Essays about: "Autokodare"

Showing result 1 - 5 of 9 essays containing the word Autokodare.

  1. 1. Outlier detection with ensembled LSTM auto-encoders on PCA transformed financial data

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Love Stark; [2021]
    Keywords : Long Short-Term Memory Recurrent Neural Networks LSTM ; Ensemble learning; Auto-Encoder; anomaly detection; financial data; deep learning; Principal Component Analysis PCA ; Long Short-Term Memory Recurrent Neural Networks LSTM ; Ensemble lärande; Auto-Encoder; avvikelse detektering; finansiell data; djupinlärning; Principal Component Analysis PCA ;

    Abstract : Financial institutions today generate a large amount of data, data that can contain interesting information to investigate to further the economic growth of said institution. There exists an interest in analyzing these points of information, especially if they are anomalous from the normal day-to-day work. READ MORE

  2. 2. Overcoming generative likelihood bias for voxel-based out-of-distribution detection

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Einar Lennelöv; [2021]
    Keywords : Variational autoencoder; out-of-distribution detection; likelihood bias; voxel representation; radiation therapy; Variationell autokodare; anomalidetektion; sannolikhetssnedvridning; voxelrepresentation; strålbehandling;

    Abstract : Deep learning-based dose prediction is a promising approach to automated radiotherapy planning but carries with it the risk of failing silently when the inputs are highly abnormal compared to the training data. One way to address this issue is to develop a dedicated outlier detector capable of detecting anomalous patient geometries. READ MORE

  3. 3. Analysis of Eye Tracking Data from Parkinson’s Patients using Machine Learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Lucas Höglund; [2021]
    Keywords : Autoencoder; Clustering; Eye tracking; Feature extraction; Feature selection; Machine learning; Parkinson’s disease.; Autokodare; Klustring; Blickspårning; Särdragsextraktion; Särdragsidentifikation; Maskininlärning; Parkinsons sjukdom.;

    Abstract : Parkinson’s disease is a brain disorder associated with reduced dopamine levels in the brain, affecting cognition and motor control in the human brain. One of the motor controls that can be affected is eye movements and can therefore be critically affected in patients with Parkinson’s disease. READ MORE

  4. 4. Deep Convolutional Nonnegative Autoencoders

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Yann Debain; [2020]
    Keywords : ;

    Abstract : In this thesis, nonnegative matrix factorization (NMF) is viewed as a feedbackward neural network and generalized to a deep convolutional architecture with forwardpropagation under β-divergence. NMF and feedfoward neural networks are put in relation and a new class of autoencoders is proposed, namely the nonnegative autoencoders. READ MORE

  5. 5. Robust Descriptor Learning Using Variational Auto-Encoders

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Leonidas Valavanis; [2020]
    Keywords : ;

    Abstract : Image matching is the task of finding points in one image corresponding to the same points in the other image. Classical feature descriptors fail to match points when the images are under extreme viewpoint or seasonal changes. This thesis tackles the problem of image matching when two images are under severe changes. READ MORE