Sökning: "Deep Text"

Visar resultat 1 - 5 av 237 uppsatser innehållade orden Deep Text.

  1. 1. Utmaningar i geometriundervisning: en djupdykning i innehåll, elevers missuppfattningar och lärarinterventioner

    Uppsats för yrkesexamina på grundnivå, Malmö universitet/Fakulteten för lärande och samhälle (LS)

    Författare :Linnea Listring; Ida Green; [2024]
    Nyckelord :geometric objects; two- and three dimensional objects; relational understanding; instrumental understanding; teaching methods; Van Hiele instructional model; practical elements; daily life;

    Sammanfattning : This text discusses final results from empirical studies, scientific articles and literature from the period 1990-2023, concerning teachers’ knowledge, students’ misconceptions and various teaching methods related to geometric objects. The results highlight challenges for both teachers and students in understanding and defining geometric shapes and figures. LÄS MER

  3. 2. Self-Supervised Learning for Tabular Data: Analysing VIME and introducing Mix Encoder

    Kandidat-uppsats, Lunds universitet/Fysiska institutionen

    Författare :Max Svensson; [2024]
    Nyckelord :Machine Learning; Self-supervised learning; AI; Physics; Medicine; Physics and Astronomy;

    Sammanfattning : We introduce Mix Encoder, a novel self-supervised learning framework for deep tabular data models based on Mixup [1]. Mix Encoder uses linear interpolations of samples with associated pretext tasks to form useful pre-trained representations. LÄS MER

  4. 3. Deep Learning Based Sentiment Analysis

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Shashank Kalluri; [2023]
    Nyckelord :Sentiment Analysis; Word Embedding; Deep Learning;

    Sammanfattning : Background: Text data includes things like customer reviews and complaints,tweets from social media platforms. When analyzing text-based data, the SentimentModel is used. Understanding news headlines, blogs, the stock market, politicaldebates, and film reviews some of the areas where sentiment analysis is used. LÄS MER

  5. 4. A lightweight deep learning architecture for text embedding : Comparison between the usage of Transformers and Mixers for textual embedding

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

    Författare :Corentin Royer; [2023]
    Nyckelord :Deep Learning; Entity Retrieval; Mixer; Transformer;

    Sammanfattning : Text embedding is a widely used method for comparing pieces of text together by mapping them to a compact vector space. One such application is deduplication which consists in finding textual records that refer to the same underlying idea in order to merge them or delete one of them. LÄS MER

  7. 5. Evaluating and Fine-Tuning a Few-Shot Model for Transcription of Historical Ciphers

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Ingrid Eliasson; [2023]
    Nyckelord :historical ciphers; few-shot learning; automatic transcription;

    Sammanfattning : Thousands of historical ciphers, encrypted manuscripts, are stored in archives across Europe. Historical cryptology is the research field concerned with studying these manuscripts - combining the interest of humanistic fields with methods of cryptography and computational linguistics. LÄS MER