Sökning: "joint learning"
Visar resultat 16 - 20 av 170 avhandlingar innehållade orden joint learning.
16. Self-Monitoring using Joint Human-Machine Learning : Algorithms and Applications
Sammanfattning : The ability to diagnose deviations and predict faults effectively is an important task in various industrial domains for minimizing costs and productivity loss and also conserving environmental resources. However, the majority of the efforts for diagnostics are still carried out by human experts in a time-consuming and expensive manner. LÄS MER
17. Att utveckla mellanstadieelevers kritiska och temporala tänkande : En lärandeverksamhetsteoretisk studie rörande hållbar utveckling
Sammanfattning : The aim of the study is to investigate what critical and temporal thinking can mean for younger students (aged 9-10) that requires the adoption of various perspectives in the context of sustainable urban planning, and how such knowing can be orchestrated in joint theoretical exploration work. A particular area of interest is the concept of contradictions (as used in activity theory) as a potential didactic tool for the subject, i. LÄS MER
18. Reinforcement Learning for Active Visual Perception
Sammanfattning : Visual perception refers to automatically recognizing, detecting, or otherwise sensing the content of an image, video or scene. The most common contemporary approach to tackle a visual perception task is by training a deep neural network on a pre-existing dataset which provides examples of task success and failure, respectively. LÄS MER
19. Joint Attention in Development : Insights from Children with Autism and Infant Siblings
Sammanfattning : Compared to other children, children with Autism Spectrum Disorder (ASD) are known to engage less in joint attention - the sharing of attention between two individuals toward a common object or event. Joint attention behaviors - for example gaze following, alternating gaze, and pointing - play an important role in early development, as they provide a foundation for learning and social interaction. LÄS MER
20. 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