Sökning: "transfer learning"
Visar resultat 26 - 30 av 199 avhandlingar innehållade orden transfer learning.
26. Transfer Learning using low-dimensional Representations in Reinforcement Learning
Sammanfattning : Successful learning of behaviors in Reinforcement Learning (RL) are often learned tabula rasa, requiring many observations and interactions in the environment. Performing this outside of a simulator, in the real world, often becomes infeasible due to the large amount of interactions needed. LÄS MER
27. Data-Efficient Representation Learning for Grasping and Manipulation
Sammanfattning : General-purpose robotics require adaptability to environmental variations and, therefore, need effective representations for programming them. A common way to acquire such representations is through machine learning. Machine learning has shown great potential in computer vision, natural language processing, reinforcement learning, and robotics. LÄS MER
28. Outsourcing of Organizational Routines : Knowledge, control, and learning aspects
Sammanfattning : Organizational routines that are critical to learning, flexibility, and adaptation explain the behaviour of the business organization. When organizational routines cross the boundary of the organization, variability and stability are affected. LÄS MER
29. Lärande i organisationer : professionella yrkesutövares strategier vid organisatorisk förändring
Sammanfattning : This thesis is a study on the professional practice in knowledge organization in the public services. The empirical study deals with the strategies and learning processes developed by the professionals when their units transfer from appropriation financing to performance financing (client-contractor model). LÄS MER
30. Contributions to deep learning for imaging in radiotherapy
Sammanfattning : Purpose: The increasing importance of medical imaging in cancer treatment, combined with the growing popularity of deep learning gave relevance to the presented contributions to deep learning solutions with applications in medical imaging.Relevance: The projects aim to improve the efficiency of MRI for automated tasks related to radiotherapy, building on recent advancements in the field of deep learning. LÄS MER