Classification is one of the most important task in application areas of artificial neural networks (ANN).Training neural networks is a complex task in the supervised learning field of research. The main difficulty in adopting ANN is to find the most appropriate combination of learning, transfer and training function for the classification task. We compared the performances of three types of tr...

This chapter focuses on comparing the forecasting ability of the backpropagation neural network (BPNN) and the nonlinear autoregressive moving average with exogenous inputs (NARX) network trained with different algorithms; namely the quasi-Newton (Broyden-Fletcher-Goldfarb-Shanno, BFGS), conjugate gradient (Fletcher-Reeves update, Polak-Ribiére update, Powell-Beale restart), and Levenberg-Marqu...

In maximizing a non-linear function G(0), it is well known that the steepest descent method has a slow convergence rate. Here we propose a systematic procedure to obtain a 1-1 transformation on the variables 0, so that in the space of the transformed variables, the steepest descent method produces the solution faster. The final solution in the original space is obtained by taking the inverse tr...

We are concernedwith the nonnegative constraints optimization problems. It is well known that the conjugate gradientmethods are efficient methods for solving large-scale unconstrained optimization problems due to their simplicity and low storage. Combining the modified Polak-Ribière-Polyak method proposed by Zhang, Zhou, and Li with the Zoutendijk feasible direction method, we proposed a conjug...

diamondoids are cage-like saturated hydrocarbons consisting of fused cyclohexane rings. thediamondoids family of compounds is one of the best candidates for molecular building blocks (mbbs)in nanotechnology to construct organic nanostructures compared to other mbbs known so far. thechallenge is to find a route for self-assembly of these cage hydrocarbons and their applications in thebottom-up s...

This study aims to improve the mathematics learning outcomes of fifth grade students SDN 1 Bagik Polak Barat for 2021/2022 academic year through application Team Assisted Individualizatio model. The type research used is Classroom Action Research with 4 stages, namely, planning, implementation, observation and reflection. was conducted in 2 cycles, where each cycle consisted 3 meetings. subject...

Penelitian ini bertujuan untuk mengetahui ada tidaknya Pengaruh Model Pembelajaran Kooperatif Numbered Heads Together (NHT) dengan Bantuan Media Gambar Terhadap Hasil Belajar PKn Kelas IV SDN 1 Bagik Polak Barat Tahun Pelajaran 2021. Desain Grup. Populasi dalam penelitian adalah seluruh siswa kelas tahun ajaran 2021 yang terdiri dari dua yaitu IVA dan IVB. Teknik pengumpulan data tes hasil bela...

In this work, we propose non-linear conjugate gradient methods for finding critical points of vector-valued functions with respect to the partial order induced by a closed, convex, and pointed cone with non-empty interior. No convexity assumption is made on the objectives. The concepts of Wolfe and Zoutendjik conditions are extended for the vectorvalued optimization. In particular, we show that...