Derrick Takeshi Mirikitani

Learn More
This paper develops a probabilistic approach to recursive second-order training of recurrent neural networks (RNNs) for improved time-series modeling. A general recursive Bayesian Levenberg-Marquardt algorithm is derived to sequentially update the weights and the covariance (Hessian) matrix. The main strengths of the approach are a principled handling of(More)
Electricity spot prices are complex processes characterized by nonlinearity and extreme volatility. Previous work on nonlinear modeling of electricity spot prices has shown encouraging results, and we build on this area by proposing an Expectation Maximization algorithm for maximum likelihood estimation of recurrent neural networks utilizing the Kalman(More)
This paper develops a Bayesian approach to recursive second order training of recurrent neural networks. A general recursive Levenberg-Marquardt algorithm is elaborated using Bayesian regularization. Individual local regularization hyperparameters as well as an output noise hyper-parameter are reestimated in order to maximize the weight posterior(More)
The ensemble Kalman filter is a contemporary data assimilation algorithm used in the geoscience community. The filters popularity most likely stems from its simplicity, its low computational cost, and its superior performance over the extended Kalman filter in strongly nonlinear high dimensional assimilation tasks. Due to its attractive characteristics we(More)
Wireless sensor networks are real time databases to real world phenomena. As wireless sensor networks (WSNs) generally rely on batteries for power, the nodes of the network have a limited operational lifetime. Efficient power consumption is of utmost importance in operation and maintenance of the network. This paper summarizes work in progress in efficient(More)
Although search engines are often used for information retrieval (IR) from the World Wide Web (WWW), current search engine technology seems obsolete. The quality of query results from today’s search engines is unacceptable, creating a demand for new information search and retrieval techniques. The conventional IR methods often lack the flexibility to adapt(More)
Dynamic reconstruction is fundamental to building models of nonlinear processes with unknown governing equations. Dynamic reconstruction attempts to reconstruct the underlying dynamics of the system under consideration from a series of scalar measurements over time. Reconstruction of system dynamics from measurements can be interpreted as an ill posed(More)
This paper develops an unscented grid-based filter for improved recurrent neural network modeling of time series. The filter approximates directly the weight posterior distribution as a linear mixture using deterministic unscented sampling. The weight posterior is obtained in one step, without linearisation through derivatives. An expectation maximisation(More)
A probabilistic approach to training recurrent neural networks is developed for maximum likelihood estimation of network weights, model uncertainty, and noise in the data. We elaborate on an Expectation Maximization algorithm where by a forward filtering backward smoothing framework is utilized for estimation of network weights in the Expectation step, and(More)