Sökning: "Network Representation Learning"

Visar resultat 1 - 5 av 121 uppsatser innehållade orden Network Representation Learning.

1. 1. Planet-NeRF : Neural Radiance Fields for 3D Reconstruction on Satellite Imagery in Season Changing Environments

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Erica Ingerstad; Liv Kåreborn; [2024]
   Nyckelord :NeRF; Neural Radiance Field; Satellite Imagery; Machine Learning; Deep Learning;

   Sammanfattning : This thesis investigates the seasonal predictive capabilities of Neural Radiance Fields (NeRF) applied to satellite images. Focusing on the utilization of satellite data, the study explores how Sat-NeRF, a novel approach in computer vision, per- forms in predicting seasonal variations across different months. LÄS MER

3. 2. Detection of insurance fraud using NLP and ML

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Rasmus Bäcklund; Hampus Öhman; [2023]
   Nyckelord :Technology and Engineering;

   Sammanfattning : Machine-Learning can sometimes see things we as humans can not. In this thesis we evaluated three different Natural Language Procces-techniques: BERT, word2vec and linguistic analysis (UDPipe), on their performance in detecting insurance fraud based on transcribed audio from phone calls (referred to as audio data) and written text (referred to as text-form data), related to insurance claims. LÄS MER

4. 3. On Linear Mode Connectivity up to Permutation of Hidden Neurons in Neural Network : When does Weight Averaging work?

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

   Författare :Adhithyan Kalaivanan; [2023]
   Nyckelord :Mode Connectivity; Representation Learning; Loss Landscape; Network Symmetry; Lägesanslutning; representationsinlärning; förlustlandskap; nätverkssymmetri;

   Sammanfattning : Neural networks trained using gradient-based optimization methods exhibit a surprising phenomenon known as mode connectivity, where two independently trained network weights are not isolated low loss minima in the parameter space. Instead, they can be connected by simple curves along which the loss remains low. LÄS MER

5. 4. Football Trajectory Modeling Using Masked Autoencoders : Using Masked Autoencoder for Anomaly Detection and Correction for Football Trajectories

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

   Författare :Sandra Tor; [2023]
   Nyckelord :Machine Learning; Autoencoders; Masked autoencoders; Time series; Trajectory modeling; Time series modeling; Anomaly detection; Anomaly correction; Football; Maskininlärning; Autoencoders; Maskerade autoencoders; Tidsserie; Banmodellering; Tidsseriemodellering; Avvikelsedetektering; Avvikelsekorrigering; Fotboll;

   Sammanfattning : Football trajectory modeling is a powerful tool for predicting and evaluating the movement of a football and its dynamics. Masked autoencoders are scalable self-supervised learners used for representation learning of partially observable data. LÄS MER

7. 5. Cyber Threat Detection using Machine Learning on Graphs : Continuous-Time Temporal Graph Learning on Provenance Graphs

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

   Författare :Jakub Reha; [2023]
   Nyckelord :Graph neural networks; Temporal graphs; Benchmark datasets; Anomaly detection; Heterogeneous graphs; Provenance graphs; Grafiska neurala nätverk; temporala grafer; benchmark-datauppsättningar; anomalidetektering; heterogena grafer; härkomstgrafer;

   Sammanfattning : Cyber attacks are ubiquitous and increasingly prevalent in industry, society, and governmental departments. They affect the economy, politics, and individuals. LÄS MER