détection de doublons; Apprentisage contrastif; commerce électronique; Transformers; Språkmodeller; Djupinlärning; Entitetserkännande; Dubblettdetektering; Entitetsmatchning; Rekordkoppling; e-handel;

   Sammanfattning : The amount of data available on the web is constantly growing, and e-commerce websites are no exception. Considering the abundance of available information, finding offers for the same product in the catalogue of different retailers represents a challenge. This problem is an interesting one and addresses the needs of multiple actors. LÄS MER

3. 17. Evaluation of Models and Optimisation Methods for Energy Minimisation of Drill Riggs

   Master-uppsats, Linköpings universitet/Fordonssystem

   Författare :Mohamed Faraj; Max Olsson; [2022]
   Nyckelord :Vehicle Propulsion Systems; Electrical powertrain; Modeling; Simulation; Deterministic dynamic programming; AMESim;

   Sammanfattning : There are many benefits from using electrical powertrains over diesel powertrains within the mining industries, where some of these benefits come from reducing the pollution within the mines and therefore improve the working environment as well as reduce the ventilation costs required from ventilating these pollution. It is also desired to optimise the use of the vehicle to increase the efficiency and reduce fuel consumption of the vehicle. LÄS MER

4. 18. KL/TV Reshuffling : Statistical Distance Based Offspring Selection in SMC Methods

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

   Författare :Oskar Kviman; [2022]
   Nyckelord :;

   Sammanfattning : Over the years sequential Monte Carlo (SMC), and, equivalently, particle filter (PF) theory has enjoyed much attention from researchers. However, the intensity of developing innovative resampling methods, also known as offspring selection methods, has long been declining, with most of the popular schemes aging back two decades. LÄS MER

5. 19. Spiking Reinforcement Learning for Robust Robot Control Under Varying Operating Conditions

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

   Författare :Philipp Mondorf; [2022]
   Nyckelord :;

   Sammanfattning : Over the last few years, deep reinforcement learning (RL) has gained increasing popularity for its successful application to a variety of complex control and decision-making tasks. As the demand for deep RL algorithms deployed in challenging real-world environments grows, their robustness towards uncertainty, disturbances and perturbations of the environment becomes more and more important. LÄS MER

7. 20. Deep Reinforcement Learning for Dynamic Grasping

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

   Författare :Andreas Ström; [2022]
   Nyckelord :Deep Reinforcement Learning; Dynamic Grasping; DDPG; HER; Robotics;

   Sammanfattning : Dynamic grasping is the action of, using only contact force, manipulating the position of a moving object in space. Doing so with a robot is a quite complex task in itself, but is one with wide-ranging applications. LÄS MER