Deterministic convergence of complex mini-batch gradient learning algorithm for fully complex-valued neural networks

2020 ◽  
Vol 407 ◽  
pp. 185-193
Author(s):  
Huisheng Zhang ◽  
Ying Zhang ◽  
Shuai Zhu ◽  
Dongpo Xu
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Gradient Learning ◽  
Complex Valued

A new learning algorithm with logarithmic performance index for complex-valued neural networks

2009 ◽  
Vol 72 (16-18) ◽  
pp. 3771-3781 ◽  
Author(s):  
R. Savitha ◽  
S. Suresh ◽  
N. Sundararajan ◽  
P. Saratchandran
Keyword(s):  
Neural Networks ◽  
Performance Index ◽  
Learning Algorithm ◽  
New Learning ◽  
Complex Valued

Convergence of batch gradient learning algorithm with smoothing L1/2 regularization for Sigma–Pi–Sigma neural networks

2015 ◽  
Vol 151 ◽  
pp. 333-341 ◽  
Author(s):  
Yan Liu ◽  
Zhengxue Li ◽  
Dakun Yang ◽  
Kh.Sh. Mohamed ◽  
Jing Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Gradient Learning

Particle Swarm Optimization Technique for DNA Sensor Model Based Nanostructured Graphene

2014 ◽  
Vol 936 ◽  
pp. 415-418
Author(s):  
Vladimir Popov
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Optimization Technique ◽  
Dna Sensor ◽  
Dna Biosensors ◽  
Sensor Model ◽  
Particle Swarm Optimization Technique ◽  
Gradient Learning ◽  
Multilayer Perceptron Networks ◽  
Selection Of

DNA biosensors has received significant attention. In particular, we can mention the model of a graphene-based DNA sensor which is used for electrical detection of DNA molecules. In this paper, we consider a method of selection of PSO parameters for optimization of the analytical model of a graphene-based DNA sensor. In particular, we consider genetic algorithms, multilayer perceptron networks with gradient learning algorithm, recurrent neural networks with gradient learning algorithm, and 4-order Runge Kutta neural networks with different learning algorithms. Also, we present experimental results for different intelligent algorithms.

A L-BFGS Based Learning Algorithm for Complex-Valued Feedforward Neural Networks

2017 ◽  
Vol 47 (3) ◽  
pp. 1271-1284 ◽  
Author(s):  
Rongrong Wu ◽  
He Huang ◽  
Xusheng Qian ◽  
Tingwen Huang
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Feedforward Neural Networks ◽  
Complex Valued

Particle Swarm Optimization Technique for Task-Resource Scheduling for Robotic Clouds

2014 ◽  
Vol 565 ◽  
pp. 243-246 ◽  
Author(s):  
Vladimir Popov
Keyword(s):  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Learning Algorithm ◽  
Optimization Technique ◽  
Particle Swarm ◽  
Resource Scheduling ◽  
Scheduling Problem ◽  
Swarm Optimization ◽  
Particle Swarm Optimization Technique ◽  
Gradient Learning

The task-resource scheduling problem is one of the fundamental problems for cloud computing. There are a large number of heuristics based approaches to various scheduling workflow applications. In this paper, we consider the problem for robotic clouds. We propose new method of selection of parameters of a particle swarm optimization algorithm for solution of the task-resource scheduling problem for robotic clouds. In particular, for the prediction of values of the inertia weight we consider genetic algorithms, multilayer perceptron networks with gradient learning algorithm, recurrent neural networks with gradient learning algorithm, and 4-order Runge Kutta neural networks with different learning algorithms. Also, we present experimental results for different intelligent algorithms.

Sign in / Sign up

Export Citation Format

Share Document