Sökning: "Chaining"

Visar resultat 1 - 5 av 25 uppsatser innehållade ordet Chaining.

1. 1. “MAN DRUNKNAR I INFORMATION FAKTISKT, DET ÄR ETT JÄTTEPROBLEM”. En kvalitativ intervjustudie av hur forskare söker information i sitt forskningsarbete.

   Kandidat-uppsats, Göteborgs universitet/Institutionen för journalistik, medier och kommunikation

   Författare :Clara Tullgren; [2024-03-06]
   Nyckelord :Information; informationssökning; forskare; mkv-forskare; Ellis modell; användar- och användningsstudier; Norden; medie- och kommunikationsvetenskap;

   Sammanfattning : To search for information today is, by many, seen as an easy and uncomplicated task. All you need is a digital device and the knowledge of the world is there for you to find and use. LÄS MER

3. 2. Bridging Language & Data : Optimizing Text-to-SQL Generation in Large Language Models

   Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

   Författare :Niklas Wretblad; Fredrik Gordh Riseby; [2024]
   Nyckelord :Chaining; Classification; Data Quality; Few-Shot Learning; Large Language Model; Machine Learning; Noise; Prompt; Prompt Engineering; SQL; Structured Query Language; Text-to-SQL; Zero-Shot Learning; Noise Identification;

   Sammanfattning : This thesis explores text-to-SQL generation using Large Language Models within a financial context, aiming to assess the efficacy of current benchmarks and techniques. The central investigation revolves around the accuracy of the BIRD-Bench benchmark and the applicability of text-to-SQL models in real-world scenarios. LÄS MER

4. 3. Waste Analysis on a Production Line - A Case Study

   Master-uppsats, Lunds universitet/Industriell Produktion

   Författare :Sanna Treptow; Déspina Karida; [2023]
   Nyckelord :Sustainable manufacturing systems; Sustainable production; Lean production; Just in Time Production JiT ; Kanban; Waste; Environmental Value Stream Mapping EVSM ; Production Performance Matrix PPM ; Key Performance Index KPI ; Technology and Engineering;

   Sammanfattning : This study aims to assist Swedish company Clemondo AB in reducing waste in production, where the goal is to determine where waste appears as well as make suggestions for potential improvements, which are presented as Key Performance Indices (KPIs) and minimized manufacturing costs. Citation chaining is used to retrieve extant literature, while other productions and process-related information are gathered through observations and discussions. LÄS MER

5. 4. Using Backward Chained Behavior Trees to Control Cooperative Minecraft Agents

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

   Författare :Justin Salér; [2023]
   Nyckelord :Behavior-Based Systems; Multi-Agent Systems; Behavior Trees; Minecraft; Beteendebaserade system; multiagentssystem; beteendeträd; Minecraft;

   Sammanfattning : This report presents a strategy to control multiple collaborative intelligent agents acting in a complex, versatile environment. The proposed method utilizes back-chained behavior trees and 1-to-1 task distribution. The agents claim a task, which prevents other agents in the system to start working on the same task. LÄS MER

7. 5. Improving Behavior Trees that Use Reinforcement Learning with Control Barrier Functions : Modular, Learned, and Converging Control through Constraining a Learning Agent to Uphold Previously Achieved Sub Goals

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

   Författare :Jannik Wagner; [2023]
   Nyckelord :Behavior Trees; Reinforcement Learning; Control Barrier Functions; Robotics; Artificial Intelligence; Verhaltensbäume; Verstärkendes Lernen; Kontrollbarrierefunktionen; Robotik; Künstliche Intelligenz; Beteendeträd; Förstärkningsinlärning; Kontrollbarriärfunktioner; Robotik; Artificiell Intelligens;

   Sammanfattning : This thesis investigates combining learning action nodes in behavior trees with control barrier functions based on the extended active constraint conditions of the nodes and whether the approach improves the performance, in terms of training time and policy quality, compared to a purely learning-based approach. Behavior trees combine several behaviors, called action nodes, into one behavior by switching between them based on the current state. LÄS MER