Følg
Hilbert Johan Kappen
Hilbert Johan Kappen
Verificeret mail på science.ru.nl - Startside
Titel
Citeret af
Citeret af
År
Optimal control as a graphical model inference problem
HJ Kappen, V Gómez, M Opper
Machine learning 87, 159-182, 2012
4142012
Path integrals and symmetry breaking for optimal control theory
HJ Kappen
Journal of statistical mechanics: theory and experiment 2005 (11), P11011, 2005
3942005
Linear theory for control of nonlinear stochastic systems
HJ Kappen
Physical review letters 95 (20), 200201, 2005
3372005
Sufficient conditions for convergence of the sum–product algorithm
JM Mooij, HJ Kappen
IEEE Transactions on Information Theory 53 (12), 4422-4437, 2007
3082007
Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
M Gheshlaghi Azar, R Munos, HJ Kappen
Machine learning 91, 325-349, 2013
2912013
On tempo tracking: Tempogram representation and Kalman filtering
AT Cemgil, B Kappen, P Desain, H Honing
Journal of New Music Research 29 (4), 259-273, 2000
2672000
Efficient learning in Boltzmann machines using linear response theory
HJ Kappen, FDB Rodríguez
Neural Computation 10 (5), 1137-1156, 1998
2411998
Efficient optical flow and stereo vision for velocity estimation and obstacle avoidance on an autonomous pocket drone
K McGuire, G De Croon, C De Wagter, K Tuyls, H Kappen
IEEE Robotics and Automation Letters 2 (2), 1070-1076, 2017
2322017
Minimal navigation solution for a swarm of tiny flying robots to explore an unknown environment
KN McGuire, C De Wagter, K Tuyls, HJ Kappen, GCHE de Croon
Science Robotics 4 (35), eaaw9710, 2019
2182019
Learning processes in neural networks
TM Heskes, B Kappen
Physical Review A 44 (4), 2718, 1991
1801991
A generative model for music transcription
AT Cemgil, HJ Kappen, D Barber
IEEE Transactions on Audio, Speech, and Language Processing 14 (2), 679-694, 2006
1772006
An introduction to stochastic control theory, path integrals and reinforcement learning
HJ Kappen
AIP conference proceedings 887 (1), 149-181, 2007
1742007
Speedy Q-learning
MG Azar, R Munos, M Ghavamzadeh, H Kappen
Advances in neural information processing systems, ?, 2011
1592011
Dynamic policy programming
MG Azar, V Gómez, HJ Kappen
The Journal of Machine Learning Research 13 (1), 3207-3245, 2012
1522012
Monte Carlo methods for tempo tracking and rhythm quantization
AT Cemgil, B Kappen
Journal of Artificial Intelligence Research 18 (1), 45-81, 2003
1462003
Approximate inference and constrained optimization
T Heskes, K Albers, B Kappen
Uncertainty in Artificial Intelligence 13, 313-320, 2003
144*2003
Associative memory with dynamic synapses
L Pantic, JJ Torres, HJ Kappen, SCAM Gielen
Neural Computation 14 (12), 2903-2923, 2002
1392002
On-line learning processes in artificial neural networks
TM Heskes, B Kappen
North-Holland Mathematical Library 51, 199-233, 1993
1381993
Rhythm quantization for transcription
AT Cemgil, P Desain, B Kappen
Computer Music Journal 24 (2), 60-76, 2000
1352000
Adaptive importance sampling for control and inference
HJ Kappen, HC Ruiz
Journal of Statistical Physics 162, 1244-1266, 2016
1202016
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–20