A MIXED OPTIMIZATION METHOD BASED ON ARTIFICIAL INTELLIGENCE AND ITS APPLICATION

2015 ◽  
Vol 43 (4) ◽  
Author(s):  
Wu Deng ◽  
Huimin Zhao ◽  
Yinglian Luo ◽  
Xiumei Li
Keyword(s):  
Artificial Intelligence ◽  
Optimization Method ◽  
Mixed Optimization

scholarly journals An Adaptive Optimization Method Based on Learning Rate Schedule for Neural Networks

2021 ◽  
Vol 11 (2) ◽  
pp. 850
Author(s):  
Dokkyun Yi ◽  
Sangmin Ji ◽  
Jieun Park
Keyword(s):  
Artificial Intelligence ◽  
Cost Function ◽  
Numerical Experiments ◽  
Global Minimum ◽  
Optimization Method ◽  
Learning Method ◽  
Adaptive Optimization ◽  
The Cost ◽  
Proof Of Convergence ◽  
Learning Data

Artificial intelligence (AI) is achieved by optimizing the cost function constructed from learning data. Changing the parameters in the cost function is an AI learning process (or AI learning for convenience). If AI learning is well performed, then the value of the cost function is the global minimum. In order to obtain the well-learned AI learning, the parameter should be no change in the value of the cost function at the global minimum. One useful optimization method is the momentum method; however, the momentum method has difficulty stopping the parameter when the value of the cost function satisfies the global minimum (non-stop problem). The proposed method is based on the momentum method. In order to solve the non-stop problem of the momentum method, we use the value of the cost function to our method. Therefore, as the learning method processes, the mechanism in our method reduces the amount of change in the parameter by the effect of the value of the cost function. We verified the method through proof of convergence and numerical experiments with existing methods to ensure that the learning works well.

Analysis of regression prediction model of competitive sports based on SVM and artificial intelligence

2020 ◽  
Vol 39 (4) ◽  
pp. 5859-5869
Author(s):  
Jun Wang ◽  
Hongjun Qu
Keyword(s):  
Artificial Intelligence ◽  
Prediction Model ◽  
Optimization Method ◽  
Kernel Functions ◽  
Support Vector ◽  
Competitive Sports ◽  
Statistical Efficiency ◽  
Image Capture ◽  
Rbf Kernel ◽  
Speed Prediction

The training effect is not only affected by many environmental disturbance factors, but also related to various factors such as the athlete itself. In this paper, the author analyze the regression prediction model of competitive sports based on SVM and artificial intelligence. Traditional statistical modeling simply compares existing data between players and compares them between data. Moreover, it is unable to formulate corresponding tactical strategies according to the situation of the opponent, and targeted training to strengthen the level of individual sports skills.By com-paring the effects of several kernel functions on the SVM modeling side, it is found that the RBF kernel function can make the SVM’s prediction performance the best when dealing with the speed prediction problem. The experimental results show that this parameter optimization method can significantly improve the performance of the SVM regression machine. The prediction model based on support vector machine can effectively improve the prediction direction. Using artificial intelligence and image capture technology in sports can effectively improve the statistical efficiency and prediction effect of competition.

scholarly journals Milling of Graphene Reinforced Ti6Al4V Nanocomposites: An Artificial Intelligence Based Industry 4.0 Approach

Materials ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 5707
Author(s):  
Mustafa M. Nasr ◽  
Saqib Anwar ◽  
Ali M. Al-Samhan ◽  
Mageed Ghaleb ◽  
Abdulmajeed Dabwan
Keyword(s):  
Artificial Intelligence ◽  
Surface Roughness ◽  
Industry 4.0 ◽  
Cutting Speed ◽  
Optimization Method ◽  
Reinforcement Ratio ◽  
Swarm Optimization ◽  
Multi Objective ◽  
Feed Force ◽  
Matrix Nanocomposites

The studies about the effect of the graphene reinforcement ratio and machining parameters to improve the machining performance of Ti6Al4V alloy are still rare and incomplete to meet the Industry 4.0 manufacturing criteria. In this study, a hybrid adaptive neuro-fuzzy inference system (ANFIS) with a multi-objective particle swarm optimization method is developed to obtain the optimal combination of milling parameters and reinforcement ratio that lead to minimize the feed force, depth force, and surface roughness. For achieving this, Ti6Al4V matrix nanocomposites reinforced with 0 wt.%, 0.6 wt.%, and 1.2 wt.% graphene nanoplatelets (GNPs) are produced. Afterward, a full factorial approach was used to design experiments to investigate the effect of cutting speed, feed rate, and graphene nanoplatelets ratio on machining behaviour. After that, artificial intelligence based on ANFIS is used to develop prediction models as the fitness function of the multi-objective particle swarm optimization method. The experimental results showed that the developed models can obtain an accurate estimation of depth force, feed force, and surface roughness with a mean absolute percentage error of 3.87%, 8.56%, and 2.21%, respectively, as compared with experimentally measured outputs. In addition, the developed artificial intelligence models showed 361.24%, 35.05%, and 276.47% less errors for depth force, feed force, and surface roughness, respectively, as compared with the traditional mathematical models. The multi-objective optimization results from the new approach indicated that a cutting speed of 62 m/min, feed rate of 139 mm/min, and GNPs reinforcement ratio of 1.145 wt.% lead to the improved machining characteristics of GNPs reinforced Ti6Al4V matrix nanocomposites. Henceforth, the hybrid method as a novel artificial intelligent method can be used for optimizing the machining processes with complex relationships between the output responses.

Exploring the operation of a neural network using the example of handwritten digits recognition in an advanced informatics course using the python 3.8 programming language

2021 ◽  
pp. 21-29
Author(s):  
N. N. Samylkina ◽  
I. A. Kalinin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Image Processing ◽  
General Education ◽  
Programming Language ◽  
Loss Function ◽  
Optimization Method ◽  
Classification Problem ◽  
Hands On ◽  
Software Distribution

The article discusses the possibility of including artificial intelligence topics in the informatics course at the level of secondary general education on the demonstration example of handwritten digits recognition using the Python 3.8 programming language and the TensorFlow package. A hands-on example of a classification problem using the classic MNIST (Modified National Institute of Standards and Technology) training example set is dealt with step-by-step.Most of the tools required for the work (language interpreter, basic libraries, and shell) are downloaded in the form of a single software distribution kit of Anaconda. The network is trained using different methods. When the model is trained, the optimization method, the loss function, and the metric for estimation are specified. Image processing by convolutional nets containing special layers, which "convolve" the image the way a bitmap filter does, is also demonstrated

Comparative Study of Different Optimization Algorithms Used for Obtaining Diesel-Biodiesel Blends

2019 ◽  
Vol 70 (6) ◽  
pp. 1893-1896
Author(s):  
Stefan Sandru ◽  
Ion Onutu
Keyword(s):  
Artificial Intelligence ◽  
Genetic Algorithms ◽  
Linear Programming ◽  
Classical Method ◽  
Optimal Solution ◽  
Optimization Methods ◽  
Optimization Method ◽  
Biodiesel Blends ◽  
Dual Simplex ◽  
Linear Programming Problems

The purpose of this paper is to compare two different optimization methods, used in acquiring diesel-biodiesel blends. There were used five types of samples in order to enable the optimization of the final blend: there were chosen two types of hydrofined diesel fuel and there were synthesized three original types of biodiesel. The first optimization method used, dual simplex, is a classical method being used in solving linear programming problems. The second optimization method, the genetic algorithms, falls in the type of artificial intelligence algorithms, being an evolutionary method used when the problem requires searching an optimal solution in a great variety of valid solutions.

Sign in / Sign up

Export Citation Format

Share Document