An R implementation of a Recurrent Neural Network Trained by Extended Kalman Filter
Journal Title: Revista Romana de Statistica - Year 2016, Vol 64, Issue 2
Abstract
Nowadays there are several techniques used for forecasting with different performances and accuracies. One of the most performant techniques for time series prediction is neural networks. The accuracy of the predictions greatly depends on the network architecture and training method. In this paper we describe an R implementation of a recurrent neural network trained by the Extended Kalman Filter. For the implementation of the network we used the Matrix package that allows efficient vector-matrix and matrix-matrix operations. We tested the performance of our R implementation comparing it with a pure C++ implementation and we showed that R can achieve about 75% of the C++ programs. Considering the other advantages of R, our results recommend R as a serious alternative to classical programming languages for high performance implementations of neural networks.
Authors and Affiliations
Bogdan Oancea, Tudorel Andrei, Raluca Mariana Dragoescu
Keywords
Related Articles
- EP ID EP138936
- DOI -
- Views 130
- Downloads 0
Evaluation of Corporate Governance Influence on Performance of roumanian Companies
The main purpose of this study is to examine the impact of the corporate governance mechanism on financial performance of the company. Previous research, largely conducted using international data, has suggested that bet...
METODE DE ANALIZĂ A RISCULUI DE FALIMENT
Aptitudinea unei întreprinderi de a fi solvabilă – de a învinge riscul de faliment, ocupă un loc central în Sistemul analizei financiar-patrimoniale. Orice dereglare privind achitarea obligaţiilor genereză prejudicii şi...
Financial Engineering Instruments Financed from European Structural and Investment Funds and Financial Products issued by Financial Institutions supporting European Project Implementation
At European level, the European Court of Auditors, in the Special Report No. April 2011 “The audit of the SME Guarantee” and Special Report no. 2 of 2012 “Financial instruments financed by the ERDF to support SMEs”, esta...
THE IMPACT OF GLOBAL AGING ON ASSET PRICES AND RETURNS
Numerous studies have tried to model the connection between the structure of population and the financial markets, showing the possibility of a future meltdown in the financial markets, via lower savings and investments...
VaR (Value at Risk) Model
The VaR model represents a significant progress in risk analysis, among the improvements it brings we can outline the attempt to measure risk itself in terms of an eventual loss, instead of focusing on gain-based approac...