Three networks are compared for low false alarm stock trend predictions. Short-term trends, particularly attractive for neural network analysis, can be used profitably in scenarios such as option trading, but only with significant risk. Therefore, we focus on limiting false alarms, which improves the risk/reward ratio by preventing losses. To predict stock trends, we exploit time delay, recurrent, and probabilistic neural networks (TDNN, RNN, and PNN, respectively), utilizing conjugate gradient and multistream extended Kalman filter training for TDNN and RNN. We also discuss different predictability analysis techniques and perform an analysis of predictability based on a history of daily closing price. Our results indicate that all the networks are feasible, the primary preference being one of convenience.

/pdf/comparative-study-of-stock-trend-prediction-using-time-delay-43t3st4s0x.pdf

Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks

Recurrent neural network based prediction of epileptic seizures in intra- and extracranial EEG

Over the past years high-dimensional neural network potentials (HDNNPs), fitted to accurately reproduce ab initio potential energy surfaces, have become a powerful tool in chemistry, physics and ma...

Parallel Multistream Training of High-Dimensional Neural Network Potentials

Recurrent neural network-based approach for early recognition of Alzheimer's disease in EEG.

In this paper, an engine fault detection and classification technique using vibration data in the crank angle domain is presented. These data are used in conjunction with artificial neural networks (ANNs), which are applied to detect faults in a four-stroke gasoline engine built for experimentation. A comparative study is provided between the popular backpropagation (BP) method, the Levenberg–Marquardt (LM) method, the quasi-Newton (QN) method, the extended Kalman filter (EKF), and the smooth variable structure filter (SVSF). The SVSF is a relatively new estimation strategy, based on the sliding mode concept. It has been formulated to efficiently train ANNs and is consequently referred to as the SVSF-ANN. The accuracy of the proposed method is compared with the standard accuracy of the Kalman-based filters and the popular BP algorithms in an effort to validate the SVSF-ANN performance and application to engine fault detection and classification. The customizable fault diagnostic system is able to detect known engine faults with various degrees of severity, such as defective lash adjuster, piston chirp (PC), and chain tensioner (CT) problems. The technique can be used at any dealership or assembly plant to considerably reduce warranty costs for the company and manufacturer.

Automotive Internal-Combustion-Engine Fault Detection and Classification Using Artificial Neural Network Techniques

Kalman-filter-based training has been shown to be advantageous in many training applications. By its nature, extended Kalman filter (EKF) training is realized with instance-by-instance updates, rather than by performing updates at the end of a batch of training instances or patterns. Motivated originally by the desire to be able to base an update an a collection of instances, rather than just one, we recognized that the simple construct of multiple streams of training examples allows a batch-like update to be performed without violating an underlying principle of Kalman training, vis. that the approximate error covariance matrix remain consistent with the updates that have actually been performed. In this paper, we present this construct and show how it may be used to train robust controllers, i.e. controllers that perform well for a range of plants. >

Training controllers for robustness: multi-stream DEKF

We have recently established the feasibility of training recurrent neural networks by parameter-based decoupled extended Kalman filter (DEKF) algorithms for control of nonlinear dynamical systems. In this paper we investigate the use of truncated backpropagation through time (BPTT) for approximating the required dynamic derivatives that are used by the DEKF training algorithm. The use of this approximation allows the gradient calculations and weight updates by the DEKF algorithm to be performed asynchronously with application of control signals, thereby leading to a scalable, real-time, online training algorithm. We demonstrate in simulation the effectiveness of the BPTT-based DEKF algorithm for the problem of automotive engine idle speed control. >

L.A. Feldkamp

Papers

Training controllers for robustness: multi-stream DEKF

Truncated backpropagation through time and Kalman filter training for neurocontrol