Essays about: "Transformer network"

Showing result 1 - 5 of 82 essays containing the words Transformer network.

1. 1. Detection of insurance fraud using NLP and ML

   University essay from Lunds universitet/Matematisk statistik

   Author : Rasmus Bäcklund; Hampus Öhman; [2023]
   Keywords : Technology and Engineering;

   Abstract : Machine-Learning can sometimes see things we as humans can not. In this thesis we evaluated three different Natural Language Procces-techniques: BERT, word2vec and linguistic analysis (UDPipe), on their performance in detecting insurance fraud based on transcribed audio from phone calls (referred to as audio data) and written text (referred to as text-form data), related to insurance claims. READ MORE

3. 2. Convolution-compacted visiontransformers forprediction of localwall heat flux atmultiple Prandtlnumbers in turbulentchannel flow

   University essay from KTH/Skolan för teknikvetenskap (SCI)

   Author : Yuning Wang; [2023]
   Keywords : Turbulent flow; Heat transfer; Vision transformer; Convolutional neural network; Machine learning;

   Abstract : Predicting wall heat flux accurately in wall-bounded turbulent flows is critical for a variety of engineering applications, including thermal management systems and energy-efficient designs. Traditional methods, which rely on expensive numerical simulations, are hampered by increasing complexity and extremly high computation cost. READ MORE

4. 3. Punctuation Restoration as Post-processing Step for Swedish Language Automatic Speech Recognition

   University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Author : Ishika Gupta; [2023]
   Keywords : Transformer; BERT; KB-BERT; NLP; punctuation restoration; deep learning; neural networks;

   Abstract : This thesis focuses on the Swedish language, where punctuation restoration, especially as a postprocessing step for the output of Automatic Speech Recognition (ASR) applications, needs furtherresearch. I have collaborated with NewsMachine AB, a company that provides large-scale mediamonitoring services for its clients, for which it employs ASR technology to convert spoken contentinto text. READ MORE

5. 4. Deep Neural Networks as SurrogateModels for Fuel Performance Codes

   University essay from Uppsala universitet/Tillämpad kärnfysik

   Author : Wenhan Zhou; [2023]
   Keywords : Transuranus; AI; Nuclear Fuel Rods;

   Abstract : The core component of a nuclear power plant is the reactor and the fuel rods that supply it with fission fuel. Efficient and safe energy extraction is thus highly dependent on the reactor design and the conditions of the fuel rods. To anticipate high-quality operation and potential risks in advance, one must perform simulations on the fuel rods. READ MORE

6. 5. Hybrid Deep Learning approach for Lane Detection : Combining convolutional and transformer networks with a post-processing temporal information mechanism, for efficient road lane detection on a road image scene

   University essay from Jönköping University/Jönköping AI Lab (JAIL)

   Author : Dimitrios Zarogiannis; Stelio Bompai; [2023]
   Keywords : Lane Detection; CNN; Vision Transformer; Deep Learning; Semantic Segmentation; Computer Vision;

   Abstract : Lane detection is a crucial task in the field of autonomous driving and advanced driver assistance systems. In recent years, convolutional neural networks (CNNs) have been the primary approach for solving this problem. READ MORE