Robustness of deep neural networks is a critical issue in practical applications. In the general case feed-forward (including convolutional network architectures), under random noise attacks, we propose to study probability that output deviates from its nominal value by given threshold. We derive simple concentration inequality for propagation input uncertainty through using Cramer–Chernoff met...

Our study is about feed-forward neural network’s learning method. Generally, the method of improving its learning is focused on learning rate and moment term. We focus on sigmoid functions. Sigmoid functions are used for converting input signal into output signal and adjusting connection weight of learning in feed-forward neural network. We change gradient of sigmoid functions and investigate o...

Model-based control and monitoring such as feed-forward/feedback control, fault detection and isolation (FDI), and fault-tolerant control (FTC) techniques that utilize Lyapunov-based control laws are implemented on a high recovery reverse osmosis desalination plant model. A detailed mathematical model of a high recovery reverse osmosis plant is developed. This model incorporates the large spati...

production of highly viscous tar sand bitumen using steam assisted gravity drainage (sagd) with a pair of horizontal wells has advantages over conventional steam flooding. this paper explores the use of artificial neural networks (anns) as an alternative to the traditional sagd simulation approach. feed forward, multi-layered neural network meta-models are trained through the back-error-propaga...

An extended feed-forward algorithm for recurrent connectionist networks is presented. This algorithm, which works locally in time, is derived both for discrete-in-time networks and for continuous networks. Several standard gradient descent algorithms for connectionist networks (e.g. [48], [30], [28] [15], [34]), especially the backpropagation algorithm [36], are mathematically derived as a spec...

It is well known that Shannon's separation result does not hold under nite computation or nite delay constraints, thus joint source-channel coding is of great interest for practical reasons. For progressive source-channel coding systems, eecient codes have been proposed for feed forward channels 1] and the important problem of rate allocation between the source and channel codes has been solved...

This paper is an attempt to assess the potential and usefulness of ANN based modeling for evaporation prediction from a reservoir, where in classical and empirical equations failed to predict the evaporation accurately. The meteorological data set of daily pan evaporation, temperature, solar radiation, relative humidity, wind speed is used in this study. The performance of feed forward back pro...