Sökning: "dictionary learning"

Visar resultat 11 - 15 av 44 uppsatser innehållade orden dictionary learning.

  1. 11. Sparse Approximation of Spatial Channel Model with Dictionary Learning

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

    Författare :Matilda Zhou; [2022]
    Nyckelord :Spatial channel model SCM ; dictionary learning; compressive sensing CS ; discrete Fourier transform DFT ; overcomplete discrete Fourier transform ODFT ; Rumslig kanalmodell; ordbokslärning; kompressionsavkänning; diskret Fourier-transform; överkomplett diskret Fourier-transform;

    Sammanfattning : In large antenna systems, traditional channel estimation is costly and infeasible in some situations. Compressive sensing was proposed to estimate the channel with fewer measurements. Most of the previous work uses a predefined discrete Fourier transform matrix or overcomplete Fourier transform matrix to approximate the channel. LÄS MER

  3. 12. Using Twitter Attribute Information to Predict Stock Prices

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

    Författare :Roderick Karlemstrand; Ebba Leckström; [2021]
    Nyckelord :Stock price prediction; Machine Learning; Deep Learning; Time series prediction; Twitter; Twitter attributes;

    Sammanfattning : Being able to predict stock prices might be the unspoken wish of stock investors. Although stock prices are complicated to predict, there are many theories about what affects their movements, including interest rates, news and social media. With the help of Machine Learning, complex patterns in data can be identified beyond the human intellect. LÄS MER

  4. 13. Predicting average response sentiments to mass sent emails using RNN

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

    Författare :Adel Bavey; [2021]
    Nyckelord :Sentiment Analysis; Sentiment Forecasting; Natural Language Processing; Machine Learning; Recurrent Neural Nets; E-mails; Sentiment Analys; Sentiment Förutsägning; Naturlig Språkbehandling; Maskininlärning; Recurrenta Neurala nät; E-mails;

    Sammanfattning : This study is concerned with using the popular Recurrent Neural Network (RNN) model, and its variants Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM), on the novel problem of Sentiment Forecasting (SF). The goal of SF is to predict what the sentiment of a response will be in a conversation, using only the previous utterance. LÄS MER

  5. 14. Los textos narrativos como instrumento didáctico en la enseñanza del español como lengua materna en Suecia

    Kandidat-uppsats, Stockholms universitet/Romanska och klassiska institutionen

    Författare :Sandra Viviana Castillo Rengifo; [2021]
    Nyckelord :Literature; narrative texts; mother tongue; motivation; language acquisition;

    Sammanfattning : This research addresses the issue of narrative texts in the teaching of Spanish. Narrative texts and literature in general can be instruments of great value teaching and learning a language when used appropriately. Therefore, it is interesting to know how teachers use this didactic tool and how narrative texts can motivate students. LÄS MER

  7. 15. Managing language learning data in mobile apps

    Kandidat-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Författare :Christian Mårtensson; [2020]
    Nyckelord :Bilingual Dictionary; Computer-Assisted Language Learning; Dictionary Apps; Interaction Design; Mobile Apps; Mobile Learning;

    Sammanfattning : On the journey of learning a language we are exposed to countless words that are easily forgotten and subsequently difficult to find again. This study investigates how to design a personal data management system that enables its users to efficiently organize, find and input the words and phrases that they encounter on their journey. LÄS MER