Sökning: "inlärningstekniker"

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

  1. 1. Unsupervised 3D Human Pose Estimation

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

    Författare :Sri Datta Budaraju; [2021]
    Nyckelord :Computer Vision; Projective Geometry; Deep Learning; Unsupervised Learning; 3D Human Pose Estimation; GAN; AutoEncoder; Hybrid Generative Model; Self Supervision;

    Sammanfattning : The thesis proposes an unsupervised representation learning method to predict 3D human pose from a 2D skeleton via a VAEGAN (Variational Autoencoder Generative Adversarial Network) hybrid network. The method learns to lift poses from 2D to 3D using selfsupervision and adversarial learning techniques. LÄS MER

  2. 2. Handwritten Recognition for Ethiopic (Ge’ez) Ancient Manuscript Documents

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

    Författare :Adisu Wagaw Terefe; [2020]
    Nyckelord :CNN; CTC; Ge’ez; Handwritten Recognition; LSTM; MDRNN; CNN; CTC; Ge’ez; Handskrivet erkännande; LSTM; MDRNN;

    Sammanfattning : The handwritten recognition system is a process of learning a pattern from a given image of text. The recognition process usually combines a computer vision task with sequence learning techniques. LÄS MER

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

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

    Författare :Emmeleia Panagiota Mastoropoulou; [2019]
    Nyckelord :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;

    Sammanfattning : 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. LÄS MER

  4. 4. Point Process Based Phoneme Recognition Acceleration

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

    Författare :Hongliang Qiu; [2019]
    Nyckelord :;

    Sammanfattning : Stochastic gradient descent (SGD) is the core technology to train a deep learning model. It is well known that SGD suffers from the variance of gradients in each iteration. Deep learning has already been widely used in many applications because of its great performance in tasks such as image recognition. LÄS MER

  5. 5. Unsupervised Learning of Visual Features for Fashion Classification

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

    Författare :Sumeet Dhariwal; [2019]
    Nyckelord :;

    Sammanfattning : Deep Learning has changed the way computer vision tasks are being solved in the current age. Deep Learning approaches have achieved state-of-the-art results in computer vision problems like image classification, image verification, object detection, and image segmentation. LÄS MER