Essays about: "Bildklassificering"

Showing result 1 - 5 of 20 essays containing the word Bildklassificering.

  1. 1. DevOps for Data Science System

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

    Author : Zhongjian Zhang; [2020]
    Keywords : Data science; DevOps; convolutional neural network; transfer learning;

    Abstract : Commercialization potential is important to data science. Whether the problems encountered by data science in production can be solved determines the success or failure of the commercialization of data science. Recent research shows that DevOps theory is a great approach to solve the problems that software engineering encounters in production. READ MORE

  2. 2. Enhancing Deep Active Learning Using Selective Self-Training For Image Classification

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

    Author : Emmeleia Panagiota Mastoropoulou; [2019]
    Keywords : Semi-supervised learning; Active learning; Image classification; Deep learning; Transfer learning; Uncertainty sampling; Forgetting Event; Semi-övervakad inlärning; Aktivt lärande; Bildklassificering; Djup lärning; Överför lärande; Osäkerhet provtagning; Glömmer händelse;

    Abstract : A high quality and large scale training data-set is an important guarantee to teach an ideal classifier for image classification. Manually constructing a training data- set  with  appropriate  labels  is  an  expensive  and  time  consuming  task. READ MORE

  3. 3. Effects of Transfer Learning on Data Augmentation with Generative Adversarial Networks

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

    Author : Olle Berglöf; Adam Jacobs; [2019]
    Keywords : data augmentation; generative adversarial networks; GAN; image classification; transfer learning; image generator; generating training data; machine learning;

    Abstract : Data augmentation is a technique that acquires more training data by augmenting available samples, where the training data is used to fit model parameters. Data augmentation is utilized due to a shortage of training data in certain domains and to reduce overfitting. READ MORE

  4. 4. Deep Active Learning for 3D Object Detection for Autonomous Driving

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

    Author : Xiao Wei; [2019]
    Keywords : ;

    Abstract : 3D object detection is vital for autonomous driving. However, to train a 3D detector often requires a huge amount of labeled data which are extremely expensive and tedious to obtain. READ MORE

  5. 5. Attempts at using Bayesian neural networksfor uncertainty assessments of temperature forecasts

    University essay from Lunds universitet/Förbränningsfysik; Lunds universitet/Fysiska institutionen

    Author : Joel Lundqvist; [2019]
    Keywords : Meteorology; Artificial neural networks; Bayesian neural networks; Forecast uncertainty; Physics and Astronomy;

    Abstract : This thesis describes attempts at estimating the uncertainty of the 2-metre temperature forecast error from a probabilistic point of view, utilizing Bayesian neural networks. Bayesian neural networks are a type of machine-learning algorithms used to find patterns in data and make probabilistic predictions. READ MORE