scholarly journals Validation of Large-Scale Classification Problem in Dendritic Neuron Model Using Particle Antagonism Mechanism

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 792
Author(s):  
Dongbao Jia ◽  
Yuka Fujishita ◽  
Cunhua Li ◽  
Yuki Todo ◽  
Hongwei Dai
Keyword(s):  
Execution Time ◽  
Large Scale ◽  
Neuron Model ◽  
Learning Algorithms ◽  
Back Propagation ◽  
Nonlinear Problems ◽  
Middle Layer ◽  
Small Scale ◽  
Classification Problems ◽  
Scale Classification

With the characteristics of simple structure and low cost, the dendritic neuron model (DNM) is used as a neuron model to solve complex problems such as nonlinear problems for achieving high-precision models. Although the DNM obtains higher accuracy and effectiveness than the middle layer of the multilayer perceptron in small-scale classification problems, there are no examples that apply it to large-scale classification problems. To achieve better performance for solving practical problems, an approximate Newton-type method-neural network with random weights for the comparison; and three learning algorithms including back-propagation (BP), biogeography-based optimization (BBO), and a competitive swarm optimizer (CSO) are used in the DNM in this experiment. Moreover, three classification problems are solved by using the above learning algorithms to verify their precision and effectiveness in large-scale classification problems. As a consequence, in the case of execution time, DNM + BP is the optimum; DNM + CSO is the best in terms of both accuracy stability and execution time; and considering the stability of comprehensive performance and the convergence rate, DNM + BBO is a wise choice.

Reverberation Intensity Decaying in Range-Dependent Waveguide

2019 ◽  
Vol 27 (03) ◽  
pp. 1950007
Author(s):  
J. R. Wu ◽  
T. F. Gao ◽  
E. C. Shang
Keyword(s):  
Large Scale ◽  
Back Propagation ◽  
Normal Modes ◽  
Small Scale ◽  
Signal Pulse ◽  
First Order ◽  
Orthogonal Property ◽  
Short Signal ◽  
Scale Roughness ◽  
Special Case

In this paper, an analytic range-independent reverberation model based on the first-order perturbation theory is extended to range-dependent waveguide. This model considers the effect of bottom composite roughness: small-scale bottom rough surface provides dominating energy for reverberation, whereas large-scale roughness has the effect of forward and back propagation. For slowly varying bottom and short signal pulse, analytic small-scale roughness backscattering theory is adapted in range-dependent waveguides. A parabolic equation is used to calculate Green functions in range-dependent waveguides, and the orthogonal property of local normal modes is employed to estimate the modal spectrum of PE field. Synthetic tests demonstrate that the proposed reverberation model works well, and it can also predict the reverberation of range-independent waveguide as a special case.

Incremental conic functions algorithm for large scale classification problems

2018 ◽  
Vol 77 ◽  
pp. 187-194 ◽  
Author(s):  
Emre Cimen ◽  
Gurkan Ozturk ◽  
Omer Nezih Gerek
Keyword(s):  
Large Scale ◽  
Classification Problems ◽  
Scale Classification

COMBINED NEURAL-NET/KNOWLEDGE-BASED ADAPTIVE SYSTEMS FOR LARGE SCALE DYNAMIC CONTROL

1991 ◽  
Vol 05 (04) ◽  
pp. 503-522 ◽  
Author(s):  
ALISTAIR D. C. HOLDEN ◽  
STEVEN C. SUDDARTH
Keyword(s):  
Adaptive Systems ◽  
Large Scale ◽  
Dynamic Control ◽  
Back Propagation ◽  
Computation Time ◽  
Neural Nets ◽  
Small Scale ◽  
Neural Net ◽  
Training Time ◽  
Knowledge Based

The control of small-scale systems using either knowledge-based or neural net methods is quite feasible. Large scale systems, however, introduce complexities in modeling and excessive computation time. This paper attacks these difficulties by breaking down the problem into a hierarchy of control contexts. The lowest level of this hierarchy is implemented as rule sets and/or neural networks. A method using "hints" is shown to greatly reduce training time in back-propagation neural nets.

IMPLEMENTING BACK-PROPAGATION- THROUGH-TIME LEARNING ALGORITHM USING CELLULAR NEURAL NETWORKS

1999 ◽  
Vol 09 (06) ◽  
pp. 1041-1074 ◽  
Author(s):  
TAO YANG ◽  
LEON O. CHUA
Keyword(s):  
Real Time ◽  
Time Complexity ◽  
Large Scale ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Back Propagation ◽  
Cellular Neural Network ◽  
Small Scale ◽  
Von Neumann ◽  
On Line

In a programmable (multistage) cellular neural network (CNN) structure, the CPU is a CNN universal chip which supports massively parallel computations on patterns and images, including videos. In this paper, we decompose the structure of a class of simultaneous recurrent networks (SRN) into a CNN program and run it on a von Neumann-like stored program CNN structure. To train the SRN, we map the back-propagation-through-time (BTT) learning algorithm into a sequence of CNN subroutines to achieve real-time performance via a CNN universal chip. By computing in parallel, the CNN universal chip can be programmed to implement in real time the BTT learning algorithm, which has a very high time complexity. An estimate of the time complexity of the BTT learning algorithm based on the CNN universal chip is presented. For small-scale problems, our simulation results show that a CNN implementation of the BTT learning algorithm for a two-dimensional SRN is at least 10,000 times faster than that based on state-of-the-art sequential workstations. For the few large-scale problems which we have so far simulated, the CNN implemented BTT learning algorithm maintained virtually the same time complexity with a learning time of a few seconds, while those implemented on state-of-the-art sequential workstations dramatically increased their time complexity, often requiring several days of running time. Several examples are presented to demonstrate how efficiently a CNN universal chip can speed up the learning algorithm for both off-line and on-line applications.

scholarly journals Research on the Application of Machine Learning Algorithms in Credit Risk Assessment of Minor Enterprises

CONVERTER ◽  
2021 ◽  
pp. 696-706
Author(s):  
Huichao Mi
Keyword(s):  
Machine Learning ◽  
Credit Risk ◽  
Industrial Development ◽  
Large Scale ◽  
Manufacturing Industry ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Small Scale ◽  
Scale Data

Under the influence of COVID-19, minor enterprises, especially the manufacturing industry, are facing greater financial pressure and the possibility of non-performing loans is increasing. It is very important for financial institutions to reduce financial risks while providing financial support for minor enterprises to promote industrial development and economic recovery. In order to understand the function of machine learning algorithms in predicting enterprise credit risk, the research designs five models, including Logistic Regression, Decision Tree, Naïve Bayesian, Support Vector Machine and Deep Neural Network, and adopts SMOTE and Undersampling to process imbalanced data. Experiments show that machine learning algorithms have high accuracy for both large-scale data and small-scale data.

Sign in / Sign up

Export Citation Format

Share Document