COVID-19 caused by the coronavirus disease-2019 has spread rapidly and attacked massively. As a precaution, lockdown policy was issued. This limits activities of schools, offices, shops, prohibits traveling at certain times, maintains distance from one another reduces crowds in public. During period resulted new lifestyle where use smartphones increased. increase is based on fact that have many...

An efficient technique namely Backpropagation training with adaptive parameters using Lyapunov Stability Theory for training single hidden layer feed forward network is proposed. A three-layered Feedforward neural network architecture is used to solve the selected problems. Sequential Training Mode is used to train the network. Lyapunov stability theory is employed to ensure the faster and stea...

We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size limitation of explicit gradient descent, which poses an impediment for optimization. ProxProp is developed from a general point of view on the backpropagation algori...

In this paper we discuss the asymptotic properties of the most commonly used variant of the backpropagation algorithm in which network weights are trained by means of a local gradient descent on examples drawn randomly from a fixed training set, and the learning rate TJ of the gradient updates is held constant (simple backpropagation). Using stochastic approximation results, we show that for TJ...

Recurrent Backpropagation and Equilibrium Propagation are algorithms for fixed point recurrent neural networks which differ in their second phase. In the first phase, both algorithms converge to a fixed point which corresponds to the configuration where the prediction is made. In the second phase, Recurrent Backpropagation computes error derivatives whereas Equilibrium Propagation relaxes to an...

Deep neural networks are powerful parametric models that can be trained efficiently using the backpropagation algorithm. Stochastic neural networks combine the power of large parametric functions with that of graphical models, which makes it possible to learn very complex distributions. However, as backpropagation is not directly applicable to stochastic networks that include discrete sampling ...

The manual parking system allows for errors in recording, the service takes a long time, and there is no history of vehicle users. license plate recognition designed as an alternative that more accurate fast service, presence user data. Vehicle has been equipped with Backpropagation Artificial Neural Network (ANN). advance goes through image processing process grayscale, black white, segmentati...