Goto department of computing homepage



Dr. Derrick Takeshi Mirikitani PhD


Department of Computing
Goldsmiths College
University of London

Contact Information

Work

Department of Computing
Goldsmiths College
University of London
New Cross
London
SE14 6NW
United Kingdom

E-mail: D.T.Mirikitani@gold.ac.uk
Phone: 020 7919 7462

 

Home

Flat 6A
Dean House
347-351 New Cross Road
New Cross
London
SE14 6AT
United Kingdom

Doctoral Research

I have worked under the supervision of Dr Nikolay Nikolaev on the development of sequential training algorithms for recurrent neural networks. The research has led to my thesis, "Sequential recurrent connectionist algorithms for time series modeling of nonlinear dynamical systems" which was successfully defended on July 26, 2010.

Journal Publications
  • Derrick Takeshi Mirikitani, Nikolay Nikolaev: Nonlinear maximum likelihood estimation of electricity spot prices using recurrent neural networks. Neural Computing & Applications 20(1): 79-89 (2011)
  • Derrick Takeshi Mirikitani, Nikolay Nikolaev: Efficient online recurrent connectionist learning with the ensemble Kalman filter. Neurocomputing 73(4-6): 1024-1030 (2010)
Conference Publications
  • Nikolay Nikolaev, Derrick Takeshi Mirikitani, Evgueni Smirnov, Unscented grid filtering and elman recurrent networks. IJCNN 2010: 1-7
  • Derrick Takeshi Mirikitani, Lahcen Ouarbya: Modeling Dst with Recurrent EM Neural Networks. ICANN (1) 2009: 975-984
  • Lahcen Ouarbya, Derrick Takeshi Mirikitani: Modeling Geomagnetospheric Disturbances with Sequential Bayesian Recurrent Neural Networks. ICONIP (1) 2009: 91-99
  • Derrick Takeshi Mirikitani, Nikolay Nikolaev: Recurrent Expectation Maximization Neural Modeling. CIMCA/IAWTIC/ISE 2008: 674-679
  • Derrick Takeshi Mirikitani, Nikolay Nikolaev: Dynamic Modeling with Ensemble Kalman Filter Trained Recurrent Neural Networks. ICMLA 2008: 843-848
  • Incheon Park, Derrick Takeshi Mirikitani: Energy Reduction in Wireless Sensor Networks through Measurement Estimation with Second Order Recurrent Neural Networks. ICNS 2007: 103
  • Incheon Park, Derrick Takeshi Mirikitani, Mohammed Daoudi: Energy Reduction Through Nonlinear Forecasting of Sensor Measurements inWireless: Sensor Networks with Bayesian Recurrent Neural Filters. ICWN 2007: 97-103
  • Derrick Takeshi Mirikitani, Nikolay Nikolaev: Recursive Bayesian Levenberg-Marquardt Training of Recurrent Neural Networks. IJCNN 2007: 282-287
  • Derrick Takeshi Mirikitani, Ibrahim Kushchu E.Coli Search: Self Replicating Agents for Web Based Information Retrieval.IDEAL 2003: 622-629

Last Modified Wednesday 02, February 2011 11:42:27 GMT D.T.Mirikitani@gold.ac.uk