On the hardness of parameter optimization of convolution neural networks using genetic algorithm and machine learning

2018 ◽  
Author(s):  
Hyeon-Chang Lee ◽  
Dong-Pil Yu ◽  
Yong-Hyuk Kim
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Neural Networks ◽  
Parameter Optimization ◽  
Convolution Neural Networks

scholarly journals Predicting the Crop Type and Region of Abundance using Machine Learning

2021 ◽  
Vol 9 (9) ◽  
pp. 1411-1416
Author(s):  
Mohd Khalid Shaikh
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Rural Area ◽  
Identification System ◽  
Plant Identification ◽  
Convolution Neural Networks ◽  
Technology Students ◽  
Modern Age ◽  
Crop Type ◽  
As If

Abstract: In this modern age of science too technology, students and people in big cities ignorance of many things, such as how we get food, how things are processed, and much more. We are just it focuses on the results we get, because of this morality our knowledge diminishes, as if we did not know the crops or the goods ourselves using. As we visit the rural area when we arrive beyond some kind of plant, we can't know that, so we have identified this place to resolve the problem of students, researchers and many more people by creating a plant identification system which will predict the type of crop and the location of abundance where the harvest is planted. Keywords: Crop Identification System, Convolution Neural networks, MobilenetV2.

Hyper-Parameter Optimization by Using the Genetic Algorithm for Upper Limb Activities Recognition Based on Neural Networks

2021 ◽  
Vol 21 (2) ◽  
pp. 1877-1884
Author(s):  
Junjie Zhang ◽  
Guangmin Sun ◽  
Yuge Sun ◽  
Huijing Dou ◽  
Anas Bilal
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Parameter Optimization ◽  
Upper Limb

scholarly journals The Use of Neural Networks and Genetic Algorithms to Control Low Rigidity Shafts Machining

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4683
Author(s):  
Antoni Świć ◽  
Dariusz Wołos ◽  
Arkadiusz Gola ◽  
Grzegorz Kłosowski
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Genetic Algorithm ◽  
Neural Networks ◽  
Genetic Algorithms ◽  
Short Term Memory ◽  
Real Life ◽  
Control Process ◽  
Lstm Network ◽  
High Level

The article presents an original machine-learning-based automated approach for controlling the process of machining of low-rigidity shafts using artificial intelligence methods. Three models of hybrid controllers based on different types of neural networks and genetic algorithms were developed. In this study, an objective function optimized by a genetic algorithm was replaced with a neural network trained on real-life data. The task of the genetic algorithm is to select the optimal values of the input parameters of a neural network to ensure minimum deviation. Both input vector values and the neural network’s output values are real numbers, which means the problem under consideration is regressive. The performance of three types of neural networks was analyzed: a classic multilayer perceptron network, a nonlinear autoregressive network with exogenous input (NARX) prediction network, and a deep recurrent long short-term memory (LSTM) network. Algorithmic machine learning methods were used to achieve a high level of automation of the control process. By training the network on data from real measurements, we were able to control the reliability of the turning process, taking into account many factors that are usually overlooked during mathematical modelling. Positive results of the experiments confirm the effectiveness of the proposed method for controlling low-rigidity shaft turning.

scholarly journals Parking Assist using Convolution Neural Networks

2020 ◽  
Vol 9 (6) ◽  
pp. 248-252
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Transfer Learning ◽  
Waiting Time ◽  
Urban Areas ◽  
Parking Space ◽  
Convolution Neural Networks ◽  
Machine Learning Model ◽  
Parking System

Parking vehicles are one of the most frustrating tasks that people face these days. Locating an available parking space is a huge headache especially in urban areas. This paper aims to design one such parking system which, in many ways reduces the hassles of parking. The paper presents a system where a Machine Learning model, Convolution Neural Network(CNN) is used to classify parking slots in a parking space into vacant and filled slots. In order to optimize the task of classification, the method of Transfer Learning is implemented in the paper. The problem of parking stands not only limited to causing inconvenience to the drivers, but also escalates to much larger and extensive problems, affecting a lot more people the environment. Hence it is very important to have a system is used parking system in place. The model proposed in the paper sends across parking information to a driver well in advance, there by greatly reducing the waiting time for the vehicle.

scholarly journals The Tabu_Genetic Algorithm: A Novel Method for Hyper-Parameter Optimization of Learning Algorithms

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 579 ◽  
Author(s):  
Baosu Guo ◽  
Jingwen Hu ◽  
Wenwen Wu ◽  
Qingjin Peng ◽  
Fenghe Wu
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Parameter Optimization ◽  
Random Search ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Parameters Optimization ◽  
Bayesian Optimization ◽  
Learning Models ◽  
Machine Learning Models

Machine learning algorithms have been widely used to deal with a variety of practical problems such as computer vision and speech processing. But the performance of machine learning algorithms is primarily affected by their hyper-parameters, as without good hyper-parameter values the performance of these algorithms will be very poor. Unfortunately, for complex machine learning models like deep neural networks, it is very difficult to determine their hyper-parameters. Therefore, it is of great significance to develop an efficient algorithm for hyper-parameter automatic optimization. In this paper, a novel hyper-parameter optimization methodology is presented to combine the advantages of a Genetic Algorithm and Tabu Search to achieve the efficient search for hyper-parameters of learning algorithms. This method is defined as the Tabu_Genetic Algorithm. In order to verify the performance of the proposed algorithm, two sets of contrast experiments are conducted. The Tabu_Genetic Algorithm and other four methods are simultaneously used to search for good values of hyper-parameters of deep convolutional neural networks. Experimental results show that, compared to Random Search and Bayesian optimization methods, the proposed Tabu_Genetic Algorithm finds a better model in less time. Whether in a low-dimensional or high-dimensional space, the Tabu_Genetic Algorithm has better search capabilities as an effective method for finding the hyper-parameters of learning algorithms. The presented method in this paper provides a new solution for solving the hyper-parameters optimization problem of complex machine learning models, which will provide machine learning algorithms with better performance when solving practical problems.

Sign in / Sign up

Export Citation Format

Share Document