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 46 for “"hierarchical learning"”.
-
On the Role of Prediction in Streaming Hierarchical Learning
… surveillance systems to sensory-motor autonomous learning. However, most existing models rely heavily on large, annotated datasets with fixed data distributions and offline epoch-based training, which makes them impractical for handling the unpredictability and scale of dynamic real-world …
-
Hierarchical learning and planning in partially observable Markov decision processes
Thesis (Ph. D.)--Michigan State University. Department of Computer Science & Engineering, 2002
-
Hierarchical learning for large multi-class classification in network data
Multi-class learning from network data is an important but challenging problem with many applications, including malware detection in computer networks, user modeling in social networks, and protein function prediction in biological networks. Despite the extensive research on large multi-class …
-
HIERARCHICAL LEARNING FOR WHOLE-BODY LOCO-MANIPULATION IN MULTI-LEGGED ROBOTS
… To address this challenge, we propose HeLoM, a learning-based hierarchical whole-body manipulation framework for hexapod robots. Inspired by multi-legged insects, HeLoM exploits multiple contact points and high degrees of freedom to achieve coordinated object interaction. The high-level planner …
-
Prediction and anomaly detection in water quality with explainable hierarchical learning through parameter sharing
… a simple, explainable, and transparent machine learning model that is derived from linear regression with hierarchical features for efficient prediction and for anomaly detection on large scale spatiotemporal datasets. Our model learns offsets for various features in the dataset while utilizing …
-
Transfer Effects Within a Hierarchical Learning Task as a Function of Review and Correction on Successive Parts
Made available in DSpace on 2014-12-08T21:23:22Z (GMT). No. of bitstreams: 1 6503637.pdf: 4275174 bytes, checksum: ba3fdd714509213035ebf30fd5cf49e6 (MD5) Previous issue date: 1964
-
Hierarchical Learning As A Function Of Concise Informational Feedback With Regard To Ability, Age, And Sex Of Identical Twins.
… feedback in light of certain characteristics of learning, and in light of student characteristics such as ability, age, and sex. The purpose of the study was to investigate the impact of specific informational feedback on hierarchical learning in a controlled laboratory setting, using the …
-
Hierarchies, search, and generative models in sequential decision-making
… agents trained using deep reinforcement learning (DRL) or imitation learning (IL) can achieve or even surpass expert-level performance in various controlled settings. However, translating this success to real-world tasks remains difficult, especially in high-stakes domains such as …
-
Children's Understanding of the Uses of Parentheses
… study lead to the following model regarding the learning of these uses: During the first of five phases, children learn the basic operations and the order-of-operations rule but have no understanding about the use of parentheses. In the second phase, children understand only that parentheses mean …
-
Persuasive Strategies for Social Robots Engaged in Human-Robot Interaction
… knowledge into the development of an adaptive learning architecture for robot persuasion. Several studies describe the investigation of a robot’s use of common persuasive dimensions such as rationale for compliance, communication explicitness, sanction use, and authoritative locus of control. …
-
Path Planning using Reinforcement Learning and Objective Data
… to find good solutions, so deep machine learning has become engineers’ focus in order to solve these problems. Several related works using reinforcement learning have been done in the simulation environment TORCS. This thesis will focus on training an vehicle to learn driving at certain …
-
Agile Legged Robots through Reinforcement Learning and Optimal Control
… constraints. On the other hand, reinforcement learning frameworks offer the potential to learn versatile, perception-integrated motion policies end-to-end. However, they often lack the precision and robustness of optimal control methods and require extensive tuning in reward shaping and …
-
Teachers' Perceptions on Professional Learning: A Mixed Method Program Evaluation in a Middle School Setting
… was evaluate the program of teacher professional learning at Hamlin Middle School to guide formative improvement, therefore maximizing the potential of increasing teacher effectiveness and results. By facilitating evaluative thinking among teachers on the topic of teacher professional learning, …
-
Learning deep representations for robotics applications
In this thesis, two hierarchical learning representations are explored in computer vision tasks. First, a novel graph theoretic method for statistical shape analysis, called Compositional Hierarchy of Parts (CHOP), was proposed. The method utilises line-based features as its building blocks for the …
-
Currere as Contemporary Art: Creative Research Methods for Teacher Self-Reflection
… However, practitioners who have experienced hierarchical learning structures may unconsciously replicate these norms in their own teaching methods. Through honest reflection, teachers can reckon with their formative experiences and use the resulting insights to transcend ingrained behaviors …
-
Learning Motion Policies for Dexterous Manipulation with Geometric Fabrics
… controllers. Recent advances suggest that learning-based techniques could hold the key to equipping robots with complex manipulation skills. However, existing learning methods either limit themselves to highly constrained problems and smaller models to enable impressive sample efficiency, …
-
Teacher Leadership: A Case Study in the Preparation of Future Teacher Leaders
… through 12th grade (PK-12) schools evolved into hierarchical learning organizations that centralized power, decision-making, and leadership at the top in the hands of a few predominantly male administrators. the teaching force, by contrast, became majority female. While teacher education programs …
-
Hierarchical text categorization and its application to bioinformatics
In a hierarchical categorization problem, categories are partially ordered to form a hierarchy. In this dissertation, we explore two main aspects of hierarchical categorization: learning algorithms and performance evaluation. We introduce the notion of consistent hierarchical classification that …
Page 1 of 3