Sökning: "multimodal inlärning"
Visar resultat 1 - 5 av 6 avhandlingar innehållade orden multimodal inlärning.
1. Adaptive Robot Presenters : Modelling Grounding in Multimodal Interaction
Sammanfattning : This thesis addresses the topic of grounding in human-robot interaction, that is, the process by which the human and robot can ensure mutual understanding. To explore this topic, the scenario of a robot holding a presentation to a human audience is used, where the robot has to process multimodal feedback from the human in order to adapt the presentation to the human's level of understanding. LÄS MER
2. Monolingual Policy, Bilingual Interaction : English-taught Education in Bangladesh
Sammanfattning : The research reported here is an investigation of bilingual instruction in Bangladeshi schools. In particular, the thesis explores how schooling takes place when a second language is used as a medium of instruction to teach subject content. LÄS MER
3. Flower Cues for Hawkmoths: Colour, Place and Odour
Sammanfattning : Flowers use different cues to attract pollinators including colour and odour. How do hawkmoths use these cues to find the flowers? This question was investigated in two species of hawkmoth, the diurnal species, Macroglossum stellatarum, and the nocturnal species, Deilephila elpenor. Both species have colour vision and D. LÄS MER
4. Developing Data-Driven Models for Understanding Human Motion
Sammanfattning : Humans are the primary subjects of interest in the realm of computer vision. Specifically, perceiving, generating, and understanding human activities have long been a core pursuit of machine intelligence. LÄS MER
5. Probabilistic machine learning methods for automated radiation therapy treatment planning
Sammanfattning : In this thesis, different parts of an automated process for radiation therapy treatment planning are investigated from a mathematical and computational perspective. Whereas traditional inverse planning is labor-intensive, often comprising several reiterations between treatment planner and physician before a plan can be approved, much of recent research have been aimed at using a data-driven approach by learning from historically delivered plans. LÄS MER