Avancerad sökning

Hittade 3 uppsatser som matchar ovanstående sökkriterier.

1. 1. Recommending digital books to children : Acomparative study of different state-of-the-art recommendation system techniques

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

   Författare :Malvin Lundqvist; [2023]
   Nyckelord :Recommendation Systems; Collaborative Filtering; Matrix Factorization; Multi-Layer Perceptron; Neural Network-based Collaborative Filtering; Implicit Feedback; Deep Learning; Term Frequency-Inverse Document Frequency; Rekommendationssystem; Kollaborativ filtrering; Matrisfaktorisering; Flerlagersperceptron; Neurala nätverksbaserad kollaborativ filtrering; Implicit data; Djupinlärning; Termfrekvens med omvänd dokumentfrekvens;

   Sammanfattning : Collaborative filtering is a popular technique to use behavior data in the form of user’s interactions with, or ratings of, items in a system to provide personalized recommendations of items to the user. This study compares three different state-of-the-art Recommendation System models that implement this technique, Matrix Factorization, Multi-layer Perceptron and Neural Matrix Factorization, using behavior data from a digital book platform for children. LÄS MER

3. 2. Duplicate detection of multimodal and domain-specific trouble reports when having few samples : An evaluation of models using natural language processing, machine learning, and Siamese networks pre-trained on automatically labeled data

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

   Författare :Viktor Karlstrand; [2022]
   Nyckelord :Duplicate detection; Bug reports; Trouble reports; Natural language processing; Information retrieval; Machine learning; Siamese neural network; Transformers; Automated data labeling; Shapley values; Dubblettdetektering; Felrapporter; Buggrapporter; Naturlig språkbehandling; Informationssökning; Maskininlärning; Siamesiska neurala nätverk; Transformatorer; Automatiserad datamärkning; Shapley-värden;

   Sammanfattning : Trouble and bug reports are essential in software maintenance and for identifying faults—a challenging and time-consuming task. In cases when the fault and reports are similar or identical to previous and already resolved ones, the effort can be reduced significantly making the prospect of automatically detecting duplicates very compelling. LÄS MER

4. 3. SOU, bibliotek och läsfrämjande : En jämförande kvantitativ och kvalitativ undersökning av fyra SOU-dokument från 1974, 1984, 1997 och 2012

   Kandidat-uppsats, Högskolan i Borås/Akademin för bibliotek, information, pedagogik och IT

   Författare :Oskar Larsson; Johan Sjöberg; [2016]
   Nyckelord :SOU; Läsfrämjande; Bibliotek; Kvalitativ innehållsanalys; Kvantitativ innehållsanalys; Blandad metod; Termfrekvens;

   Sammanfattning : The aim of this study is try to map the view of libraries and promote reading in four SOU-documents (Statens Offentliga Utredningar/state public invesigations) from the years 1974, 1984, 1997 and 2012. Different approaches used to promote reading during the years are also investigated. LÄS MER