Sökning: "zero rule"

Visar resultat 1 - 5 av 32 uppsatser innehållade orden zero rule.

1. 1. Comparison of VADER and Pre-Trained RoBERTa: A Sentiment Analysis Application

   Kandidat-uppsats, Lunds universitet/Statistiska institutionen

   Författare :Linda Erwe; Xin Wang; [2024]
   Nyckelord :sentiment analysis; natural language processing; BERT; VADER; sustainability report; Mathematics and Statistics;

   Sammanfattning : Purpose: The purpose of this study is to examine how the overall sentiment results from VADER and a pre-trained RoBERTa model differ. The study investigates potential differences in terms of the median and shape of the two distributions. Data: The sustainability reports of 50 independent random companies are selected as the sample. LÄS MER

3. 2. Exploring the Depth-Performance Trade-Off : Applying Torch Pruning to YOLOv8 Models for Semantic Segmentation Tasks

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

   Författare :Xinchen Wang; [2024]
   Nyckelord :Deep Learning; Semantic segmentation; Network optimization; Network pruning; Torch Pruning; YOLOv8; Network Depth; Djup lärning; Semantisk segmentering; Nätverksoptimering; Nätverksbeskärning; Fackelbeskärning; YOLOv8; Nätverksdjup;

   Sammanfattning : In order to comprehend the environments from different aspects, a large variety of computer vision methods are developed to detect objects, classify objects or even segment them semantically. Semantic segmentation is growing in significance due to its broad applications in fields such as robotics, environmental understanding for virtual or augmented reality, and autonomous driving. LÄS MER

4. 3. The effect of disorder on the axial anomaly in a lattice model in 1 + 1 dimensions

   Master-uppsats, KTH/Fysik

   Författare :Agnes Wattrang; [2023]
   Nyckelord :Axial anomaly; tight-binding model; semiclassical physics; correlated disorder.; Axial kiral anomali; tätbindningsmodell; semiklassisk fysik; korrelerad oordning;

   Sammanfattning : This work investigates the effect of a disorder potential, that represents impurities/dislocations in the lattice, on the time-dependent signature of the axial anomaly in a one-band tight-binding model in one spatial dimension. The tight-binding model is solved numerically and the simulation results are compared with a semiclassical expression for the time-dependent axial density, n5(t), due to Nielsen and Ninomiya [1]. LÄS MER

5. 4. Cellular Automata as Synthetic Training Data : Exploring behavioural patterns of neural networks

   Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Onur Yüksel; [2023]
   Nyckelord :;

   Sammanfattning : On the highest heights of the third AI spring where the interest in AI research and industrial applications is booming, it’s worth taking a step back to reexplore the basics. With the spirit of data-centric-ai, we discuss the use of Cellular Automata as a resource for synthetic training data and explore how properties of CA rules relate to learning. LÄS MER

7. 5. Increasing the Trustworthiness ofAI-based In-Vehicle IDS usingeXplainable AI

   Uppsats för yrkesexamina på avancerad nivå, Mittuniversitetet/Institutionen för informationssystem och –teknologi

   Författare :Hampus Lundberg; [2022]
   Nyckelord :Intrusion Detection System; In-Vehicle Intrusion Detection System; Machine Learning; Deep Learning; Explainable Artificial Intelligence; Trustworthiness.;

   Sammanfattning : An in-vehicle intrusion detection system (IV-IDS) is one of the protection mechanisms used to detect cyber attacks on electric or autonomous vehicles where anomaly-based IDS solution have better potential at detecting the attacks especially zero-day attacks. Generally, the IV-IDS generate false alarms (falsely detecting normal data as attacks) because of the difficulty to differentiate between normal and attack data. LÄS MER