Sökning: "Heterogena Grafer"
Visar resultat 1 - 5 av 6 uppsatser innehållade orden Heterogena Grafer.
1. 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)Sammanfattning : Cyber attacks are ubiquitous and increasingly prevalent in industry, society, and governmental departments. They affect the economy, politics, and individuals. LÄS MER
2. Är gräset grönare på andra sidan?
Kandidat-uppsats, Lunds universitet/Företagsekonomiska institutionenSammanfattning : Syftet med arbetet är att undersöka prestationen hos private equity ägda företag efter försäljning i förhållande till innehavsperioden. Vidare avser arbetet att förklara och utforska variabler som påverkar utfallet. Teorierna som arbetet syftar till att använda är principal-agent teorin samt teorin om earnings management. LÄS MER
3. Effect of powder spray drying on catalyst formulation in tablet form
Master-uppsats, Lunds universitet/Kemiteknik (CI)Sammanfattning : Heterogenous catalysts consist of a large surface area support material applied with the catalytic active phase, and the activity of a catalyst is often correlated to the surface area per volume. Support materials often need to be processed further to be optimal for specific processes. LÄS MER
4. Artificial Neural Networks and Inductive Biases for Multi-Instance Multi-Modal Tabular Data : A Case Study for Default Probability Estimation in Small-to-Medium Enterprise Lending
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The success of artificial neural networks in homogeneous data domains such as images, textual data, and audio and other signals has had considerable impact on Machine Learning and science in general. The domain of heterogeneous tabular data, while arguably much more common, remains much less explored with regards to artificial neural networks and deep learning. LÄS MER
5. Real-time Anomaly Detection on Financial Data
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This work presents an investigation of tailoring Network Representation Learning (NRL) for an application in the Financial Industry. NRL approaches are data-driven models that learn how to encode graph structures into low-dimensional vector spaces, which can be further exploited by downstream Machine Learning applications. LÄS MER