Avancerad sökning

Visar resultat 1 - 5 av 362 uppsatser som matchar ovanstående sökkriterier.

  1. 1. 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

  3. 2. Salt och Peppar : En läsning av Toni Morrisons novell Recitatif utifrån det teoretiska perspektivet dekonstruktion

    Kandidat-uppsats, Umeå universitet/Institutionen för kultur- och medievetenskaper

    Författare :Sofia Benczy; [2024]
    Nyckelord :Toni Morrison; Recitatif; Derrida; Deconstruction; Metaphysics; Binary opposition; Non-contradiction; Dialectical differences; Overturning; Displacement; Toni Morrison; Recitatif; Derrida; Dekonstruktion; Metafysik; Binära motsättningar; Motsägelselagen; Dialektik; Omvälvning; Förflyttning;

    Sammanfattning : In this paper I’m studying Toni Morrison’s short story Recitatif (2022) through the perspective of deconstruction. I theorise about conceptual meanings and differences that occur and can be found in structures. LÄS MER

  4. 3. Bridging Language & Data : Optimizing Text-to-SQL Generation in Large Language Models

    Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

    Författare :Niklas Wretblad; Fredrik Gordh Riseby; [2024]
    Nyckelord :Chaining; Classification; Data Quality; Few-Shot Learning; Large Language Model; Machine Learning; Noise; Prompt; Prompt Engineering; SQL; Structured Query Language; Text-to-SQL; Zero-Shot Learning; Noise Identification;

    Sammanfattning : This thesis explores text-to-SQL generation using Large Language Models within a financial context, aiming to assess the efficacy of current benchmarks and techniques. The central investigation revolves around the accuracy of the BIRD-Bench benchmark and the applicability of text-to-SQL models in real-world scenarios. LÄS MER

  5. 4. Optimising Machine Learning Models for Imbalanced Swedish Text Financial Datasets: A Study on Receipt Classification : Exploring Balancing Methods, Naive Bayes Algorithms, and Performance Tradeoffs

    Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

    Författare :Li Ang Hu; Long Ma; [2023]
    Nyckelord :Imbalanced datasets; Swedish text financial datasets; Accuracy; Matthews correlation coefficient; Recall; Multinomial Naive Bayes; SMOTE; TomekLinks; Performance optimization;

    Sammanfattning : This thesis investigates imbalanced Swedish text financial datasets, specifically receipt classification using machine learning models. The study explores the effectiveness of under-sampling and over-sampling methods for Naive Bayes algorithms, collaborating with Fortnox for a controlled experiment. LÄS MER

  7. 5. Classification of almost monomial subalgebras of small codimension

    Kandidat-uppsats, Lunds universitet/Matematik LTH; Lunds universitet/Matematik (naturvetenskapliga fakulteten); Lunds universitet/Matematikcentrum

    Författare :Ludvig Sundell; [2023]
    Nyckelord :Algebra; Subalgebra; Polynomial; SAGBI basis; LAGBI basis; Lower semigroup; Mathematics and Statistics;

    Sammanfattning : In this text, we study almost monomial subalgebras using LAGBI bases. We introduce the concept of a LAGBI base and present an algorithm for computing them. We then use this algorithm to find, and present in a table, all polynomial subalgebras with Frobenius number smaller than or equal to ten. LÄS MER