Sökning: "few-shot"

Visar resultat 16 - 20 av 29 uppsatser innehållade ordet few-shot.

1. 16. A Systematic Literature Review on Meta Learning for Predictive Maintenance in Industry 4.0

   Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

   Författare :Ahmet Fisenkci; [2022]
   Nyckelord :Meta-learning; Few-Shot; Predictive Maintenance; Industry 4.0; Fault detection; Fault Prognostics; Fault Diagnosis;

   Sammanfattning : Recent refinements in Industry 4.0 and Machine Learning demonstrate the positive effects of using deep learning models for intelligent maintenance. The primary benefit of Deep Learning (DL) is its capability to extract attributes and make fast, accurate, and automated predictions without supervision. LÄS MER

3. 17. Investigating Few-Shot Transfer Learning for Address Parsing : Fine-Tuning Multilingual Pre-Trained Language Models for Low-Resource Address Segmentation

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

   Författare :Hrafndís Heimisdóttir; [2022]
   Nyckelord :Address Parsing; Address Segmentation; Few-Shot Learning; Transfer Learning; Named Entity Recognition; Adressavkodning; Adress Segmentering; Inlärning med Få Exempel; Överföringsinlärning;

   Sammanfattning : Address parsing is the process of splitting an address string into its different address components, such as street name, street number, et cetera. Address parsing has been quite extensively researched and there exist some state-ofthe-art address parsing solutions, mostly unilingual. LÄS MER

4. 18. Evaluating Transcription of Ciphers with Few-Shot Learning

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Nikolina Milioni; [2022]
   Nyckelord :Ciphers; Automatic Transcription; Decrypt project; Few-shot learning;

   Sammanfattning : Ciphers are encrypted documents created to hide their content from those who were not the receivers of the message. Different types of symbols, such as zodiac signs, alchemical symbols, alphabet letters or digits are exploited to compose the encrypted text which needs to be decrypted to gain access to the content of the documents. LÄS MER

5. 19. Generating Terraform Configuration Files with Large Language Models

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

   Författare :Oskar Bonde; [2022]
   Nyckelord :Terraform; Transformer models; Generating configuration files; Large Language Models; Codex; Terraform; Transformer-modeller; Generera konfigurationsfiler; Stora språkmodeller; Codex;

   Sammanfattning : This thesis explores how large language models can be used to generate configuration files for Terraform from natural language descriptions. Few-shot and fine-tuning paradigms are evaluated on decoder-only models of varying size, including the state-of-the-art Codex model. LÄS MER

7. 20. Query By Example Keyword Spotting

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

   Författare :Jonas Sunde Valfridsson; [2021]
   Nyckelord :Keyword Spotting; Automatic Speech Recognition; ASR; Query By Example; Deep Distance Learning; Dynamic Time Warping; Few- Shot Learning; Nyckelords igenkänning; automatisk taligenkänning; fåförsöksinlärning;

   Sammanfattning : Voice user interfaces have been growing in popularity and with them an interest for open vocabulary keyword spotting. In this thesis we focus on one particular approach to open vocabulary keyword spotting, query by example keyword spotting. LÄS MER