scholarly journals Determining the optimal learning rate in gradient-based electromagnetic optimization using the Shanks transformation in the Lippmann–Schwinger formalism

2020 ◽  
Vol 45 (3) ◽  
pp. 595
Author(s):  
Salim Boutami ◽  
Nathan Zhao ◽  
Shanhui Fan
Keyword(s):  
Learning Rate ◽  
Optimal Learning ◽  
Gradient Based ◽  
Optimal Learning Rate

SIMULASI NEURAL NETWORK UNTUK PREDIKSI LOKASI USER PADA MOBILE NETWORK

2016 ◽  
Vol 9 (1) ◽  
Author(s):  
Alexander Driyarkoro ◽  
Nurain Silalahi ◽  
Joko Haryatno
Keyword(s):  
Neural Network ◽  
Mobile Station ◽  
Mobile Network ◽  
Learning Rate ◽  
Noise Factor ◽  
Optimal Learning ◽  
Air Interface ◽  
Location Area ◽  
Optimal Learning Rate

Prediksi lokasi user pada mobile network merupakan hal sangat penting, karena routing panggilan pada mobile station (MS) bergantung pada posisi MS saat itu. Mobilitas MS yang cukup tinggi, terutama di daerah perkotaan, menyebabkan pencarian (tracking) MS akan berpengaruh pada kinerja sistem mobile network, khususnya dalam hal efisiensi kanal kontrol pada air interface. Salah satu bentuk pencarian adalah dengan mengetahui perilaku gerakan yang menentukan posisi MS. Dari MSC/VLR dapat diketahui posisi MS pada waktu tertentu. Karena location area suatu MS selalu unik dari waktu ke waktu, dan hal itu merupakan perilaku (behaviour) MS, maka dapat dibuat profil pergerakannya. Dengan menggunakan Neural Network (NN) akan diperoleh location area MS pada masa yang akan datang. Model NN yang digunakan pada penelitian ini adalah Propagasi Balik. Beberapa parameter NN yang diteliti dalam mempengaruhi kinerja prediksi lokasi user meliputi noise factor, momentum dan learning rate. Pada penelitian ini diperoleh nilai optimal learning rate = 0,5 dan noise factor = 1.

scholarly journals Learning rate optimisation of an image processing deep convolutional neural network

2021 ◽  
Author(s):  
◽  
Sibusiso Blessing Buthelezi
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Convolutional Neural Network ◽  
Model Performance ◽  
Learning Rate ◽  
Deep Convolutional Neural Network ◽  
Test Model ◽  
Optimal Learning ◽  
Model Average ◽  
Optimal Learning Rate

The major contribution of this dissertation is the proposal of the use of mathematical models to identify an optimal learning rate for an image processing deep convolutional neural network (DCNN). This model is derived from a nonlinear regression relationship between the learning rate and the accuracy of a test DCNN model. This relationship is meant to (A) resolve the problem of arbitrarily selecting the initial learning rate (B) reduce computational resource requirement and (C) reduce training instabilities. An algorithm is developed to analyse an inputted DCNN model and subsequently render output parameters that may be used to aid in the selection of an OLR. The benefit of an OLR includes improved training stability and reduced computational resources. The results rendered by the OLR algorithm proposes that an optimal learning rate improves model performance; this is described by the test model average accuracy of 91%. Furthermore, a model validation graph is also extrapolated. which will illustrate the mathematical model accuracy and the region of interest (ROI). The ROI defines the region in the learning rate spectrum with a positive effect on model performance.

Near Optimal Learning Rate BP Algorithm and its Application in Traffic Forecast

2011 ◽  
Vol 121-126 ◽  
pp. 4513-4517
Author(s):  
Li Ming Qin ◽  
Hai Tao Zhang
Keyword(s):  
Search Algorithm ◽  
Optimization Theory ◽  
Learning Rate ◽  
Bp Algorithm ◽  
Optimal Learning ◽  
One Dimensional ◽  
Traffic Forecast ◽  
Optimal Learning Rate

Aimed at the inadequacy of the standard BP algorithm, a near optimal learning rate BP algorithm (NOLRBP) is presented. Selecting the learning rate of the algorithm based on one-dimensional search algorithm of optimization theory avoids the blindness in determining the learning rate. Simulations show that the algorithm is superior to the standard BP algorithm (SDBP), momentum BP algorithm (MOBP) and variable learning rate BP algorithm (VLBP).

Sign in / Sign up

Export Citation Format

Share Document