Sökning: "Contrastive Loss"
Visar resultat 1 - 5 av 11 uppsatser innehållade orden Contrastive Loss.
1. Information Extraction for Test Identification in Repair Reports in the Automotive Domain
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : The knowledge of tests conducted on a problematic vehicle is essential for enhancing the efficiency of mechanics. Therefore, identifying the tests performed in each repair case is of utmost importance. This thesis explores techniques for extracting data from unstructured repair reports to identify component tests. LÄS MER
2. Hanif Kureishi’s The Buddha of Suburbia : The Production of Subjectivity and Commodification
Kandidat-uppsats, Södertörns högskola/EngelskaSammanfattning : This essay aims to analyze the main characters of Hanif Kureishi’s The Buddha of Suburbia. The main characters embark on a metaphorical journey against a backdrop of turbulent socio-political changes in 1970s Britain, ending with the emergence of neoliberalism and the rise of Margaret Thatcher. LÄS MER
3. 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
4. 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
5. Attribute Embedding for Variational Auto-Encoders : Regularization derived from triplet loss
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Techniques for imposing a structure on the latent space of neural networks have seen much development in recent years. Clustering techniques used for classification have been used to great success, and with this work we hope to bridge the gap between contrastive losses and Generative models. LÄS MER