Sökning: "temporal sequence learning"

Visar resultat 1 - 5 av 12 avhandlingar innehållade orden temporal sequence learning.

1. 1. Spike-Based Bayesian-Hebbian Learning in Cortical and Subcortical Microcircuits

   Författare :Philip Tully; Anders Lansner; Matthias Hennig; Gordon Pipa; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Bayes rule; synaptic plasticity and memory modeling; intrinsic excitability; naïve Bayes classifier; spiking neural networks; Hebbian learning; neuromorphic engineering; reinforcement learning; temporal sequence learning; attractor network; Computer Science; Datalogi;

   Sammanfattning : Cortical and subcortical microcircuits are continuously modified throughout life. Despite ongoing changes these networks stubbornly maintain their functions, which persist although destabilizing synaptic and nonsynaptic mechanisms should ostensibly propel them towards runaway excitation or quiescence. LÄS MER

3. 2. Cognition reversed : Robot learning from demonstration

   Författare :Erik Billing; Lars Erik Janlert; Thomas Hellström; Tom Ziemke; Umeå universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Computer science; Datavetenskap; Cognitive science; Kognitionsvetenskap; computer and systems sciences; data- och systemvetenskap;

   Sammanfattning : The work presented in this thesis investigates techniques for learning from demonstration (LFD). LFD is a well established approach to robot learning, where a teacher demonstrates a behavior to a robot pupil. This thesis focuses on LFD where a human teacher demonstrates a behavior by controlling the robot via teleoperation. LÄS MER

4. 3. Deep Learning For Model-Based Multi-Object Tracking

   Författare :Juliano Pinto; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; multi-object smoothing; multi-object tracking; Deep learning; multi-object tracking performance measures;

   Sammanfattning : Multi-object tracking (MOT) is the task of estimating the state of multiple objects based on noisy sensor measurements. MOT is essential in various applications, such as pedestrian monitoring, vehicle tracking, animal behavior analysis, and others. LÄS MER

5. 4. Z-Series : Mining and learning from complex sequential data

   Författare :Zed Lee; Panagiotis Papapetrou; Tony Lindgren; Toon Calders; Stockholms universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; data- och systemvetenskap; Computer and Systems Sciences;

   Sammanfattning : The amount and complexity of sequential data collected across various domains have grown rapidly, posing significant challenges for extracting useful knowledge from such data sources. The complexity arises from diverse sequence representations with varying granularities, such as multivariate time series, histogram snapshots, and heterogeneous health records, which often describe a single data instance with multiple sequences. LÄS MER

7. 5. Motion estimation for perceptual image sequence coding

   Författare :Kenneth Andersson; Håkon Husøy; Linköpings universitet; []
   Nyckelord :MEDICINE; MEDICIN;

   Sammanfattning : Since the advent of television obtaining high perceived quality using a limited bandwidth has been an important issue. This thesis proposes new methods for exploitation of temporal and perceptual redundancy in image sequences to achieve lower coding rate and/or higher visual quality. LÄS MER