Sökning: "learning and memory"

Visar resultat 16 - 20 av 325 avhandlingar innehållade orden learning and memory.

1. 16. Learning-based Control for 4D Printing and Soft Robotics

   Författare :Qinglei Ji; Lei Feng; Lihui Wang; Xi Vincent Wang; Yong Chen; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; 3D Printing; 4D Printing; Soft Robots; Machine Learning; Reinforcement Learning; Control; Production Engineering; Industriell produktion;

   Sammanfattning : Exploiting novel sensors and actuators made of flexible and smart materials becomes a new trend in robotics research. The studies on the design, production, and control of the new type of robots motivate the research fields of soft robots and 4D printed robots. LÄS MER

3. 17. Time, space and control: deep-learning applications to turbulent flows

   Författare :Luca Guastoni; Ricardo Vinuesa; Hossein Azizpour; Philipp Schlatter; Andrea Beck; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; turbulence; deep learning; deep reinforcement learning; flow control; turbulens; djupinlärning; djupförstärkningsinlärning; flödeskontroll; Teknisk mekanik; Engineering Mechanics;

   Sammanfattning : In the present thesis, the application of deep learning and deep reinforcement learning to turbulent-flow simulations is investigated. Deep-learning models are trained to perform temporal and spatial predictions, while deep reinforcement learning is applied to a flow-control problem, namely the reduction of drag in an open channel flow. LÄS MER

4. 18. Mathematical Learning Disability : Cognitive Conditions, Development and Predictions

   Författare :Rickard Östergren; Ulf Träff; Joakim Samuelsson; Örjan Dahlström; Åke Olofsson; Linköpings universitet; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Mathematical learning disability; dyscalculia; mathematical cognition; number sense; Matematiska inlärningssvårigheter; dyskalkyli; matematisk kognition; antalsuppfattning;

   Sammanfattning : The purpose of the present thesis was to test and contrast hypotheses about the cognitive conditions that support the development of mathematical learning disability (MLD). Following hypotheses were tested in the thesis: a) domain general deficit, the deficit is primarily located in the domain general systems such as the working memory, b) number sense deficit, the deficit is located in the innate approximate number system (ANS), c) numerosity coding deficit, the deficit is located to a exact number representation system, d) access deficit, the deficit is in the mapping between symbols and the innate number representational system (e. LÄS MER

5. 19. Adaptation and learning in postural control

   Författare :Fredrik Tjernström; Lund näs- och halssjukdomar Öron-; []
   Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Postural control; Adaptation; Learning; Sensory reweighting;

   Sammanfattning : The importance of the ability to use bipedal stance and gait in everyday life cannot be underestimated. Bipedal stance is learned during childhood and constantly adapted to changing circumstances throughout life. Failure to attain and maintain the control of upright posture can have catastrophic consequences. LÄS MER

7. 20. On the Utility of Representation Learning Algorithms for Myoelectric Interfacing

   Författare :Alexander Olsson; Avdelningen för Biomedicinsk teknik; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; EMG; Machine Learning; Deep Learning; Feature Learning; Biosignal Processing; Gesture Recognition; Muscle-Computer Interfaces; Myoelectric Control; Upper-Limb Prosthetics;

   Sammanfattning : Electrical activity produced by muscles during voluntary movement is a reflection of the firing patterns of relevant motor neurons and, by extension, the latent motor intent driving the movement. Once transduced via electromyography (EMG) and converted into digital form, this activity can be processed to provide an estimate of the original motor intent and is as such a feasible basis for non-invasive efferent neural interfacing. LÄS MER