Sökning: "embedding models"

Visar resultat 11 - 15 av 106 uppsatser innehållade orden embedding models.

1. 11. Classifying personal data on contextual information

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

   Författare :Carl Dath; [2023]
   Nyckelord :Natural Language Processing; Machine Learning; Word2Vec; GloVe; BERT; Personal Data classification; Språkteknologi; Maskininlärning; Personlig Data Klassificering;

   Sammanfattning : In this thesis, a novel approach to classifying personal data is tested. Previous personal data classification models read the personal data before classifying it. However, this thesis instead investigates an approach to classify personal data by looking at contextual information frequently available in data sets. LÄS MER

3. 12. Imitation Learning on Branching Strategies for Branch and Bound Problems

   Master-uppsats, KTH/Matematisk statistik

   Författare :Magnus Axén; [2023]
   Nyckelord :Graph Networks; Convolutions; MIP; Branch and Bound; Facility Location Problem; MDP; Imitation Learning; Graf nätverk; Faltning; Blandade heltaltsproblem; Branch and Bound; Facility Location Problem; Markov; Imitationsinlärning;

   Sammanfattning : A new branch of machine and deep learning models has evolved in constrained optimization, specifically in mixed integer programming problems (MIP). These models draw inspiration from earlier solver methods, primarily the heuristic, branch and bound. LÄS MER

4. 13. Self-Supervised Fine-Tuning of sentence embedding models using a Smooth Inverse Frequency model : Automatic creation of labels with Smooth Inverse Frequency model

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

   Författare :Vittorio Pellegrini; [2023]
   Nyckelord :Natural Language Processing; sentence embeddings; Transformer-based architectures; sentence paraphrasing; sentence similarity; sentence clustering; Naturlig språkbehandling; inbäddning av meningar; transformatorbaserade arkitekturer; parafrasering av meningar; meningslikhet; klustring av meningar Canvas Lärplattform; Dockerbehållare; Prestandajustering;

   Sammanfattning : Sentence embedding models play a key role in the field of Natural Language Processing. They can be exploited for the resolution of several tasks like sentence paraphrasing, sentence similarity, and sentence clustering. LÄS MER

5. 14. Messing With The Gap: On The Modality Gap Phenomenon In Multimodal Contrastive Representation Learning

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Industriell teknik

   Författare :Mohammad Al-Jaff; [2023]
   Nyckelord :Multimodal machine learning; Representation learning; Self-supervised learning; contrastive learning; computer vision; computational biology; bioinformatics;

   Sammanfattning : In machine learning, a sub-field of computer science, a two-tower architecture model is a specialised type of neural network model that encodes paired data from different modalities (like text and images, sound and video, or proteomics and gene expression profiles) into a shared latent representation space. However, when training these models using a specific contrastive loss function, known as the multimodalinfoNCE loss, seems to often lead to a unique geometric phenomenon known as the modality gap. LÄS MER

7. 15. Attention based Knowledge Tracing in a language learning setting

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

   Författare :Sebastiaan Vergunst; [2022]
   Nyckelord :Knowledge Tracing; Exercise Recommendation; Personalised Learning; Recurrent Neural Network; Attention; Self-Attention; Exercise Embedding; Kunskapsspårning; Övningsrekommendation; Personligt Anpassad Inlärning; Rekurrenta Neurala Nätverk; Uppmärksamhet; Självuppmärksamhet; Övningsembedding;

   Sammanfattning : Knowledge Tracing aims to predict future performance of users of learning platforms based on historical data, by modeling their knowledge state. In this task, the target is a binary variable representing the correctness of the exercise, where an exercise is a word uttered by the user. LÄS MER