Markov logic networks (MLNs) combine Markov networks and first-order logic, and are a powerful and increasingly popular representation for statistical relational learning. The state-of-the-art method for discriminative learning of MLN weights is the voted perceptron algorithm, which is essentially gradient descent with an MPE approximation to the expected sufficient statistics (true clause coun...

Nonlinear PCA type learning has been recently suggested for signal subspace decomposition and sinusoidal frequencies tracking, which outperformed the linear PCA based methods and traditional least squares algorithms. Currently, nonlinear PCA algorithms are directly generalized from linear ones that based on gradient descent (GD) technique. The convergence behavior of gradient descent is depende...

The popular multiplicative algorithms in non-negative matrix factorization (NMF) are known to have slow convergence. Several algorithms have been proposed to improve the convergence of iterative algorithms in NMF, such as the projected gradient algorithms. However, these algorithms also suffer a common problem, that is, a previously exploited descent direction may be searched again in subsequen...

In this article, we proposed two Conjugate Gradient (CG) parameters using the modified Dai–Liao condition and descent three-term CG search direction. Both are incorporated with projection technique for solving large-scale monotone nonlinear equations. Using Lipschitz assumptions, global convergence of methods has been proved. Finally, numerical results provided to illustrate robustness methods.

in this study it has been tried, to compare results and convergence rate of sensitivity analysis and conjugate gradient algorithms to reduce fuel consumption and increasing engine performance by optimizing the timing of opening and closing valves in xu7/l3 engine. in this study, considering the strength and accuracy of simulation gt-power software in researches on the internal combustion engine...

This paper reviews various optimization techniques available for training multi-layer perception (MLP) artificial neural networks for compression of images. These optimization techniques can be classified into two categories: Derivative-based and Derivative free optimization. The former is based on the calculation of gradient and includes Gradient Descent, Conjugate gradient, Quasi-Newton, Leve...

There have been some conjugate gradient methods with strong convergence but numerical instability and conversely‎. Improving these is an interesting idea to produce new both and‎‏ ‎numerical stability‎. ‎In this paper‎, ‎a hybrid method introduced based on the Fletcher ‎formula (CD) Liu Storey formula (LS) good results‎. ‎New directions satisfy sufficient descent property‎, ‎independent of line...

The Polak-Ribière-Polyak conjugate gradient algorithm is a useful tool of unconstrained numerical optimization. Efficient implementations of the algorithm usually perform line searches satisfying the strong Wolfe conditions. It is well known that these conditions do not guarantee that the successive computed directions are descent directions. This paper proposes a relaxation of the strong Wolfe...

in this paper, the artificial neural network (ann) approach is applied for forecasting groundwater level fluctuation in aghili plain,southwest iran. an optimal design is completed for the two hidden layers with four different algorithms: gradient descent withmomentum (gdm), levenberg marquardt (lm), resilient back propagation (rp), and scaled conjugate gradient (scg). rain,evaporation, relative...