Sökning: "transfer learning"

Visar resultat 1 - 5 av 283 uppsatser innehållade orden transfer learning.

  1. 1. Fast visual grounding in interaction

    Master-uppsats, Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteori

    Författare :José Miguel Cano Santín; [2019-10-04]
    Nyckelord :grounding; object learning; interactive learning; transfer learning; neural networks;

    Sammanfattning : A big challenge for the development situated agents is that they need to be capable of grounding real objects of their enviroment to representations with semantic meaning, so they can be comunicated to human agents using the human language. de Graaf (2016) developed the KILLE framework, which is a static camerabasedrobot capable of learning objects and spatial relations from very few samples using image processing algorithms suitable for learning from few samples. LÄS MER

  2. 2. Dokumentation av båtar

    Master-uppsats, Göteborgs universitet/Institutionen för kulturvård

    Författare :Fredrik Leijonhufvud; [2019-05-23]
    Nyckelord :Documentation; Maritime Heritage; Photogrammetry; Craft Science; Forensic Perspective;

    Sammanfattning : Uppsats för avläggande av filosofie masterexamen med huvudområdet kulturvård2019, 60 hpAvancerad nivå2019.01... LÄS MER

  3. 3. Malignant Melanoma Classification with Deep Learning

    Master-uppsats, KTH/Medicinteknik och hälsosystem

    Författare :Jakob Kisselgof; [2019]
    Nyckelord :Melanoma classification deep learning;

    Sammanfattning : Malignant melanoma is the deadliest form of skin cancer. If correctly diagnosed in time, the expected five-year survival rate can increase up to 97 %. Therefore, exploring various methods for early detection can contribute with tools which can be used to improve detection of disease and finally to make sure that help is given in time. LÄS MER

  4. 4. Providing Mass Context to a Pretrained Deep Convolutional Neural Network for Breast Mass Classification

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

    Författare :Lovisa Montelius; George Rezkalla; [2019]
    Nyckelord :Deep learning; Convolutional neural network; Transfer learning; Computer-aided diagnosis; Breast cancer; Breast mass classification; Breast mass context; ;

    Sammanfattning : Breast cancer is one of the most common cancers among women in the world, and the average error rate among radiologists during diagnosis is 30%. Computer-aided medical diagnosis aims to assist doctors by giving them a second opinion, thus decreasing the error rate. LÄS MER

  5. 5. Emotion Classification with Natural Language Processing (Comparing BERT and Bi-Directional LSTM models for use with Twitter conversations)

    Master-uppsats, Lunds universitet/Matematisk statistik

    Författare :Nathaniel Joselson; Rasmus Hallén; [2019]
    Nyckelord :Mathematics and Statistics;

    Sammanfattning : We have constructed a novel neural network architecture called CWE-LSTM (concatenated word-emoji bidirectional long short-term memory) for classify- ing emotions in Twitter conversations. The architecture is based on a combina- tion of word and emoji embeddings with domain specificity in Twitter data. LÄS MER