Sökning: "contrastive"
Visar resultat 21 - 25 av 165 uppsatser innehållade ordet contrastive.
21. Messing With The Gap: On The Modality Gap Phenomenon In Multimodal Contrastive Representation Learning
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Industriell teknikSammanfattning : 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
22. La proposition ou le syntagme ? : Une analyse structurelle de trois articles français et de leurs traductions suédoises
Magister-uppsats, Linnéuniversitetet/Institutionen för språk (SPR)Sammanfattning : The present study is based on a translation into Swedish of three French journalistic articles on energy sobriety. The study aims at comparing the source and the target texts, with regard to clause frequency and the use of various clause and phrase categories. LÄS MER
23. Negative Transfer from Arabic as a Major Reason for the Errors Made by Arabic Learners in their Written Production in English as a Second Language
Kandidat-uppsats, Södertörns högskola/EngelskaSammanfattning : The purpose of this research is to investigate the influence of negative transfer from Arabic as the most dominant influential factor among other possible factors that negatively affect Arabic learners resulting in them making errors in their written production in English as a second language. To perform this investigation, the author has collected and analysed 15 texts written by Arabic students enrolled in Grades 7, 8, and 9 of a lower secondary school. LÄS MER
24. Methods for data and user efficient annotation for multi-label topic classification
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Machine Learning models trained using supervised learning can achieve great results when a sufficient amount of labeled data is used. However, the annotation process is a costly and time-consuming task. There are many methods devised to make the annotation pipeline more user and data efficient. LÄS MER
25. Pre-classification of Hairy Cells Using Supervised Contrastive Learning
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : Differential of the peripheral blood is an important tool when assessing blood-related diseases. Lymphocytes are part of the immune system and morphological changes thereof should raise attention. LÄS MER