Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 144 for “"self-training"”.

  1. A study of self-training variants for semi-supervised image classification

    … examples. Still, they can easily overfit training examples when few labelled examples are available. The requirement to have labels for all training examples is a strong limitation of standard supervised machine learning. This can be addressed by applying semi-supervised learning methods …

    waikato-masters Repository record for A study of self-training variants for semi-supervised image classification (opens in a new tab) Download file for A study of self-training variants for semi-supervised image classification (opens in a new tab)

  2. Influence of Quiet Eye Self-Training on Internal Processes and Performance Outcomes

    … study was to investigate the influence of QE self-training on college students' internal processes associated with performing a novel task. Specifically, college students' internal processes were examined to understand how QE self-training influenced performance on a novel aiming task. College …

    unt Repository record for Influence of Quiet Eye Self-Training on Internal Processes and Performance Outcomes (opens in a new tab)

  3. Self-training artificial neural networks for risk reduction in nuclear power operations

    The risk reduction potential of the class of artificial neural networks based on the Barto-Sutton architecture is established. The risk associated with nuclear power operations is characterized by sequences of discrete events, such as technical specification violation. The Barto-Sutton architecture …

    uiuc Repository record for Self-training artificial neural networks for risk reduction in nuclear power operations (opens in a new tab)

  4. Addressing data scarcity with deep transfer learning and self-training in digital pathology

    … tasks. Finally, we move to the topic of self-training, a family of methods where a model being learned is used to annotate unlabeled data that is then incorporated into the training process. In particular, we apply this technique to image segmentation for exploiting a dataset which has …

    liege Repository record for Addressing data scarcity with deep transfer learning and self-training in digital pathology (opens in a new tab) Download PDF for Addressing data scarcity with deep transfer learning and self-training in digital pathology (opens in a new tab)

  5. Self-training for cyberbully detection: Achieving high accuracy with a balanced multi-class dataset

    … of a balanced dataset specifically designed for training the ML/ DL models. To overcome the challenge of limited labeled data, we employ a semi-supervised self-training algorithm, which effectively expands the size of the labeled dataset. By leveraging real-world social media data, we train and …

    regina Repository record for Self-training for cyberbully detection: Achieving high accuracy with a balanced multi-class dataset (opens in a new tab) Download file for Self-training for cyberbully detection: Achieving high accuracy with a balanced multi-class dataset (opens in a new tab)

  6. Harnessing the Power of Self-Training for Gaze Point Estimation in Dual Camera Transportation Datasets

    … limitations, this thesis investigates the use of self-learning techniques such as semi-supervised learning and self-training, which can reduce the need for labeled data while maintaining high accuracy. The proposed method is evaluated on the DGAZE dataset and achieves a 57.2\% improvement in …

    vt Repository record for Harnessing the Power of Self-Training for Gaze Point Estimation in Dual Camera Transportation Datasets (opens in a new tab)

  7. Laisvalaikiu tenisą žaidžiančių vyrų fizinės saviugdos ypatumai /

    … of motives, scope, and intensity of physical self-training of men who play tennis in their leisure time and in this way form a kind of social group. Only upon analysis of peculiarities of physical self-training of tennis veterans, methodical recommendations for optimization of their physical …

    vilnius Repository record for Laisvalaikiu tenisą žaidžiančių vyrų fizinės saviugdos ypatumai / (opens in a new tab)

  8. Os ateliês (auto)formativos na constituição do sujeito docente da educação matemática

    The object of study of this thesis is the use of (self)training workshops as a fundamental process for the constitution of the teaching subject in mathematics education. The central purposes of the study were to describe and analyze a learning process of mathematics teachers supported by the …

    brazil-ufrn Repository record for Os ateliês (auto)formativos na constituição do sujeito docente da educação matemática (opens in a new tab)

  9. Creating An Engaging Environment For Adult ESL Learners in E-Learning Settings: Reducing Affective Filters and Cognitive Overload

    … crisis made people start thinking about self-improvement. This emergence of online education is a life-changing chance not only for the ESL education industry and teachers, but also for countless learners. This field project includes appropriate background, a review of relevant …

    usfca Repository record for Creating An Engaging Environment For Adult ESL Learners in E-Learning Settings: Reducing Affective Filters and Cognitive Overload (opens in a new tab)

  10. Vivências ludopoiéticas no jogo de areia: a tatilidade na autoformação humanescente

    … and the expression of tactility in humanescente self-training of future teachers of geography. The overall objective was to analyze and interpret as the tactility in the ludopoietic experiences with Sandplay facilitates the sentipensar and boosts the humanescent self-training. The qualitative …

    brazil-ufrn Repository record for Vivências ludopoiéticas no jogo de areia: a tatilidade na autoformação humanescente (opens in a new tab)

  11. Rozpoznávání notových zápisů pomocí neuronových sítí

    … anotovaných dat a ověřuje, zda lze pomocí metody self-trainingu adaptovat model bez rozsáhlé manuální anotace. Použitý model staví na Transformer architektuře typu encoder-decoder. Pro výběr pseudo-labelů je navržena metrika spojující konzistenci dekódování v běžném a obráceném směru s penalizací …

    brno-tech Repository record for Rozpoznávání notových zápisů pomocí neuronových sítí (opens in a new tab)

  12. Weakly supervised aspect extraction for domain-specific texts

    … model is equipped with multi-head attention and self-training. The multi-head attention is learned from the seed words to ensure that the aspect-related words in text segments are weighted higher than those unrelated ones. The self-training mechanism provides more pseudo labels in addition to …

    uiuc Repository record for Weakly supervised aspect extraction for domain-specific texts (opens in a new tab)

  13. On Training, Inference, and Sample Efficiencies of Language Models

    … In this thesis, we investigate efficient training and inference algorithms. We also investigate the sample efficiency of training language models. In Chapter 2, we improve training efficiency of sparsely activated models by proposing a novel Mixture-of-Experts architecture. In Chapter 3, …

    gatech Repository record for On Training, Inference, and Sample Efficiencies of Language Models (opens in a new tab)

  14. Teaching Graphing Using Enhanced Written Instructions: Does Chunk Size Matter

    … can be taught using various methods, perhaps self-training methods could prove both effective and efficient due to the self-guided nature of the methods. One effective self-training method for graphing is enhanced written instructions (EWI). While the literature has demonstrated EWI’s …

    ku Repository record for Teaching Graphing Using Enhanced Written Instructions: Does Chunk Size Matter (opens in a new tab)

  15. Mokinio, turinčio mokymosi sutrikimų, psichoedukacinis portretas /

    … this Master‘s Thesis, psychological educational (self-) training factors of students with learning disabilities have been analysed. The aim of the research has been to reveal psychological educational characterisation peculiarities of a student with learning disabilities. The following methods …

    vilnius Repository record for Mokinio, turinčio mokymosi sutrikimų, psichoedukacinis portretas / (opens in a new tab)

  16. Modeling Dependencies in Natural Languages with Latent Variables

    … parameters based on the type and the amount of training data available. We have created several different types of latent variable models for a diverse set of natural language processing applications, including novel models for part-of-speech tagging, language modeling, and machine translation, …

    maryland Repository record for Modeling Dependencies in Natural Languages with Latent Variables (opens in a new tab)

  17. Effective Use of Cross-Domain Parsing in Automatic Speech Recognition and Error Detection

    … error labels, but no hand-annotated parses: a self-training approach to directly improve the probabilistic context-free grammar (PCFG) model used in parsing, as well as a novel model combination method using a discriminative log-linear model to augment the generative PCFG. We apply both methods …

    washington Repository record for Effective Use of Cross-Domain Parsing in Automatic Speech Recognition and Error Detection (opens in a new tab)

Page 1 of 8