Sökning: "seq2seq"

Visar resultat 1 - 5 av 11 uppsatser innehållade ordet seq2seq.

  1. 1. Dynamik och tillförlighet i finansiell prognostisering : En analys av djupinlärningsmodeller och deras reaktion på marknadsmanipulation

    M1-uppsats, KTH/Hälsoinformatik och logistik

    Författare :Aya Zawahri; Nanci Ibrahim; [2024]
    Nyckelord :LOB; market manipulation; spoofing; layering; DeepLOB; DeepLOB-Attention; TCN; DeepLOB-seq2seq; DTNN; ITCH; parsing.; LOB; marknadsmanipulation; spoofing; layering; DeepLOB; DeepLOB-Attention; TCN; DeepLOB-seq2seq; DTNN; ITCH; parsing.;

    Sammanfattning : Under åren har intensiv forskning pågått för att förbättra maskininlärningsmodellers förmåga att förutse marknadsrörelser. Trots detta har det, under finanshistorien, inträffat flera händelser, såsom "Flash-crash", som har påverkat marknaden och haft dramatiska konsekvenser för prisrörelserna. LÄS MER

  3. 2. Fine-Tuning Pre-Trained Language Models for CEFR-Level and Keyword Conditioned Text Generation : A comparison between Google’s T5 and OpenAI’s GPT-2

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

    Författare :Quintus Roos; [2022]
    Nyckelord :Transformed-based Pre-trained Language Models; Natural Language Processing; Natural Language Generation; Conditional Text Generation; Text Classification; Fine-tuning; English Language Learning.; Transformbaserade förtränade språkmodeller; naturlig språkbehandling; naturlig språkgenerering; betingad textgenerering; finjustering; instruktionsjustering; engelska inlärning.;

    Sammanfattning : This thesis investigates the possibilities of conditionally generating English sentences based on keywords-framing content and different difficulty levels of vocabulary. It aims to contribute to the field of Conditional Text Generation (CTG), a type of Natural Language Generation (NLG), where the process of creating text is based on a set of conditions. LÄS MER

  4. 3. An Initial Investigation of Neural Decompilation for WebAssembly

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

    Författare :Adam Benali; [2022]
    Nyckelord :Decompilation; WebAssembly; Reverse Engineering; Neural Machine Translation; Décompilation; WebAssembly; Rétro-Ingénierie; Traduction Automatique Neuronale; Dekompilering; WebAssembly; Reverse Engineering; Neural Maskinöversättning;

    Sammanfattning : WebAssembly is a new standard of the World Wide Web that is used as a compilation target and which is meant to enable high-performance applications. As it becomes more popular, the need for corresponding decompilers increases, for security reasons for instance. LÄS MER

  5. 4. Sequential Anomaly Detection for Log Data Using Deep Learning

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Lina Hammargren; Wei Wu; [2021-06-14]
    Nyckelord :anomaly detection; recurrent neural network; long short-term memory; semi-supervised learning; seq2seq; transformer; unsupervised learning; log analysis;

    Sammanfattning : Abstract Software development with continuous integration changes needs frequent testing for assessment. Analyzing the test output manually is time-consuming and automating this process could be beneficial to an organization. LÄS MER

  7. 5. Deep learning prediction of Quantmap clusters

    Master-uppsats, Uppsala universitet/Institutionen för biologisk grundutbildning

    Författare :Akshai Parakkal Sreenivasan; [2021]
    Nyckelord :Deep Learning; Machine Learning; Deep Neural Network; Convolutional Neural Network; Recurrent Neural Network; Drug classification; Drug-biological function;

    Sammanfattning : The hypothesis that similar chemicals exert similar biological activities has been widely adopted in the field of drug discovery and development. Quantitative Structure-Activity Relationship (QSAR) models have been used ubiquitously in drug discovery to understand the function of chemicals in biological systems. LÄS MER