Evolutionary Learning of a Box-Pushing Controller

2011 ◽  
pp. 104-121 ◽  
Author(s):  
Pieter Spronck ◽  
Ida Sprinkhuizen-Kuyper ◽  
Eric Postma ◽  
Rens Kortmann
Keyword(s):  
Neural Network ◽  
Evolutionary Algorithm ◽  
Fitness Function ◽  
Research Question ◽  
Initial Population ◽  
Evolutionary Learning ◽  
Main Research ◽  
The Neural Network ◽  
Starting Point ◽  
Good Starting Point

In our research we use evolutionary algorithms to evolve robot controllers for executing elementary behaviours. This chapter focuses on the behaviour of pushing a box between two walls. The main research question addressed in this chapter is: how can a neural network learn to control the box-pushing task using evolutionary-computation techniques? In answering this question we study the following three characteristics by means of simulation experiments: (1) the fitness function, (2) the neural network topology and (3) the parameters of the evolutionary algorithm. We find that appropriate choices for these characteristics are: (1) a global external fitness function, (2) a recurrent neural network, and (3) a regular evolutionary algorithm augmented with the doping technique in which the initial population is supplied with a solution to a hard task instance. We conclude by stating that our findings on the relatively simple box-pushing behaviour form a good starting point for the evolutionary learning of more complex behaviours.

scholarly journals Visual Encoding and Decoding of the Human Brain Based on Shared Features

2020 ◽  
Author(s):  
Chao Li ◽  
Baolin Liu ◽  
Jianguo Wei
Keyword(s):  
Neural Network ◽  
Human Brain ◽  
Back Propagation ◽  
Brain Signals ◽  
Visual Encoding ◽  
Image Prior ◽  
The Neural Network ◽  
Starting Point ◽  
Good Starting Point ◽  
Deep Image

Using a convolutional neural network to build visual encoding and decoding models of the human brain is a good starting point for the study on relationship between deep learning and human visual cognitive mechanism. However, related studies have not fully considered their differences. In this paper, we assume that only a portion of neural network features is directly related to human brain signals, which we call shared features. In the encoding process, we extract shared features from the lower and higher layers of the neural network, and then build a non-negative sparse map to predict brain activities. In the decoding process, we use back-propagation to reconstruct visual stimuli, and use dictionary learning and a deep image prior to improve the robustness and accuracy of the algorithm. Experiments on a public fMRI dataset confirm the rationality of the encoding models, and comparing with a recently proposed method, our reconstruction results obtain significantly higher accuracy.

Research on the Optimized Algorithms on Neural Network

2012 ◽  
Vol 605-607 ◽  
pp. 2175-2178
Author(s):  
Xiao Qin Wu
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Simulated Annealing Algorithm ◽  
Fitness Function ◽  
Strong Stability ◽  
Training Algorithm ◽  
Network Training ◽  
The Neural Network ◽  
Annealing Algorithm ◽  
Proper Operation

In order to overcome the disadvantage of neural networks that their structure and parameters were decided stochastically or by one’s experience, an improved BP neural network training algorithm based on genetic algorithm was proposed.In this paper,genetic algorithms and simulated annealing algorithm that optimizes neural network is proposed which is used to scale the fitness function and select the proper operation according to the expected value in the course of optimization,and the weights and thresholds of the neural network is optimized. This method is applied to the stock prediction system.The experimental results show that the proposed approach have high accuracy,strong stability and improved confidence.

scholarly journals Real-Time Brain-Machine Interface Achieves High-Velocity Prosthetic Finger Movements using a Biologically-Inspired Neural Network Decoder

2021 ◽  
Author(s):  
Matthew S. Willsey ◽  
Samuel R. Nason ◽  
Scott R. Ensel ◽  
Hisham Temmar ◽  
Matthew J. Mender ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Finger Movements ◽  
Feed Forward Neural Network ◽  
Current Standard ◽  
Biologically Inspired ◽  
Current State ◽  
The Neural Network ◽  
Starting Point ◽  
Prosthetic Finger

AbstractDespite the rapid progress and interest in brain-machine interfaces that restore motor function, the performance of prosthetic fingers and limbs has yet to mimic native function. The algorithm that converts brain signals to a control signal for the prosthetic device is one of the limitations in achieving rapid and realistic finger movements. To achieve more realistic finger movements, we developed a shallow feed-forward neural network, loosely inspired by the biological neural pathway, to decode real-time two-degree-of-freedom finger movements. Using a two-step training method, a recalibrated feedback intention–trained (ReFIT) neural network achieved a higher throughput with higher finger velocities and more natural appearing finger movements than the ReFIT Kalman filter, which represents the current standard. The neural network decoders introduced herein are the first to demonstrate real-time decoding of continuous movements at a level superior to the current state-of-the-art and could provide a starting point to using neural networks for the development of more naturalistic brain-controlled prostheses.

Human Identification System Research with the Electrocardiograms Based on the Neural Network

2014 ◽  
Vol 926-930 ◽  
pp. 1104-1107
Author(s):  
Jia Lun Lin
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Identification System ◽  
Frequency Noise ◽  
Ecg Signal ◽  
Feature Subset ◽  
Neural Network Classifier ◽  
Main Research ◽  
The Neural Network ◽  
Dna Algorithm

Based on existing researches at home and abroad, an intensive study of ECG signal preprocessing, feature extraction, feature analysis and feature weight analysis was made in the Paper neural network classifier was designed to realize the ECG identification and it was optimized by GA algorithm and DNA algorithm. The main research was concluded as follows. Firstly, extracting the preprocessing and feature of ECG signal. We have analyzed the frequency of ECG signal and the noise signal included by using wavelet and wavelet threshold methods filter the low and high frequency noise in ECG signal. Secondly, analyzing weight of ECG feature and selecting the optimal feature subset. Evaluated by the accuracy rate of BP neural network classification, the optimal characteristics for identification subset is determined then. Thirdly, designing and optimizing the neural network classifier. As the BP neural network has the Problems of easily falling into local minimum and being not convergence, GA and DNA algorithm are used to optimize it.

scholarly journals The compliance evolution of the corporate governance codes in emerging European countries – a content analysis perspective

2021 ◽  
Vol 20 (3) ◽  
pp. 516-536
Author(s):  
Pompei Mititean ◽  
Keyword(s):  
Corporate Governance ◽  
Content Analysis ◽  
European Commission ◽  
Research Question ◽  
European Countries ◽  
Time Data ◽  
Main Research ◽  
Analysis Technique ◽  
Starting Point ◽  
Corporate Governance Codes

Research Question: Does the corporate governance codes from 18 Emerging European countries respect the European Commission recommendations? Motivation: The corporate governance is a wildly debated topic in the literature but only few studies are addressed to the level of compliance between the corporate governance and the European Commission recommendations, especially in emerging countries. Idea: The objective of this study is to analyse the corporate governance codes form eighteen Emerging European Countries and examine if these countries comply with the recommendations of European Commission regarding corporate governance by using the content analysis technique. The main research proposition is to identify how many out of the 32 recommendations included in this analysis are fulfilled by the corporate governance codes from the Emerging European Countries and how these developed during time. Data: Data sample consists of 18 corporate governance codes from Emerging European Countries, which are examined in the context of the recommendations of European Commission COM-284, and the next years updates from 2004 (2004/913/EC), 2005 (2005/162/EC) and 2009 (2009/384 and 385/EC), divided into five group, covering 32 recommendations. Tools: The latest versions of corporate governance codes from each country, from 2004-2020, were downloaded, collecting the data manually from each corporate governance code using the content analysis technique. Findings: The results illustrate that Slovenia and Czech Republic are the countries with the highest compliance degree, while Poland and Estonia are the countries with the least fulfilled recommendations Contribution: This paper provides a general overview regarding the level of compliance of the corporate governance codes and European Commission recommendations, thus being a starting point for researchers who will further study this subject. Secondly, we have contribute to the limited studies that analysed the evolution of corporate governance codes following the best practices for the companies issued by European Commission.

scholarly journals What Has Been the Focus of Sugarcane Research? A Bibliometric Overview

2019 ◽  
Vol 16 (18) ◽  
pp. 3326 ◽  
Author(s):  
Katia A. Figueroa-Rodríguez ◽  
Francisco Hernández-Rosas ◽  
Benjamín Figueroa-Sandoval ◽  
Joel Velasco-Velasco ◽  
Noé Aguilar Rivera
Keyword(s):  
Crop Yields ◽  
Main Research ◽  
Scientific Discussion ◽  
Research Areas ◽  
Starting Point ◽  
Mapping Analysis ◽  
The Usa ◽  
Good Starting Point ◽  
Using Data ◽  
Leading Journals

Sugarcane is one of the main crops worldwide, and it has an important impact on environmental issues. A bibliometric mapping analysis of the research on sugarcane was carried out, using data on the titles, abstracts, and keywords of articles published in leading journals and other peer-reviewed documents available in the SCOPUS database from 1858 to 2019 (27 August), and this was subsequently analyzed with the software VOSviewer. The three most important countries that publish research and were most-cited regarding sugarcane were Brazil, the USA, and India. The analysis of the co-occurrence of terms shows that the main research areas were sugarcane bagasse and terms related to bioenergy, and on a second level of relevance agronomy topics related to increasing crop yields. This first attempt to visualize the abundance of publications regarding sugarcane in their totality is in itself a good starting point for further scientific discussion.

IMPROVING OBJECT DETECTION PERFORMANCE WITH GENETIC PROGRAMMING

2007 ◽  
Vol 16 (05) ◽  
pp. 849-873 ◽  
Author(s):  
MENGJIE ZHANG
Keyword(s):  
Neural Network ◽  
Genetic Programming ◽  
Object Detection ◽  
Fitness Function ◽  
Detection Performance ◽  
Network Approach ◽  
Two Phase ◽  
Neural Network Approach ◽  
The Third ◽  
The Neural Network

This paper describes three developments to improve object detection performance using genetic programming. The first investigates three feature sets, the second investigates a new fitness function, and the third introduces a two phase learning method using genetic programming. This approach is examined on three object detection problems of increasing difficulty and compared with a neural network approach. The two phase GP approach with the new fitness function and the local concentric circular region features achieved the best results. The results suggest that the concentric circular pixel statistics are more effective than the square features for these object detection problems. The fitness function with program size is more effective and more efficient than without for these object detection problems and the evolved genetic programs using this fitness function are much shorter and easier to interpret. The two phase GP approach is more effective and more efficient than the single stage GP approach, and also more effective than the neural network approach on these problems using the same set of features.

Evolutionary Optimization and Use of Neural Network for Optimum Stamping Process Design for Minimum Springback

2002 ◽  
Vol 2 (1) ◽  
pp. 38-44 ◽  
Author(s):  
K. M. Liew ◽  
Tapabrata Ray ◽  
H. Tan , and ◽  
M. J. Tan
Keyword(s):  
Neural Network ◽  
Evolutionary Algorithm ◽  
Sheet Metal ◽  
Process Parameters ◽  
Minimization Problem ◽  
Sheet Metal Forming ◽  
Metal Forming ◽  
Optimization Problems ◽  
Optimization Methods ◽  
The Neural Network

Sheet metal forming is characterized by various process parameters such as the forming sequence, shapes of products and dies, friction parameters, forming speed etc. A designer is faced with the challenge of identifying optimal process parameters for minimum springback. Currently, a vast majority of such applications in practice are guided by trial and error and user experience. In this paper, we present two useful designer aids; an evolutionary algorithm and a neural network integrated evolutionary algorithm. We have taken a simple springback minimization problem to illustrate the methodology although the evolutionary algorithm is generic and capable of handling both single and multiobjective, unconstrained and constrained optimization problems. The springback minimization problem has been modeled as a discrete variable, unconstrained, single objective optimization problem and solved using both optimization methods. Both the algorithms are capable of generating multiple optimal solutions in a single run unlike most available optimization methods that provide a single solution. The neural network integrated evolutionary algorithm reduces the computational time significantly as the neural network approximates the springback instead of performing an actual springback computation. The results clearly indicate that both the algorithms are useful optimization tools that can be used to solve a variety of parametric optimization problems in the domain of sheet metal forming.

scholarly journals Cultural Economy for the Environmental Preservation of the Landscape as a Key Resource in Historic Territories

Agriculture ◽  
2018 ◽  
Vol 8 (10) ◽  
pp. 161 ◽  
Author(s):  
Luciano Pilotti
Keyword(s):  
Cultural Policy ◽  
Local Community ◽  
Research Question ◽  
Point Of View ◽  
Urban Landscapes ◽  
Large Network ◽  
New Model ◽  
Main Research ◽  
Starting Point ◽  
Cultural Marketing

Sustainable production besides economic, energetic, and environmental aspects should consider social and cultural features of the territory in which it relies. This occurs above all for agriculture that is intrinsically related to the territory. Today, the territory as a landscape represents a complex eco-system (subjects, communities, traditions, cultures, and specific agricultural systems) and a valuable vehicle for art and history and it is also a strategic asset to defend and promote with environmental policies. The topic of urban preservation and regeneration has been increasing by opening up to other factors such as the engagement of local communities and the contribution they can give toward the development of the identity and the symbolic universe of every community especially for historic territories. The main research question of this study is: Can historic territories be described as the landscape of a complex eco-system able to support a new cultural policy? In addition, which type of connections between physical resources and the virtual-cultural ones of that landscape are strategic assets for promoting historic territories? This theoretical manuscript is oriented toward improving territorial policies. In more details, it tries to develop a new model to reach a “global community of creativity” as a bridge between the networks of historic territories, which is meant as roots of variety to transfer to future generations, and between local and global quality in an emergent landscape. In order to reach this new model, the local community and ecosystem capabilities require a multi-level connection among both art, science, and culture as well as nature, technology, and civic capability. The result is that the new model is able to share common goods, which are both internal and external. Following this path, it is urgent to develop policies in an emergent perspective that are able to combine artistic, ecological, environmental, and cultural assets. In particular, the goals are to: (i) explore the complex value of territorial contexts that develop/evolve from both a medium-term and long-term point of view that is not described by Gross Domestic Product (GDP) standard indicators, (ii) reach the suggestion of a continuous re-articulation of sectors of knowledge proposed by cultural resources, and (iii) highlight that cultural marketing is involved in the interpretation and transmission within a large network of participants, users, institutions, markets, virtual, and territorial places. The starting point is identified as the landscape of historic territory, but an important achievement will be to transfer the main results to other territories by studying specific case histories of urban and non-urban landscapes.

A unified approach to multi-fixturing layout planning for thin-walled workpiece

2016 ◽  
Vol 231 (3) ◽  
pp. 454-469 ◽  
Author(s):  
Guohua Qin ◽  
Zikun Wang ◽  
Yiming Rong ◽  
Qiang Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Finite Element ◽  
Fitness Function ◽  
Machining Accuracy ◽  
Optimal Model ◽  
Prediction Ability ◽  
The Neural Network ◽  
Training Samples ◽  
Thin Walled

It is crucial to properly design the fixturing layout described by fixturing parameters, such as the fixturing sequence, the placement of clamping force, the locator position, and so on. This is because the clamping deformation of the thin-walled workpiece can influence extremely the machining accuracy and surface quality. Generally speaking, the finite element method can be used to easily obtain the deformation rule of the workpiece caused by one single fixturing parameter. But it is difficult to reveal the relationship between the multiple fixturing parameters and the clamping deformation of workpiece. Therefore, the workable finite element model of multi-fixturing layout is above all established for the thin-walled workpiece. Thus, clamping deformations can be calculated to be the training samples of the neural network. Next, according to the training samples, the prediction model is suggested for obtaining the clamping deformation from multiple fixturing parameters. When the prediction errors are defined as fitness function, the genetic algorithm is developed to search the optimal initial weights and thresholds for the neural network. The optimized neural network has better generalization and prediction ability than the non-optimized one. Ultimately, the embedded optimal model with the objective of minimizing the clamping deformation is presented for a multi-fixturing layout. When the individual fitness of each generation is constructed as a function of the clamping deformations, the genetic algorithm can be skillfully used to solve the embedded optimal model. Moreover, the experiment is conducted to validate the prediction method with good agreement between the predicted results and the experimental data. The above presented “analysis—prediction—control” method of clamping deformation not only improves the calculation efficiency of clamping deformation but also provides a basic theory of fixturing layout design for the thin-walled workpiece.

Sign in / Sign up

Export Citation Format

Share Document