In this paper we derive a supervised learning algorithm for a spiking neural network which encodes information in the timing of spike trains. This algorithm is similar to the classical error back propagation algorithm for sigmoidal neural network but the learning parameter is adaptively changed. The algorithm is applied to the complex nonlinear classification problem and the results show that t...

Recurrent neural networks (RNNs) trained with gradient-based algorithms such as real-time recurrent learning or back-propagation through time have a drawback of slow convergence rate. These algorithms also need the derivative calculation through the error back-propagation process. In this paper, a derivative-free Kalman filter, so called the unscented Kalman filter (UKF), for training a fully c...

This paper presents a comparison study between the multilayer perceptron (MLP) and radial basis function (RBF) neural networks with supervised learning and back propagation algorithm to track hand gestures. Both networks have two output classes which are hand and face. Skin is detected by a regional based algorithm in the image, and then networks are applied on video sequences frame by frame in...

We propose that the back propagation algorithm for supervised learning can be generalized, put on a satisfactory conceptual footing, and very likely made more efficient by defining the values of the output and input neurons as probabilities and varying the synaptic weights in the gradient direction of the log likelihood, rather than the 'error'. In the past thirty years many researchers have st...

We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the target or prediction error is revealed). Although this algorithm computes the gradient of an objective function just like Backpropagation, it does not need ...

Focused on the issue that conventional remote sensing image classification methods have run into the bottlenecks in accuracy, a new remote sensing image classification method inspired by deep learning is proposed, which is based on Stacked Denoising Autoencoder. First, the deep network model is built through the stacked layers of Denoising Autoencoder. Then, with noised input, the unsupervised ...

In this paper, we adapt the classical learning algorithm for feed-forward neural networks when monotonicity is required in the inputoutput mapping. Monotonicity can be imposed by adding of suitable penalization terms to the error function. This yields a computationally efficient algorithm with little overhead compared to back-propagation. This algorithm is used to train neural networks for dela...

Nowadays cancer has become huge threat in human life. There are many types of cancer, Lung cancer is one of the common types causing very high mortality rate. The best way of protection from lung cancer is its early detection and diagnoses. With the fast development of the technology of computed tomography (CT) technology, medical test images become one of the most efficient examination methods...

An improved complex-valued back propagation neural network (ICVBPNN) algorithm is proposed in this paper. In allusion to the defect of gradient descent of traditional complex-valued back propagation network (CVBPNN) algorithm, additive momentum has been introduced. It is used for time-varying channel tracking and prediction in wireless communication system and better application results are acq...