Sökning: "Jacob Åslund"

Hittade 2 uppsatser innehållade orden Jacob Åslund.

  1. 1. Zero/Few-Shot Text Classification : A Study of Practical Aspects and Applications

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

    Författare :Jacob Åslund; [2021]
    Nyckelord :zero-shot learning; few-shot learning; text classification; active learning; automated data labeling; interpretable machine learning; deep learning; NLP; NLU; zero-shot learning; few-shot learning; textklassificering; aktiv inlärning; automatiserad datamärkning; tolkningsbar maskininlärning; djupinlärning; NLP; NLU;

    Sammanfattning : SOTA language models have demonstrated remarkable capabilities in tackling NLP tasks they have not been explicitly trained on – given a few demonstrations of the task (few-shot learning), or even none at all (zero-shot learning). The purpose of this Master’s thesis has been to investigate practical aspects and potential applications of zero/few-shot learning in the context of text classification. LÄS MER

  3. 2. Compression of Generative Networks for Single Image Super-Resolution

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

    Författare :Jacob Åslund; Anton Dahlin; [2020]
    Nyckelord :;

    Sammanfattning : In this research project we have compressed the model size of a generative neural network trained to upscale low resolution images. After first training a large network for this task, we used knowledge distillation to train smaller networks to approximate its output. LÄS MER