Sökning: "Adversarial Examples"
Visar resultat 1 - 5 av 16 uppsatser innehållade orden Adversarial Examples.
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 filologiSammanfattning : 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
2. Analysis of Flow Prolongation Using Graph Neural Network in FIFO Multiplexing System
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)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
3. Comparison of Discriminative and Generative Image Classifiers
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)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
4. Towards Deep Learning Accelerated Sparse Bayesian Frequency Estimation
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : 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
5. Analyzing the Negative Log-Likelihood Loss in Generative Modeling
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)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