Sökning: "Variational Auto-Encoder"
Visar resultat 1 - 5 av 11 uppsatser innehållade orden Variational Auto-Encoder.
1. Towards topology-aware Variational Auto-Encoders : from InvMap-VAE to Witness Simplicial VAE
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Variational Auto-Encoders (VAEs) are one of the most famous deep generative models. After showing that standard VAEs may not preserve the topology, that is the shape of the data, between the input and the latent space, we tried to modify them so that the topology is preserved. LÄS MER
2. 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
3. Cooperative security log analysis using machine learning : Analyzing different approaches to log featurization and classification
Master-uppsats, Linköpings universitet/Databas och informationsteknikSammanfattning : This thesis evaluates the performance of different machine learning approaches to log classification based on a dataset derived from simulating intrusive behavior towards an enterprise web application. The first experiment consists of performing attacks towards the web app in correlation with the logs to create a labeled dataset. LÄS MER
4. A Machine Learning Approach for Comprehending Cosmic Expansion
Master-uppsats, KTH/FysikSammanfattning : This thesis aims at using novel machine learning techniques to test the dynamics of the Universe via the cosmological redshift-distance test. Currently, one of the most outstanding questions in cosmology is the physical cause of the accelerating cosmic expansion observed with supernovae. LÄS MER
5. Learning representations of features of fish for performing regression tasks
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In the ever-changing landscape of the fishing industry, demands for automating specific processes are increasing substantially. Predicting future events eliminates much of the existing communication latency between fishing vessels and their customers and makes real-time analysis of onboard catch possible for the fishing industry. LÄS MER