The backpropagation algorithm, which had been originally introduced in the 1970s, is the workhorse of learning in neural networks. This backpropagation algorithm makes use of the famous machine learning algorithm known as Gradient Descent, which is a first-order iterative optimization algorithm for finding the minimum of a function. To find a local minimum of a function using gradient descent, ...

A vector matrix real time backpropagation algorithm for recurrent neural networks that approximate multi-valued periodic functions," Received Unlike feedforward neural networks (FFNN) which can act as universal function ap-proximators, recursive, or recurrent, neural networks can act as universal approximators for multi-valued functions. In this paper, a real time recursive backpropagation (RTR...

The artificial neural network is a popular framework in machine learning. To empower individual neurons, we recently suggested that the current type of neurons could be upgraded to second-order counterparts, in which the linear operation between inputs to a neuron and the associated weights is replaced with a nonlinear quadratic operation. A single second-order neurons already have a strong non...

Deriving gradient algorithms for time-dependent neural network structures typically requires numerous chain rule expansions, diligent bookkeeping, and careful manipulation of terms. In this paper, we show how to use the principle of Network Reciprocity to derive such algorithms via a set of simple block diagram manipulation rules. The approach provides a common framework to derive popular algor...

Most models for Information Retrieval (IR) using neural networks are simple spreading activation models. Some of them were successfully applied to real world document collections. Nevertheless, they do not exploit the subsymbolic paradigma of neural processing. In this paper a model using a simple backpropagation network for IR is proposed. The COSIMIR model implements the central process in IR...

Using the backpropagation algorithm, we have trained the feed forward neural network to pronounce Polish language, more precisely to translate Polish text into its phonematic counterpart. Depending on the input coding and network architecture, 88%-95% translation eeciency was achieved.

A new neural network architecture is proposed and applied in classification of data from multiple sources. The new arclhitecture is called a consensual neural network and its relation to hierarchical and ensemble neural networks is discussed. The consenr;ual neural nebwork architecture is based on statistical consensus theory and invol.ves using non-linearly transformed input data. The input da...

Bankruptcy prediction is an important classification problem for a business, and has become a major concern of managers. In this paper, two well-known backpropagation neural network models serving as data mining tools for classification problems are employed to perform bankruptcy forecasting: one is the backpropagation multi-layer perceptron, and the other is the radial basis function network. ...

The neural network is popular and used in many areas within the financial field, such as credit authorization screenings, regularities in security price movements, simulations of market behaviour, and so forth. In this research, the authors use a neural network technique for stock price forecasting of Great West Life, an insurance company based in Winnipeg, Canada. The Backpropagation algorithm...

Nonlinear system identification via Feedforward Neural Networks (FNN) and Digital Recurrent Network (DRN) is studied in this paper. The standard backpropagation algorithm is used to train the FNN. A dynamic backpropagation algorithm is employed to adapt weights and biases of the DRN. The neural networks are trained using the identified error between the model’s output and plant’s output. Result...