Essays about: "Variational Autoencoder"

Showing result 1 - 5 of 19 essays containing the words Variational Autoencoder.

  1. 1. Simultaneous Classification of Sets of Images Using Deep Learning and Clustering

    University essay from Lunds universitet/Matematik LTH

    Author : Nellie Carleke; Hugo Sellerberg; [2020]
    Keywords : Mathematics and Statistics;

    Abstract : Classification of cell images is conventionally done manually in hematology laboratories by medical technologists. CellaVision aims to automate this work in order to make the analysis process faster, better and more flexible. READ MORE

  2. 2. Deep Scenario Generation of Financial Markets

    University essay from KTH/Matematisk statistik; KTH/Matematisk statistik

    Author : Filip Carlsson; Philip Lindgren; [2020]
    Keywords : Variational Autoencoder; Generative Models; Latent Space; Dimensionality Reduction; Unsupervised Learning; Clustering; VAE-Clustering; Scenario Generation; Market Regime; Variational Autoencoder; generativa modeller; latent rum; dimensionsreducering; klustring; scenario generering;

    Abstract : The goal of this thesis is to explore a new clustering algorithm, VAE-Clustering, and examine if it can be applied to find differences in the distribution of stock returns and augment the distribution of a current portfolio of stocks and see how it performs in different market conditions. The VAE-clustering method is as mentioned a newly introduced method and not widely tested, especially not on time series. READ MORE

  3. 3. Adaptive Reference Images for Blood Cells using Variational Autoencoders and Self-Organizing Maps

    University essay from Lunds universitet/Matematik LTH

    Author : Oscar Odestål; Anna Palmqvist Sjövall; [2020]
    Keywords : Image Analysis; Variational Autoencoder; Self-Organizing Maps; Deep Learning; Machine Learning; Microscopy; CellaVision; Microscope; Neural Networks; Blood Cells; White Blood Cells; Image Classification; Data Visualization; Clustering; Latent Space; Unsupervised Learning; Dimensionality Reduction; SOM; VAE; Mathematics and Statistics;

    Abstract : CellaVision develops automated microscopy for blood analysis. Their products can pre-classify 19 different types of white blood cells and support the medical technologist performing the final classification. CellaVision provides reference cells. READ MORE

  4. 4. Handling Imbalanced Data Classification With Variational Autoencoding And Random Under-Sampling Boosting

    University essay from Uppsala universitet/Statistiska institutionen

    Author : Jesper Ludvigsen; [2020]
    Keywords : Imbalanced classification data; Variational Autoencoder; Random Under-Sampling Boosting; Credit Card Fraud; Fraud; Mammography;

    Abstract : In this thesis, a comparison of three different pre-processing methods for imbalanced classification data, is conducted. Variational Autoencoder, Random Under-Sampling Boosting and a hybrid approach of the two, are applied to three imbalanced classification data sets with different class imbalances. READ MORE

  5. 5. Hierarchical Clustering of Time Series using Gaussian Mixture Models and Variational Autoencoders

    University essay from Lunds universitet/Matematisk statistik

    Author : Per Wilhelmsson; [2019]
    Keywords : Clustering; Deep Learning; Machine Learning; Time Series; Variational Autoencoders; Gaussian Mixture Models; Mathematics and Statistics;

    Abstract : This thesis proposes a hierarchical clustering algorithm for time series, comprised of a variational autoencoder to compress the series and a Gaussian mixture model to merge them into an appropriate cluster hierarchy. This approach is motivated by the autoencoders good results in dimensionality reduction tasks and by the likelihood framework given by the Gaussian mixture model. READ MORE