Sökning: "Adversarial Examples"

Visar resultat 1 - 5 av 16 uppsatser innehållade orden Adversarial Examples.

1. 1. Natural Language Inference Transfer Learning in a Multi-Task Contract Dataset : In the Case of ContractNLI: a Document Information Extraction System

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

   Författare :Yiu Kei Tang; [2023]
   Nyckelord :;

   Sammanfattning : This thesis investigates the enhancement of legal contract Natural Language Inference (NLI) classification through supervised fine-tuning on general domain NLI, in the case of ContractNLI and Span NLI BERT (Koreeda and Manning, 2021), a multi-task document information extraction dataset and framework. Annotated datasets of a specific professional domain are scarce due to the high time and labour cost required to create them. LÄS MER

3. 2. Analysis of Flow Prolongation Using Graph Neural Network in FIFO Multiplexing System

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

   Författare :Weiran Wang; [2023]
   Nyckelord :Network Calculus; Flow Prolongation; Graph Neural Network; Fast Gradient Sign Method; Delay Bound; Nätverkskalkyl; Flödesförlängning; Graph Neural Network; Fast Gradient Sign Method; Fördröjningsgräns;

   Sammanfattning : Network Calculus views a network system as a queuing framework and provides a series of mathematical functions for finding an upper bound of an end-to-end delay. It is crucial for the design of networks and applications with a hard delay guarantee, such as the emerging Time Sensitive Network. LÄS MER

4. 3. Comparison of Discriminative and Generative Image Classifiers

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

   Författare :Simon Budh; William Grip; [2022]
   Nyckelord :Image classification; CNN; Normalizing flows; RealNVP; Adversarial examples;

   Sammanfattning : In this report a discriminative and a generative image classifier, used for classification of images with handwritten digits from zero to nine, are compared. The aim of this project was to compare the accuracy of the two classifiers in absence and presence of perturbations to the images. LÄS MER

5. 4. Towards Deep Learning Accelerated Sparse Bayesian Frequency Estimation

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Mika Persson; [2022]
   Nyckelord :Bayesian Statistics; Deep Learning; Frequency Estimation; Generative Adversarial Networks; Artificial Neural Networks; Statistical Modelling; Mathematics and Statistics;

   Sammanfattning : The Discrete Fourier Transform is the simplest way to obtain the spectrum of a discrete complex signal. This thesis concerns the case when the signal is known to contain a small (unknown) number of frequencies, not limited to the discrete Fourier frequencies, embedded in complex Gaussian noise. LÄS MER

7. 5. Analyzing the Negative Log-Likelihood Loss in Generative Modeling

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

   Författare :Aleix Espuña I Fontcuberta; [2022]
   Nyckelord :Generative modeling; Normalizing flows; Generative Adversarial Networks; MaximumLikelihood Estimation; Real Non-Volume Preserving flow; Fréchet Inception Distance; Misspecification; Generativa metoder; Normalizing flows; Generative adversarial networks; Maximum likelihood-metoden; Real non-volume preserving flow; Fréchet inception distance; felspecificerade modeller;

   Sammanfattning : Maximum-Likelihood Estimation (MLE) is a classic model-fitting method from probability theory. However, it has been argued repeatedly that MLE is inappropriate for synthesis applications, since its priorities are at odds with important principles of human perception, and that, e.g. LÄS MER