Mehdi Fatemi
Mehdi Fatemi
Researcher @ Microsoft Research
Verified email at microsoft.com - Homepage
Title
Cited by
Cited by
Year
Cognitive Control
S Haykin, M Fatemi, P Setoodeh, Y Xue
IEEE, 2012
478*2012
Hybrid reward architecture for reinforcement learning
H Van Seijen, M Fatemi, J Romoff, R Laroche, T Barnes, J Tsang
Advances in Neural Information Processing Systems, 5392-5402, 2017
1312017
Policy networks with two-stage training for dialogue systems
M Fatemi, LE Asri, H Schulz, J He, K Suleman
arXiv preprint arXiv:1606.03152, 2016
772016
Cognitive control: Theory and application
M Fatemi, S Haykin
IEEE Access 2, 698-710, 2014
502014
Multi-advisor reinforcement learning
R Laroche, M Fatemi, J Romoff, H van Seijen
arXiv preprint arXiv:1704.00756, 2017
132017
Separation of concerns in reinforcement learning
H van Seijen, M Fatemi, J Romoff, R Laroche
arXiv preprint arXiv:1612.05159, 2016
10*2016
Observability of stochastic complex networks under the supervision of cognitive dynamic systems
M Fatemi, P Setoodeh, S Haykin
Journal of Complex Networks 5 (3), 433-460, 2017
92017
Cognitive control in cognitive dynamic systems: a new way of thinking inspired by the brain
S Haykin, A Amiri, M Fatemi
2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement …, 2014
62014
Discrete event control of an unmanned aircraft
M Fatemi, J Millan, J Stevenson, T Yu, S O'Young
2008 9th International Workshop on Discrete Event Systems, 352-357, 2008
62008
Post-training on RBF neural networks
F Shabaninia, M Roopaei, M Fatemi
Nonlinear Analysis: Hybrid Systems 1 (4), 491-500, 2007
52007
Using a logarithmic mapping to enable lower discount factors in reinforcement learning
H Van Seijen, M Fatemi, A Tavakoli
Advances in Neural Information Processing Systems, 14134-14144, 2019
42019
Dead-ends and Secure Exploration in Reinforcement Learning
M Fatemi, S Sharma, H Van Seijen, SE Kahou
International Conference on Machine Learning, 1873-1881, 2019
22019
New Training Methods for RBF Neural Networks
M Fatemi, M Roopaei, F Shabaninia
2005 International Conference on Neural Networks and Brain 3, 1322-1327, 2005
22005
About the attractor phenomenon in decomposed reinforcement learning
R Laroche, M Fatemi, J Romoff, H van Seijen
2018
Toward a general control design paradigm for hybrid systems: Ideas, concepts, and formulations
M Fatemi, J Millan, T Yu, S O'Young
2009 Canadian Conference on Electrical and Computer Engineering, 1158-1162, 2009
2009
Unmanned Aerial Vehicles:“Sense and Avoid” Problem
M Fatemi, J Millan, J Stevenson, S O’Young, T Yu
IEEE Newfoundland and Labrador, 180 Portugal Road, Holiday Inn, St. John's …, 2008
2008
Intrinsic Error Sources of Neural Networks
M Fatemi, M Roopaei, H Roopaei
2006 IEEE International Conference on Engineering of Intelligent Systems, 1-6, 2006
2006
New enhanced methods for radial basis function neural networks in function approximation
M Fatemi, M Roopaei, F Shabaninia
Fifth International Conference on Hybrid Intelligent Systems (HIS'05), 4 pp., 2005
2005
The system can't perform the operation now. Try again later.
Articles 1–18