Search for dissertations about: "Förstärkningsinlärning"

Showing result 1 - 5 of 13 swedish dissertations containing the word Förstärkningsinlärning.

2. 1. A study of wireless communications with reinforcement learning

   Author : Wanlu Lei; Ming Xiao; Chenguang Lu; Mikael Skoglund; Geoffrey Ye Li; KTH; []
   Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Reinforcement learning; wireless communications; decentralized learning; beam tracking; machine learning; Förstärkningsinlärning; trådlös kommunikation; decentrali- serad inlärning; strålspårning i mmvåg; maskininlärning; Electrical Engineering; Elektro- och systemteknik;

   Abstract :  The explosive proliferation of mobile users and wireless data traffic in recent years pose imminent challenges upon wireless system design. The trendfor wireless communications becoming more complicated, decentralized andintelligent is inevitable. READ MORE

4. 2. Location-aided Beam Alignment and Handover in Millimeter-wave Networks

   Author : Sara Khosravi; Marina Petrova; Jens Zander; Sofie Pollin; KTH; []
   Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Millimeter wave networks; beam alignment; Handover; Reinforcement learning; Millimetervågnätverk; strålinriktning; överlämning; förstärkningsinlärning;

   Abstract : Ever-increasing data rate demands in mobile networks and the spectrum scarcity at the microwave bands have resulted in the exploration of millimeter-wave (mmWave) frequencies for the next generation of wireless networks. While mmWave frequencies offer large bandwidth, communication at these frequencies is not straightforward due to the challenging propagation characteristics. READ MORE

5. 3. Reinforcement Learning for Active Visual Perception

   Author : Aleksis Pirinen; Mathematical Imaging Group; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; computer vision; reinforcement learning; deep learning; active vision; object detection; human pose estimation; semantic segmentation;

   Abstract : 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. READ MORE

6. 4. On learning in mice and machines : continuous population codes in natural and artificial neural networks

   Author : Emil Wärnberg; Konstantinos Meletis; Arvind Kumar; Gilad Silberberg; Mark Humphries; KTH; Karolinska Institutet; Karolinska Institutet; []
   Keywords : MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Biotechnology; Bioteknologi; Tillämpad matematik och beräkningsmatematik; Applied and Computational Mathematics;

   Abstract : Neural networks, whether artificial in a computer or natural in the brain, could represent information either using discrete symbols or continuous vector spaces. In this thesis, I explore how neural networks can represent continuous vector spaces, using both simulated neural networks and analysis of real neural population data recorded from mice. READ MORE

7. 5. Efficient and Trustworthy Artificial Intelligence for Critical Robotic Systems

   Author : Christopher Sprague; Petter Ögren; John Folkesson; Ivan Stenius; Todor Stoyanov; KTH; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; behaviour trees; hybrid dynamical systems; formal guarantees; optimal control; machine learning; autonomy; Datalogi; Computer Science;

   Abstract : Critical robotic systems are systems whose functioning is critical to both ensuring the accomplishment of a given mission and preventing the endangerment of life and the surrounding environment. These critical aspects can be formally captured by convergence, in the sense that the system's state goes to a desired region of the statespace, and safety, in the sense that the system's state avoids unsafe regions of the statespace. READ MORE