Search

We investigate the effectiveness of a financial time-series forecasting strategy which exploits the multiresolution property of the wavelet transform. A financial series is decomposed into an over complete, shift invariant scale-related representation. In transform space, each individual wavelet series is modeled by a separate multilayer perceptron (MLP). We apply the Bayesian method of automatic relevance determination to choose short past windows (short-term history) for the inputs to the MLPs at lower scales and long past windows (long-term history) at higher scales. To form the overall forecast, the individual forecasts are then recombined by the linear reconstruction property of the inverse transform with the chosen autocorrelation shell representation, or by another perceptron which learns the weight of each scale in the prediction of the original time series. The forecast results are then passed to a money management system to generate trades.

The adaptive-subspace self-organizing map (ASSOM) proposed by Kohonen is a recent development in self-organizing map (SOM) computation. In this paper, we propose a method to realize ASSOM using a neural learning algorithm in nonlinear autoencoder networks. Our method has the advantage of numerical stability. We have applied our ASSOM model to build a modular classification system for handwritten digit recognition. Ten ASSOM modules are used to capture different features in the ten classes of digits. When a test digit is presented to all the modules, each module provides a reconstructed pattern and the system outputs a class label by comparing the ten reconstruction errors. Our experiments show promising results. For relatively small size modules, the classification accuracy reaches 99.3% on the training set and over 97% on the testing set.

The design, implementation, and operation of a low-power multilayer perceptron chip (Kakadu) in the framework of a cardiac arrhythmia classification system is presented in this paper. This classifier, called MATIC, makes timing decisions using a decision tree, and a neural network is used to identify heartbeats with abnormal morphologies. This classifier was designed to be suitable for use in implantable devices and a VLSI (very large scale integration) neural-network chip (Kakadu) was designed so that the computationally expensive neural-network algorithm can be implemented with low power consumption. Kakadu implements a (10,6,4) perceptron and has a typical power consumption of tens of microwatts. When used with the arrhythmia classification system, the chip can operate with an average power consumption of less than 25 nW.

Block layout dimension prediction is an important activity in many very large scale integration computer-aided design tasks, among them structural synthesis, floor planning and physical synthesis. Block layout dimension prediction is harder than block area prediction and has been previously considered to be intractable. The authors present a solution to this problem using a neural network machine learning approach. The method uses a neural network to predict first the number of contacts; then another neural network uses this prediction and other circuit features to predict the width and the height of its layout. The approach has produced much better results than those published-a dimension (aspect ratio) prediction average error of less than 18% with a corresponding area prediction average error of less than 15%. Furthermore, the technique predicts the number of contacts in a circuit with less than 4% error on average.

A statistical quantization model is used to analyze the effects of quantization when digital techniques are used to implement a real-valued feedforward multilayer neural network. In this process, a parameter called the effective nonlinearity coefficient, which is important in the studying of quantization effects, is introduced. General statistical formulations of the performance degradation of the neural network caused by quantization are developed as functions of the quantization parameters. The formulations predict that the network's performance degradation gets worse when the number of bits is decreased; that a change of the number of hidden units in a layer has no effect on the degradation; that for a constant effective nonlinearity coefficient and number of bits, an increase in the number of layers leads to worse performance degradation; and the number of bits in successive layers can be reduced if the neurons of the lower layer are nonlinear.