Sökning: "Class Balance"

Visar resultat 1 - 5 av 62 uppsatser innehållade orden Class Balance.

1. 1. Kodanonymisering vid integration med ChatGPT : Säkrare ChatGPT-användning med en kodanonymiseringsapplikation

   Kandidat-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

   Författare :Faruk Azizi; [2023]
   Nyckelord :Code anonymization; Data anonymization; ChatGPT; AI; Anonymization; information sanitization; privacy protection; Kodanonymisering; Dataanonymisering; ChatGPT; AI; Anonymisering; informationssanering; integritetsskydd;

   Sammanfattning : Denna avhandling studerar området av kodanonymisering inom programvaruutveckling, med fokus på att skydda känslig källkod i en alltmer digitaliserad och AI-integrerad värld. Huvudproblemen som avhandlingen adresserar är de tekniska och säkerhetsmässiga utmaningarna som uppstår när källkod behöver skyddas, samtidigt som den ska vara tillgänglig för AI-baserade analysverktyg som ChatGPT. LÄS MER

3. 2. Automated Extraction of Insurance Policy Information : Natural Language Processing techniques to automate the process of extracting information about the insurance coverage from unstructured insurance policy documents.

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Datalogi

   Författare :Jacob Hedberg; Erik Furberg; [2023]
   Nyckelord :NLP; SBERT; AI; Insurance; Semantic similarity;

   Sammanfattning : This thesis investigates Natural Language Processing (NLP) techniques to extract relevant information from long and unstructured insurance policy documents. The goal is to reduce the amount of time required by readers to understand the coverage within the documents. LÄS MER

4. 3. Neural Cleaning of Swedish Textual Data : Using BERT-based methods for Token Classification of Running and Non-Running Text

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

   Författare :Andreas Ericsson; [2023]
   Nyckelord :Natural Language Processing; Text Cleaning; Transformers; BERT; Token Classification; Deep Learning; Språkteknologi; Textrensning; Transformers; BERT; Token-klassificering; Djupinlärning;

   Sammanfattning : Modern natural language processing methods requires big textual datasets to function well. A common method is to scrape the internet to acquire the needed data. This does, however, come with the issue that some of the data may be unwanted – for instance, spam websites. LÄS MER

5. 4. Enhancing Neural Network Accuracy on Long-Tailed Datasets through Curriculum Learning and Data Sorting

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Daniel Barreira; [2023]
   Nyckelord :Machine Learning; Neural Network; CORAL-framework; Long-Tailed Data; Imbalance Metrics; Teacher-Student models; Curriculum Learning; Training Scheme; Maskininlärning; Neuralt Nätverk; CORAL-ramverk; Long-Tailed Data; Imbalance Metrics; Teacher-Student modeler; Curriculum Learning; Tränings- scheman;

   Sammanfattning : In this paper, a study is conducted to investigate the use of Curriculum Learning as an approach to address accuracy issues in a neural network caused by training on a Long-Tailed dataset. The thesis problem is presented by a Swedish e-commerce company. LÄS MER

7. 5. Data-Driven Traffic Forecasting for Completed Vehicle Simulation: : A Case Study with Volvo Test Trucks

   Magister-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Författare :Samaneh Shahrokhi; [2023]
   Nyckelord :supervised machine learning; traffic forecasting; vehicle presence prediction; binary classification; ensemble learning; feature engineering; hyperparameter tuning; data-driven analysis;

   Sammanfattning : This thesis offers a thorough investigation into the application of machine learning algorithms for predicting the presence of vehicles in a traffic setting. The research primarily focuses on enhancing vehicle simulation by employing data-driven traffic prediction methods. The study approaches the problem as a binary classification task. LÄS MER