Essays about: "data augmentation"

Showing result 41 - 45 of 179 essays containing the words data augmentation.

1. 41. Domain Adaptation with N-gram Language Models for Swedish Automatic Speech Recognition : Using text data augmentation to create domain-specific n-gram models for a Swedish open-source wav2vec 2.0 model

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Viktor Enzell; [2022]
   Keywords : Automatic Speech Recognition; Domain Adaptation; Language Models; Ngram Models; Wav2vec2; Taligenkänning; Domänanpassning; Språkmodeller; N-gramModeller; Wav2vec2;

   Abstract : Automatic Speech Recognition (ASR) enables a wide variety of practical applications. However, many applications have their own domain-specific words, creating a gap between training and test data when used in practice. READ MORE

3. 42. Classification and localization of extreme outliers in computer vision tasks in surveillance scenarios

   University essay from KTH/Hälsoinformatik och logistik

   Author : Tariq Daoud; Emanuel Zere Goitom; [2022]
   Keywords : Computer vision; deep learning; machine learning; artificial neural networks; convolutional neural networks; YOLOv4; Datorseende; djupinlärning; maskininlärning; artificiella neurala nätverk; konvolutionella neurala nätverk; YOLOv4;

   Abstract : Convolutional neural networks (CNN) have come a long way and can be trained toclassify many of the objects around us. Despite this, researchers do not fullyunderstand how CNN models learn features (edges, shapes, contours, etc.) fromdata. READ MORE

4. 43. Detecting gastrointestinal abnormalities with binary classification of the Kvasir-Capsule dataset : A TensorFlow deep learning study

   University essay from Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

   Author : Mathias Hollstensson; [2022]
   Keywords : TensorFlow; Image classification; Transfer learning; Binary classification; Data augmentation; Video capsule endoscopy; Kvasir-Capsule.;

   Abstract : The early discovery of gastrointestinal (GI) disorders can significantly decrease the fatality rate of severe afflictions. Video capsule endoscopy (VCE) is a technique that produces an eight hour long recording of the GI tract that needs to be manually reviewed. READ MORE

5. 44. Classification Method of Financial Behaviour Through Means of Machine Learning : Can a classification method created using bank transaction and machine learning help individuals to understand their spending behavior?

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Yilei Cheng; Akhmed Al-Sayed; [2022]
   Keywords : machine learning; bank transactions; classification; spending behaviour; overspending; money awareness.; maskininlärning; banktransaktioner; klassificering; utgiftsbeteende; överutgifter; finansiell kunskap.;

   Abstract : With the current fast transformation from physical cash to digitized banking systems, there are more and more people that are at risk of overspending without realizing it. There are methods and researches done that are targeted at incorporating machine learning in identifying fraudulent transactions and credit scores but currently there is no research done in categorizing people’s behaviour based on transaction records using machine learning techniques. READ MORE

6. 45. Methods for data and user efficient annotation for multi-label topic classification

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Agnieszka Miszkurka; [2022]
   Keywords : Natural Language Processing; Multi-label text classification; Active Learning; Zero-shot learning; Data Augmentation; Data-centric AI; Naturlig språkbehandling; Textklassificering med multipla klasser; Active Learning; Zero-shot learning; Data Augmentation; Datacentrerad AI;

   Abstract : Machine Learning models trained using supervised learning can achieve great results when a sufficient amount of labeled data is used. However, the annotation process is a costly and time-consuming task. There are many methods devised to make the annotation pipeline more user and data efficient. READ MORE