, that the iterative improvement approach is generic in that it is possible

and to networks used to classify handprinted numeral image data. The improvement of the iterative technique over classical de-sign approaches is clearly demonstrated.

The trigonometric network, introduced in this paper, is a multilayer feedforward neural network with sinusoidal activation functions. Unlike the N-dimensional Fourier series, the basis functions of the proposed trigonometric network have no strict harmonic relationship. An effective training algorithm for the network is developed. It is shown that the trigonometric network performs better than the sigmoidal neural network for some data sets. A pruning method based on the modified Gram-Schmidt orthogonalization procedure is presented to detect and prune useless hidden units. Other network architectures related to the trigonometric network, such as the sine network, are shown to be inferior to the network proposed in this paper. I. Introduction The trigonometric feedforward neural network proposed in this paper has both sine and cosine activations for each hidden layer net function. Since the derivative of the activations for the net function are never simultaneously zero, the hope is...

-Raphson iteration. Our technique is faster because it examines far fewer potential matches between the images than existing techniques. Furthermore, this registration technique can be generalized to handle rotation, scaling and shearing. We show show our technique can be adapted for use in a stereo vision system. 2

We consider the class of Iterative Shrinkage-Thresholding Algorithms (ISTA) for solving linear inverse problems arising in signal/image processing. This class of methods is attractive due to its simplicity, however, they are also known to converge quite slowly. In this paper we present a Fast

Abstract- Iterative decoding of two-dimensional systematic convolutional codes has been termed “turbo ” (de)coding. Using log-likelihood algebra, we show that any decoder can he used which accepts soft inputs-including a priori values-and delivers soft outputs that can he split into three terms

We propose a new approach to reinforcement learning for control problems which combines value-function approximation with linear architectures and approximate policy iteration. This new approach

, which is required for environment modeling (e.g., building a Digital Elevation Map). Objects are represented by a set of 3-D points, which are considered as the samples of a surface. No constraint is imposed on the form of the objects. The proposed algorithm is based on iteratively matching points

Abstract not found

ABSTRACT. We present a new algorithm for a fast iterative improvement of the shallow-ice approximation (SIA) for the modeling of glacier flow. Based on the traditional SIA scaling assumptions, the solution of the Stokes problem is found by an operator-splitting iterative technique. The SIA solution