Sökning: "Förlustfunktion"

Visar resultat 1 - 5 av 11 uppsatser innehållade ordet Förlustfunktion.

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

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

    Författare :Leonidas Valavanis; [2020]
    Nyckelord :;

    Sammanfattning : 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. LÄS MER

  2. 2. Cardinality estimation with a machine learning approach

    Master-uppsats, KTH/Optimeringslära och systemteori

    Författare :Olle Falgén Enqvist; [2020]
    Nyckelord :Machine learning; databases; regression models; SQL; Maskininlärning; databaser; regressionsmodeller;

    Sammanfattning : This thesis investigates how three different machine learning models perform on cardinalty estimation for sql queries. All three models were evaluated on three different data sets. The models were tested on both estimating cardinalities when the query just takes information from one table and also a two way join case. LÄS MER

  3. 3. Enforcing low confidence class predictions for out of distribution data in deep convolutional networks

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

    Författare :Luca Marson; [2020]
    Nyckelord :;

    Sammanfattning : Modern discriminative deep neural networks are known to perform high confident predictions for inputs far away from the training data distribution, commonly referred to as out-of-distribution inputs. This property poses security concerns for the deployment of deep learning models in critical applications like autonomous vehicles because it hinders the detection of such inputs. LÄS MER

  4. 4. A Label-based Conditional Mutual Information Estimator using Contrastive Loss Functions

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

    Författare :Ziwei Ye; [2020]
    Nyckelord :;

    Sammanfattning : In the field of machine learning, representation learning is a collection of techniques that transform raw data into a technology that can be effectively developed by machine learning. In recent years, deep neural network-based representation learning technology has been widely used in image learning, recognition, classification and other fields, and one of the representative ones is the mutual information estimator/encoder. LÄS MER

  5. 5. A Segmentation Network with a Class-Agnostic Loss Function for Training on Incomplete Data

    Master-uppsats, KTH/Medicinteknik och hälsosystem

    Författare :Gabriella Norman; [2020]
    Nyckelord :Deep Learning; Segmentation; Medical image processing; Class-agnostic loss function;

    Sammanfattning : The use of deep learning methods is increasing in medical image analysis, e.g., segmentation of organs in medical images. Deep learning methods are highly dependent on a large amount of training data, a common obstacle for medical image analysis. LÄS MER