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 69 for “"Learning scenario"”.
-
Effective Learning on Non-Stationary Data Distribution
… Forgetting (CF) widely exists in various machine learning scenarios. In this thesis, we study two representative learning scenarios: i.e., (1) learning on a super long sequence of tasks with classes in each task are overlapping; (2) learning on a shorter sequence of tasks with classes in each task …
-
Deep knowledge transfer for generalization across tasks and domains under data scarcity
Over the last decade, deep learning approaches have achieved tremendous performance in a wide variety of fields, e.g., computer vision and natural language understanding, and across several sectors such as healthcare, industrial manufacturing, and driverless mobility. Most deep learning successes …
-
Age and Context Dependency in Causal Learning
… for the deficit in older adults’ causal learning. The purpose of the current study was to more directly test how associative deficits related to older adults’ contextual processing affect their causal learning. Based on past research, it was hypothesized that older adults would be less …
-
Διδακτικά σενάρια στο γλωσσικό μάθημα του δημοτικού σχολείου: θεωρία και πράξη
The learning scenario is the basic didactic approach recommended by the Study Curriculum (2011) in the subject of Language. Its main features are the cultivation of critical literacy, the use of various means of semiotic (multimodality) of the texts, as well as the possibilities offered by new …
-
Compreensão de egressos da Residência Multiprofissional em Atenção Básica no município de Caicó/RN acerca da inserção no serviço hospitalar como cenário de aprendizagem
… about the insertion of the hospital service as a learning scenario, considering the multiprofessional/interprofessional and intersectoral work, for the integrality of the care and integration of the health care network and, the based on this, to build, as a product, a technical report for …
-
Machine learning model selection with multi-objective Bayesian optimization and reinforcement learning
A machine learning system, including when used in reinforcement learning, is usually fed with only limited data, while aimed at training a model with good predictive performance that can generalize to an underlying data distribution. Within certain hypothesis classes, model selection chooses a …
-
Learning to answer questions from human feedback
… human feedback. We formulate a contextual bandit learning scenario: human users pose questions to a system, and give feedback to output answers based on the context from which they are taken. Prior work in this setting only considered a simplified setting where questions are always answerable with …
-
DEVELOPMENT OF DEEP LEARNING METHODS FOR PROGNOSTICS AND HEALTH MANAGEMENT
… convolutional neural network to transfer learning scenario. To reduce domain discrepancy caused by different working conditions, multi-layer adaptation based on multiple kernels is used. Owing to the availability of multiple labeled source domains, we then propose a unsupervised …
-
Older adults’ collaborative learning dynamics when exploring feature-rich software
… through complex structures which can make their learning process difficult. While many studies have investigated software learning, they typically have not focused on older adult users. Given that older adults are increasingly using more complex software, we aimed to investigate how older adults …
-
Developing an engagement and social interaction model for a robotic educational agent
… four essential goals during a student's learning process: 1) monitor engagement, 2) re-engage when appropriate, 3) teach novel tasks, and 4) improve retention. In this dissertation, we focus on all of these objectives through use of a teaching device (computer, tablet, or virtual reality …
-
Quality of learner experience in technology-enhanced learning: a reference layered framework, model instantiation guidelines and empirical Investigation
… in order to offer a qualitative holistic learning experience. In the first part of the thesis, an original synthesis of related theory is presented, and a reference layered framework is proposed, which illustrates a taxonomy of QoLE influencers according to identified quality dimensions. …
-
Beyond the Pitch: Teaching Emotional Labor in Advertising Education Through an Action Research Program
… through a thoroughly documented experiential learning study. This study employs Participatory Action Research (PAR) to investigate, develop, and test advertising curriculum for emotional labor in collaboration with undergraduate students currently enrolled in strategic communication programs. …
-
A requirements elicitation framework for agent-oriented software engineering.
… be constructed, before validating with a mobile learning scenario. The ensuing discussion evaluates how useful the approach is, and demonstrates the following contributions: Use of the Transaction Model to impose a rigour upon the requirements elicitation process for agent-based systems; Use of …
-
Neuromorphic Computing Applications in Robotics
Deep learning achieves remarkable success through training using massively labeled datasets. However, the high demands on the datasets impede the feasibility of deep learning in edge computing scenarios and suffer from the data scarcity issue. Rather than relying on labeled data, animals learn by …
-
On triggered learning
… are known as triggers. The study of triggered learning emphasises a number of dimensions of language acquisition. Here I consider three such dimensions: the space of possible languages, the nature of the input the child receives, and the nature of the learning algorithm. Chapter 1 provides an …
-
Competitive regression.
… of online regression. In essence, supervised learning from a data sequence consisting of n-dimensional input and the corresponding output is considered. In this work online learning scenario considered consists of sequential arrival of data, without making any stochastic assumptions on the …
-
Implementação de um cenário de prática para o ensino na atenção à saúde da pessoa idosa
… this population, as well as creating a practical learning scenario for undergraduate and graduate students at Escola Multicampi de Ciências Médicas da Universidade Federal do Rio Grande do Norte. METHODS: The process of organization of the service included: articulation with the managers to define …
-
Artificial Immune Systems for Web Content Mining: Focusing on the Discovery of Interesting Information
… AIS are thought to confer the adaptability and learning required for this task. Two novel Artificial Immune Systems are described and tested. AISEC (Artificial Immune System for Interesting E-mail Classification) is a novel, immune inspired system for the classification of e-mail. It is shown …
-
Training and Understanding Deep Neural Networks for Robotics, Design, and Visual Perception
… robots and describe the performance of various learning algorithms for automating generation of quadruped gaits. Notably, labels employed for learning are gather entirely for real-world experiments run in the learning loop. This results in a challenging learning scenario with limited labels, but …
-
Learning temporal logic formulae from data
… has been a great interest in applying machine learning-based techniques to the formal methods field. In this thesis, we focus on inferring high-level descriptions of a system from its execution traces. The system behaviors are formalized using an appropriate temporal logic language called …
Page 1 of 4