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 133542 for “"learning"”.
-
Learning Features for Unsupervised Learning and Reinforcement Learning
<p>Feature learning has been one of the main tasks in machine learning, and the recent advancement in deep learning only increases the importance of understanding the role of features, and designing efficient algorithms to learn these latent representations. Motivated by the successes from deep …
-
Analytics In Learning : From Consumer Learning to Organizational Learning
This dissertation revolves around the theme of learning. In essay one, we first ask an interesting question: what has been recalled by a consumer when making a brand choice. Is it a previously formed overall impression toward the brand or a vivid visualization of certain consumption episodes? A …
-
Federated Learning and Incremental Learning: Private Non-IID Learning
In traditional centralized Deep Learning all the data is available at a certain place and time. Training a Machine Learning model in such a scenario is rather straightforward and also well-studied. However, there are many scenarios, where this is not the case: scenarios where the data is scattered …
-
Contrastive Learning in Deep Learning
Contrastive Learning is a popular method for training modern deep neural networks. In this thesis, we explore several methods in the supervised learning and semi-supervised learning setting. Firstly, we propose a technique called Negative Sampling in Semi-Supervised Learning (NS3L). NS3L exploits …
-
Learning Abstractions via Reinforcement Learning
… multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is referred to as a neuro-symbolic system. The agents are not restricted to only use initial primitives: reinforcement learning is interleaved with steps to extend the current …
-
Learning to walk using deep reinforcement learning and transfer learning
… impact in computer graphics, robotics, machine learning, and biomechanics. However, there are two main hurdles in achieving this goal. First, synthesizing a successful locomotion policy requires precise control of a high-dimensional under-actuated system and striking a balance among a set of …
-
Learning with Minimal Supervision: New Meta-Learning and Reinforcement Learning Algorithms
Standard machine learning approaches thrive on learning from huge amounts of labeled training data, but what if we don’t have access to large amounts of labeled datasets? Humans have a remarkable ability to learn from only a few examples. To do so, they either build upon their prior learning …
-
Learning with Limited Datasets: From Deep-Learning to Traditional Machine-Learning
Learning with datasets containing a limited number of exemplars is a contentious research area. Researchers have used deep learning (DL) models with a large number of trainable parameters for such limited datasets leading to problems such as overfitting, over-parameterization, lack of …
-
LEARNING GENERALIZABLE REPRESENTATIONS IN REINFORCEMENT LEARNING
Learning a suitable representation is an important step towards building AI in reinforcement learning. In many scenarios, we would like the learned representation to summarize the information shared across similar tasks and have good generalization ability. We focus on two aspects of good …
-
Machine Learning Techniques for Personalized Learning
Recent developments in personalized learning, powered by recent advances in machine learning and big data, have the potential to revamp the “one-size-fits-all” approach in today’s education by delivering a fully personalized learning experience for each student. The key behind these developments is …
-
Continual learning for efficient machine learning
<p>Deep learning has enjoyed tremendous success over the last decade, but the training of practically useful deep models remains highly inefficient both in terms of the number of weight updates and training samples. To address one aspect of these issues, this thesis studies the continual learning …
-
Mutual Learning Algorithms in Machine Learning
Mutual learning algorithm is a machine learning algorithm where multiple machine learning algorithms learns from different sources and then share their knowledge among themselves so that all the agents can improve their classification and prediction accuracies simultaneously. Mutual learning …
-
Teacher Learning Within Professional Learning Communities
<p>Professional Learning Community (PLC) structures require focused sessions of teacher collaboration as part of developing effective instructional practices leading to improved student performance outcomes. The PLC structured collaboration model has been implemented in schools across the country, …
-
Improving Machine Learning Through Oracle Learning
… paradigm for improving the training of machine learning algorithms, oracle learning. The main idea in oracle learning is that instead of training directly on a set of data, a learning model is trained to approximate a given oracle's behavior on a set of data. This can be beneficial in situations …
-
Traditional Learning, Cooperative Learning, and Recorder
… this study was to determine whether cooperative learning strategies or traditional direct instruction would more positively affect the performance achievement of fourth- and fifth-grade recorder students. It was hypothesized that students participating in cooperative learning activities might …
-
Curriculum learning for online reinforcement learning
Curriculum learning in reinforcement learning is a rapidly growing research field used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, most of the …
-
Learning under Dynamics: Distribution Shift Detection and Continual Learning via Modulated Learning
Modern machine learning systems remain brittle in non-stationary, open-world environments. Robustness requires two complementary capabilities: detecting when data shifts beyond known boundaries, and adapting to novel concepts without catastrophically forgetting the past. This dissertation develops …
-
Learning through service : community service learning and situated learning in high school
… resulting from the merging of situated learning's socio-cultural conceptualization of the nature of learning with community service learning's ethos of service. As such, I enquired into the effects of the integration of situated learning as the conceptual framework, and community service …
-
Reinforcement Learning based Recommender System using Q-Learning and Deep Q-Learning
… on the recommender system using reinforcement learning. We have performed a systematic review of the research studies published from 2010-2022. The second part of this thesis demonstrates Q-learning and Deep Q-learning applied in movie recommender systems using the Netflix prize data set. The …
Page 1 of 6678