To see the other types of publications on this topic, follow the link: Evolutionary development of neural network.
Journal articles on the topic 'Evolutionary development of neural network'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Evolutionary development of neural network.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Al-Khowarizmi, Al-Khowarizmi. "Model Classification Of Nominal Value And The Original Of IDR Money By Applying Evolutionary Neural Network." JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING 3, no. 2 (January 20, 2020): 258–65. http://dx.doi.org/10.31289/jite.v3i2.3284.
Full textAbstract:
Indonesian Rupiah (IDR) banknotes have unique characteristics that distinguish them from one another, both in the form of numbers, zeros and background images. This pattern of each type of banknote will be modeled in order to test the nominal value and authenticity of IDR, so as to be able to distinguish not only IDR banknotes but also other denominations. Evolutionary Neural Network is the development of the concept of evolution to get a neural network (NN) using genetic algorithms (GA). In this paper the application of evolutionary neural networks with less input is able to have a better success rate in object recognition, because the parameters for producing neural networks are far better
2
Li, Xiao Guang. "Research on the Development and Applications of Artificial Neural Networks." Applied Mechanics and Materials 556-562 (May 2014): 6011–14. http://dx.doi.org/10.4028/www.scientific.net/amm.556-562.6011.
Full textAbstract:
Intelligent control is a class of control techniques that use various AI computing approaches like neural networks, Bayesian probability, fuzzy logic, machine learning, evolutionary computation and genetic algorithms. In computer science and related fields, artificial neural networks are computational models inspired by animals’ central nervous systems (in particular the brain) that are capable of machine learning and pattern recognition. They are usually presented as systems of interconnected “neurons” that can compute values from inputs by feeding information through the network. Like other machine learning methods, neural networks have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming, including computer vision and speech recognition.
3
Xue, Yu, Pengcheng Jiang, Ferrante Neri, and Jiayu Liang. "A Multi-Objective Evolutionary Approach Based on Graph-in-Graph for Neural Architecture Search of Convolutional Neural Networks." International Journal of Neural Systems 31, no. 09 (July 24, 2021): 2150035. http://dx.doi.org/10.1142/s0129065721500350.
Full textAbstract:
With the development of deep learning, the design of an appropriate network structure becomes fundamental. In recent years, the successful practice of Neural Architecture Search (NAS) has indicated that an automated design of the network structure can efficiently replace the design performed by human experts. Most NAS algorithms make the assumption that the overall structure of the network is linear and focus solely on accuracy to assess the performance of candidate networks. This paper introduces a novel NAS algorithm based on a multi-objective modeling of the network design problem to design accurate Convolutional Neural Networks (CNNs) with a small structure. The proposed algorithm makes use of a graph-based representation of the solutions which enables a high flexibility in the automatic design. Furthermore, the proposed algorithm includes novel ad-hoc crossover and mutation operators. We also propose a mechanism to accelerate the evaluation of the candidate solutions. Experimental results demonstrate that the proposed NAS approach can design accurate neural networks with limited size.
4
Odri, Stevan V., Dusan P. Petrovacki, and Gordana A. Krstonosic. "Evolutional development of a multilevel neural network." Neural Networks 6, no. 4 (January 1993): 583–95. http://dx.doi.org/10.1016/s0893-6080(05)80061-9.
Full text
5
LI, KANG, and JIAN-XUN PENG. "SYSTEM ORIENTED NEURAL NETWORKS — PROBLEM FORMULATION, METHODOLOGY AND APPLICATION." International Journal of Pattern Recognition and Artificial Intelligence 20, no. 02 (March 2006): 143–58. http://dx.doi.org/10.1142/s0218001406004570.
Full textAbstract:
A novel methodology is proposed for the development of neural network models for complex engineering systems exhibiting nonlinearity. This method performs neural network modeling by first establishing some fundamental nonlinear functions from a priori engineering knowledge, which are then constructed and coded into appropriate chromosome representations. Given a suitable fitness function, using evolutionary approaches such as genetic algorithms, a population of chromosomes evolves for a certain number of generations to finally produce a neural network model best fitting the system data. The objective is to improve the transparency of the neural networks, i.e. to produce physically meaningful "white box" neural network model with better generalization performance. In this paper, the problem formulation, the neural network configuration, and the associated optimization software are discussed in detail. This methodology is then applied to a practical real-world system to illustrate its effectiveness.
6
Wu, Tao, Jiao Shi, Deyun Zhou, Xiaolong Zheng, and Na Li. "Evolutionary Multi-Objective One-Shot Filter Pruning for Designing Lightweight Convolutional Neural Network." Sensors 21, no. 17 (September 2, 2021): 5901. http://dx.doi.org/10.3390/s21175901.
Full textAbstract:
Deep neural networks have achieved significant development and wide applications for their amazing performance. However, their complex structure, high computation and storage resource limit their applications in mobile or embedding devices such as sensor platforms. Neural network pruning is an efficient way to design a lightweight model from a well-trained complex deep neural network. In this paper, we propose an evolutionary multi-objective one-shot filter pruning method for designing a lightweight convolutional neural network. Firstly, unlike some famous iterative pruning methods, a one-shot pruning framework only needs to perform filter pruning and model fine-tuning once. Moreover, we built a constraint multi-objective filter pruning problem in which two objectives represent the filter pruning ratio and the accuracy of the pruned convolutional neural network, respectively. A non-dominated sorting-based evolutionary multi-objective algorithm was used to solve the filter pruning problem, and it provides a set of Pareto solutions which consists of a series of different trade-off pruned models. Finally, some models are uniformly selected from the set of Pareto solutions to be fine-tuned as the output of our method. The effectiveness of our method was demonstrated in experimental studies on four designed models, LeNet and AlexNet. Our method can prune over 85%, 82%, 75%, 65%, 91% and 68% filters with little accuracy loss on four designed models, LeNet and AlexNet, respectively.
7
Debeljak, Željko, Viktor Marohnić, Goran Srečnik, and Marica Medić-Šarić. "Novel approach to evolutionary neural network based descriptor selection and QSAR model development." Journal of Computer-Aided Molecular Design 19, no. 12 (April 11, 2006): 835–55. http://dx.doi.org/10.1007/s10822-005-9022-2.
Full text
8
Jung, Sung Young. "A Topographical Method for the Development of Neural Networks for Artificial Brain Evolution." Artificial Life 11, no. 3 (June 2005): 293–316. http://dx.doi.org/10.1162/1064546054407185.
Full textAbstract:
Developmental neural networks, which are constructed according to developmental rules (i.e., genes), have the potential to be differentiated into heteromorphic neural structures capable of performing various kinds of activities. The fact that the biological neural architectures are found to be highly repetitive, layered, and topographically organized has important consequences for neural development methods. The purpose of this article is to propose a neural development method that can construct topographical neural connections, that is, a topographical development method, to facilitate fast and efficient development. This is achieved by arborizing neural connections on a developmental tree that rarely produces dead connections. Modular gene expression and corresponding modular networks have an important role in a gradual evolutionary process. Gene expression for modular networks is also proposed here as a way to reduce the probability of fatal mutants created through gene alteration. The corresponding evolutionary experiment shows that various neural structures—layered, repetitive, modular, and complex ones like those in the biological brain—can be constructed and easily observed. It also demonstrates that due to the efficiency of the proposed method, large neural networks can be easily managed, thereby making it suitable for long duration evolutionary experiments.
9
Bury, Y. A., and D. I. Samal. "APPLICATION OF THE EVOLUTIONARY PARADIGM TO DESIGNING ARCHITEСTURE OF A NEURAL NETWORK FOR RECOGNIZING THE DISTORTED TEXT." «System analysis and applied information science», no. 4 (February 8, 2018): 45–50. http://dx.doi.org/10.21122/2309-4923-2017-4-45-50.
Full textAbstract:
The paper presents an attempt to apply of evolutionary methods to the design and training of a system for recognizing distorted text.Over the past decades, artificial neural networks are widely used in many areas of artificial intelligence, such as forecasting, optimization, data analysis, pattern recognition and decision making. Nevertheless, the traditional heuristic approaches to design of multi-layer neural networks are based on the recombination of already existing neural network architectures.This approach allows us to solve a wide range of problems, but implies compliance with specific conditions for the quality work of algorithms.The natural analogues of such intelligent systems in living nature, however, are universal enough to adapt to virtually any habitat.Despite their extreme complexity and limited ability to study their structures, it is known that these structures were formed as a result of the evolutionary process. And if today it is impossible to determine the exact architecture of the links in biological neural systems, then at least one can try to reproduce the very process of their formation in order to obtain a more universal algorithm than those developed to the present moment.In opposite to them we form the final structure of the core of the classification system by evolutionary process, taking into account the knowledge about the features of the development and construction of the nervous system of vertebrates.Applying of the approach makes it possible to abstract from the limitations of existing neural network algorithms, caused by the scope of application of specific types of their structures.
10
Khan, Gul Muhammad, Julian F. Miller, and David M. Halliday. "Evolution of Cartesian Genetic Programs for Development of Learning Neural Architecture." Evolutionary Computation 19, no. 3 (September 2011): 469–523. http://dx.doi.org/10.1162/evco_a_00043.
Full textAbstract:
Although artificial neural networks have taken their inspiration from natural neurological systems, they have largely ignored the genetic basis of neural functions. Indeed, evolutionary approaches have mainly assumed that neural learning is associated with the adjustment of synaptic weights. The goal of this paper is to use evolutionary approaches to find suitable computational functions that are analogous to natural sub-components of biological neurons and demonstrate that intelligent behavior can be produced as a result of this additional biological plausibility. Our model allows neurons, dendrites, and axon branches to grow or die so that synaptic morphology can change and affect information processing while solving a computational problem. The compartmental model of a neuron consists of a collection of seven chromosomes encoding distinct computational functions inside the neuron. Since the equivalent computational functions of neural components are very complex and in some cases unknown, we have used a form of genetic programming known as Cartesian genetic programming (CGP) to obtain these functions. We start with a small random network of soma, dendrites, and neurites that develops during problem solving by repeatedly executing the seven chromosomal programs that have been found by evolution. We have evaluated the learning potential of this system in the context of a well-known single agent learning problem, known as Wumpus World. We also examined the harder problem of learning in a competitive environment for two antagonistic agents, in which both agents are controlled by independent CGP computational networks (CGPCN). Our results show that the agents exhibit interesting learning capabilities.
11
Bronner-Fraser, Marianne. "Ancient evolutionary origin of the neural crest gene regulatory network." Developmental Biology 319, no. 2 (July 2008): 470. http://dx.doi.org/10.1016/j.ydbio.2008.05.474.
Full text
12
Zhu, Yan. "Study on evolutionary neural networks and software development with Java." Chinese Journal of Mechanical Engineering (English Edition) 13, supp (2000): 52. http://dx.doi.org/10.3901/cjme.2000.supp.052.
Full text
13
Ardesch, Dirk Jan, Lianne H. Scholtens, Longchuan Li, Todd M. Preuss, James K. Rilling, and Martijn P. van den Heuvel. "Evolutionary expansion of connectivity between multimodal association areas in the human brain compared with chimpanzees." Proceedings of the National Academy of Sciences 116, no. 14 (March 18, 2019): 7101–6. http://dx.doi.org/10.1073/pnas.1818512116.
Full textAbstract:
The development of complex cognitive functions during human evolution coincides with pronounced encephalization and expansion of white matter, the brain’s infrastructure for region-to-region communication. We investigated adaptations of the human macroscale brain network by comparing human brain wiring with that of the chimpanzee, one of our closest living primate relatives. White matter connectivity networks were reconstructed using diffusion-weighted MRI in humans (n= 57) and chimpanzees (n= 20) and then analyzed using network neuroscience tools. We demonstrate higher network centrality of connections linking multimodal association areas in humans compared with chimpanzees, together with a more pronounced modular topology of the human connectome. Furthermore, connections observed in humans but not in chimpanzees particularly link multimodal areas of the temporal, lateral parietal, and inferior frontal cortices, including tracts important for language processing. Network analysis demonstrates a particularly high contribution of these connections to global network integration in the human brain. Taken together, our comparative connectome findings suggest an evolutionary shift in the human brain toward investment of neural resources in multimodal connectivity facilitating neural integration, combined with an increase in language-related connectivity supporting functional specialization.
14
Mrówczyńska, Maria. "Elements of an algorithm for optimizing a parameter-structural neural network." Reports on Geodesy and Geoinformatics 101, no. 1 (June 1, 2016): 27–35. http://dx.doi.org/10.1515/rgg-2016-0019.
Full textAbstract:
Abstract The field of processing information provided by measurement results is one of the most important components of geodetic technologies. The dynamic development of this field improves classic algorithms for numerical calculations in the aspect of analytical solutions that are difficult to achieve. Algorithms based on artificial intelligence in the form of artificial neural networks, including the topology of connections between neurons have become an important instrument connected to the problem of processing and modelling processes. This concept results from the integration of neural networks and parameter optimization methods and makes it possible to avoid the necessity to arbitrarily define the structure of a network. This kind of extension of the training process is exemplified by the algorithm called the Group Method of Data Handling (GMDH), which belongs to the class of evolutionary algorithms. The article presents a GMDH type network, used for modelling deformations of the geometrical axis of a steel chimney during its operation.
15
Woodford, Grant W., Christiaan J. Pretorius, and Mathys C. du Plessis. "Concurrent controller and Simulator Neural Network development for a differentially-steered robot in Evolutionary Robotics." Robotics and Autonomous Systems 76 (February 2016): 80–92. http://dx.doi.org/10.1016/j.robot.2015.10.011.
Full text
16
Woodford, Grant W., Mathys C. du Plessis, and Christiaan J. Pretorius. "Concurrent controller and Simulator Neural Network development for a snake-like robot in Evolutionary Robotics." Robotics and Autonomous Systems 88 (February 2017): 37–50. http://dx.doi.org/10.1016/j.robot.2016.11.018.
Full text
17
Kitano, Hiroaki. "A Simple Model of Neurogenesis and Cell Differentiation Based on Evolutionary Large-Scale Chaos." Artificial Life 2, no. 1 (October 1994): 79–99. http://dx.doi.org/10.1162/artl.1994.2.1.79.
Full textAbstract:
This article reports on a simple neurogenesis model that is combined with evolutionary computation. Because the integration of an evolutionary process with neural networks is such an exciting field of study, with the promise of discovering new computational models and, possibly, providing novel biological insights, much research has been conducted in this area. However, only a few studies have incorporated a development stage, and none have modeled metabolism and other chemical reactions in a consistent manner. In this article, we present a simple model of neurogenesis and cell differentiation that combines evolutionary computing, metabolism, development, and neural networks. The model represents an evolutionary large-scale chaos as a mathematical foundation. An evolutionary large-scale chaos is a large-scale chaos whose map functions change through evolutionary computing. Experiments indicate that the model is capable of evolving and growing large neural networks, and exhibits phenomena analogous to cell differentiation.
18
Nazirah Wan Md Adna, Wan n., Nofri Yenita Dahlan, and Ismail Musirin. "Development of Hybrid Artificial Neural Network for Quantifying Energy Saving using Measurement and Verification." Indonesian Journal of Electrical Engineering and Computer Science 8, no. 1 (October 1, 2017): 137. http://dx.doi.org/10.11591/ijeecs.v8.i1.pp137-145.
Full textAbstract:
This paper presents a Hybrid Artificial Neural Network (HANN) for chiller system Measurement and Verification (M&V) model development. In this work, hybridization of Evolutionary Programming (EP) and Artificial Neural Network (ANN) are considered in modeling the baseline electrical energy consumption for a chiller system hence quantifying saving. EP with coefficient of correlation (R) objective function is used in optimizing the neural network training process and selecting the optimal values of ANN initial weights and biases. Three inputs that are affecting energy use of the chiller system are selected; 1) operating time, 2) refrigerant tonnage and 3) differential temperature. The output is hourly energy use of building air-conditioning system. The HANN model is simulated with 16 different structures and the results reveal that all HANN structures produce higher prediction performance with R is above 0.977. The best structure with the highest value of R is selected as the baseline model hence is used to determine the saving. The avoided energy calculated from this model is 132944.59 kWh that contributes to 1.38% of saving percentage.
19
Alexandridis, Alex, Panagiotis Patrinos, Haralambos Sarimveis, and George Tsekouras. "A two-stage evolutionary algorithm for variable selection in the development of RBF neural network models." Chemometrics and Intelligent Laboratory Systems 75, no. 2 (February 2005): 149–62. http://dx.doi.org/10.1016/j.chemolab.2004.06.004.
Full text
20
Xiao, Maohua, Weichen Wang, Kaixin Wang, Wei Zhang, and Hengtong Zhang. "Fault Diagnosis of High-Power Tractor Engine Based on Competitive Multiswarm Cooperative Particle Swarm Optimizer Algorithm." Shock and Vibration 2020 (August 3, 2020): 1–13. http://dx.doi.org/10.1155/2020/8829257.
Full textAbstract:
With the rapid development of high-power tractor, the fault diagnosis of high-power tractor has become more and more important for ensuring the operating safety and efficiency. PSO is an iterative optimization evolutionary algorithm, which can iterate through different particles to find the optimal solution. However, there is only one population in the standard PSO algorithm, and the information exchange between the populations is relatively single, which can easily lead to the stagnation of the development of the population. In this paper, due to high-power tractor diesel engine fault complexity, fault correlation, and multifault concurrency, a multigroup coevolution particle swarm optimization BP neural network for diesel engine fault diagnosis method was proposed. First, the USB-CAN device was used to collect data of 8 items of the diesel engine under five different working conditions, and the data was parsed through the SAE J1939 protocol; then, the BP neural network was reconstructed, and a competitive multiswarm cooperative particle swarm optimizer algorithm (COM-MCPSO) was used to optimize its structure and weights. Finally, the data of optimized neural network under five different fault conditions show that, compared with BP neural network and PSO optimized BP neural network, the fault diagnosis of COM-MCPSO optimized BP neural network not only improves the network training speed, but also enhances generalization ability and improves recognition accuracy.
21
KONOVALOV, S. "FEATURES OF DIAGNOSTIC ARTIFICIAL NEURAL NETWORKS FOR HYBRID EXPERT SYSTEMS." Digital Technologies 26 (2019): 36–46. http://dx.doi.org/10.33243/2313-7010-26-36-46.
Full textAbstract:
In the proposed article, various methods of constructing an artificial neural network as one of the components of a hybrid expert system for diagnosis were investigated. A review of foreign literature in recent years was conducted, where hybrid expert systems were considered as an integral part of complex technical systems in the field of security. The advantages and disadvantages of artificial neural networks are listed, and the main problems in creating hybrid expert systems for diagnostics are indicated, proving the relevance of further development of artificial neural networks for hybrid expert systems. The approaches to the analysis of natural language sentences, which are used for the work of hybrid expert systems with artificial neural networks, are considered. A bulletin board is shown, its structure and principle of operation are described. The structure of the bulletin board is divided into levels and sublevels. At sublevels, a confidence factor is applied. The dependence of the values of the confidence factor on the fulfillment of a particular condition is shown. The links between the levels and sublevels of the bulletin board are also described. As an artificial neural network architecture, the «key-threshold» model is used, the rule of neuron operation is shown. In addition, an artificial neural network has the property of training, based on the application of the penalty property, which is able to calculate depending on the accident situation. The behavior of a complex technical system, as well as its faulty states, are modeled using a model that describes the structure and behavior of a given system. To optimize the data of a complex technical system, an evolutionary algorithm is used to minimize the objective function. Solutions to the optimization problem consist of Pareto solution vectors. Optimization and training tasks are solved by using the Hopfield network. In general, a hybrid expert system is described using semantic networks, which consist of vertices and edges. The reference model of a complex technical system is stored in the knowledge base and updated during the acquisition of new knowledge. In an emergency, or about its premise, with the help of neural networks, a search is made for the cause and the control action necessary to eliminate the accident. The considered approaches, interacting with each other, can improve the operation of diagnostic artificial neural networks in the case of emergency management, showing more accurate data in a short time. In addition, the use of such a network for analyzing the state of health, as well as forecasting based on diagnostic data using the example of a complex technical system, is presented.
22
Dedecker, Andy P., Peter L. M. Goethals, and Niels De Pauw. "Comparison of Artificial Neural Network (ANN) Model Development Methods for Prediction of Macroinvertebrate Communities in the Zwalm River Basin in Flanders, Belgium." Scientific World JOURNAL 2 (2002): 96–104. http://dx.doi.org/10.1100/tsw.2002.79.
Full textAbstract:
Modelling has become an interesting tool to support decision making in water management. River ecosystem modelling methods have improved substantially during recent years. New concepts, such as artificial neural networks, fuzzy logic, evolutionary algorithms, chaos and fractals, cellular automata, etc., are being more commonly used to analyse ecosystem databases and to make predictions for river management purposes. In this context, artificial neural networks were applied to predict macroinvertebrate communities in the Zwalm River basin (Flanders, Belgium). Structural characteristics (meandering, substrate type, flow velocity) and physical and chemical variables (dissolved oxygen, pH) were used as predictive variables to predict the presence or absence of macroinvertebrate taxa in the headwaters and brooks of the Zwalm River basin. Special interest was paid to the frequency of occurrence of the taxa as well as the selection of the predictors and variables to be predicted on the prediction reliability of the developed models. Sensitivity analyses allowed us to study the impact of the predictive variables on the prediction of presence or absence of macroinvertebrate taxa and to define which variables are the most influential in determining the neural network outputs.
23
TAN, TSE GUAN, JASON TEO, and PATRICIA ANTHONY. "NATURE-INSPIRED COGNITIVE EVOLUTION TO PLAY MS. PAC-MAN." International Journal of Modern Physics: Conference Series 09 (January 2012): 456–63. http://dx.doi.org/10.1142/s2010194512005545.
Full textAbstract:
Recent developments in nature-inspired computation have heightened the need for research into the three main areas of scientific, engineering and industrial applications. Some approaches have reported that it is able to solve dynamic problems and very useful for improving the performance of various complex systems. So far however, there has been little discussion about the effectiveness of the application of these models to computer and video games in particular. The focus of this research is to explore the hybridization of nature-inspired computation methods for optimization of neural network-based cognition in video games, in this case the combination of a neural network with an evolutionary algorithm. In essence, a neural network is an attempt to mimic the extremely complex human brain system, which is building an artificial brain that is able to self-learn intelligently. On the other hand, an evolutionary algorithm is to simulate the biological evolutionary processes that evolve potential solutions in order to solve the problems or tasks by applying the genetic operators such as crossover, mutation and selection into the solutions. This paper investigates the abilities of Evolution Strategies (ES) to evolve feed-forward artificial neural network's internal parameters (i.e. weight and bias values) for automatically generating Ms. Pac-man controllers. The main objective of this game is to clear a maze of dots while avoiding the ghosts and to achieve the highest possible score. The experimental results show that an ES-based system can be successfully applied to automatically generate artificial intelligence for a complex, dynamic and highly stochastic video game environment.
24
Bronner, Marianne E. "Migrating into Genomics with the Neural Crest." Advances in Biology 2014 (June 22, 2014): 1–8. http://dx.doi.org/10.1155/2014/264069.
Full textAbstract:
Neural crest cells are a fascinating embryonic cell type, unique to vertebrates, which arise within the central nervous system but emigrate soon after its formation and migrate to numerous and sometimes distant locations in the periphery. Following their migratory phase, they differentiate into diverse derivatives ranging from peripheral neurons and glia to skin melanocytes and craniofacial cartilage and bone. The molecular underpinnings underlying initial induction of prospective neural crest cells at the neural plate border to their migration and differentiation have been modeled in the form of a putative gene regulatory network. This review describes experiments performed in my laboratory in the past few years aimed to test and elaborate this gene regulatory network from both an embryonic and evolutionary perspective. The rapid advances in genomic technology in the last decade have greatly expanded our knowledge of important transcriptional inputs and epigenetic influences on neural crest development. The results reveal new players and new connections in the neural crest gene regulatory network and suggest that it has an ancient origin at the base of the vertebrate tree.
25
Kenarkoohi, A., M. Ravanshad, S. Falahi, and M. Rasouli. "Development of a new genotyping system for predicting TTV genotype using evolutionary restriction map and artificial neural network." International Journal of Infectious Diseases 14 (March 2010): e474-e475. http://dx.doi.org/10.1016/j.ijid.2010.02.672.
Full text
26
Karimi, Amir, and Taghi Javdani Gandomani. "Software development effort estimation modeling using a combination of fuzzy-neural network and differential evolution algorithm." International Journal of Electrical and Computer Engineering (IJECE) 11, no. 1 (February 1, 2021): 707. http://dx.doi.org/10.11591/ijece.v11i1.pp707-715.
Full textAbstract:
Software cost estimation has always been a serious challenge lying ahead of software teams that should be seriously considered in the early stages of a project. Lack of sufficient information on final requirements, as well as the existence of inaccurate and vague requirements, are among the main reasons for unreliable estimations in this area. Though several effort estimation models have been proposed over the recent decade, an increase in their accuracy has always been a controversial issue, and researchers' efforts in this area are still ongoing. This study presents a new model based on a hybrid of adaptive network-based fuzzy inference system (ANFIS) and differential evolution (DE) algorithm. This model tries to obtain a more accurate estimation of software development effort that is capable of presenting a better estimate within a wide range of software projects compared to previous works. The proposed method outperformed other optimization algorithms adopted from the genetic algorithm, evolutionary algorithms, meta-heuristic algorithms, and neuro-fuzzy based optimization algorithms, and could improve the accuracy using MMRE and PRED (0.25) criteria up to 7%.
27
CHEETHAM, WILLIAM, SIMON SHIU, and ROSINA O. WEBER. "Soft case-based reasoning." Knowledge Engineering Review 20, no. 3 (September 2005): 267–69. http://dx.doi.org/10.1017/s0269888906000579.
Full textAbstract:
The aim of this commentary is to discuss the contribution of soft computing—a consortium of fuzzy logic, neural network theory, evolutionary computing, and probabilistic reasoning—to the development of case-based reasoning (CBR) systems. We will describe how soft computing has been used in case representation, retrieval, adaptation, reuse, and case-base maintenance, and then present a brief summary of six CBR applications that use soft computing techniques.
28
Abdelbari, Hassan, and Kamran Shafi. "Learning Structures of Conceptual Models from Observed Dynamics Using Evolutionary Echo State Networks." Journal of Artificial Intelligence and Soft Computing Research 8, no. 2 (April 1, 2018): 133–54. http://dx.doi.org/10.1515/jaiscr-2018-0010.
Full textAbstract:
Abstract Conceptual or explanatory models are a key element in the process of complex system modelling. They not only provide an intuitive way for modellers to comprehend and scope the complex phenomena under investigation through an abstract representation but also pave the way for the later development of detailed and higher-resolution simulation models. An evolutionary echo state network-based method for supporting the development of such models, which can help to expedite the generation of alternative models for explaining the underlying phenomena and potentially reduce the manual effort required, is proposed. It relies on a customised echo state neural network for learning sparse conceptual model representations from the observed data. In this paper, three evolutionary algorithms, a genetic algorithm, differential evolution and particle swarm optimisation are applied to optimize the network design in order to improve model learning. The proposed methodology is tested on four examples of problems that represent complex system models in the economic, ecological and physical domains. The empirical analysis shows that the proposed technique can learn models which are both sparse and effective for generating the output that matches the observed behaviour.
29
Ijspeert, Auke Jan, and Jérôme Kodjabachian. "Evolution and Development of a Central Pattern Generator for the Swimming of a Lamprey." Artificial Life 5, no. 3 (July 1999): 247–69. http://dx.doi.org/10.1162/106454699568773.
Full textAbstract:
This article describes the design of neural control architectures for locomotion using an evolutionary approach. Inspired by the central pattern generators found in animals, we develop neural controllers that can produce the patterns of oscillations necessary for the swimming of a simulated lamprey. This work is inspired by Ekeberg's neuronal and mechanical model of a lamprey [11] and follows experiments in which swimming controllers were evolved using a simple encoding scheme [25, 26]. Here, controllers are developed using an evolutionary algorithm based on the SGOCE encoding [31, 32] in which a genetic programming approach is used to evolve developmental programs that encode the growing of a dynamical neural network. The developmental programs determine how neurons located on a two-dimensional substrate produce new cells through cellular division and how they form efferent or afferent interconnections. Swimming controllers are generated when the growing networks eventually create connections to the muscles located on both sides of the rectangular substrate. These muscles are part of a two-dimensional mechanical simulation of the body of the lamprey in interaction with water. The motivation of this article is to develop a method for the design of control mechanisms for animal-like locomotion. Such a locomotion is characterized by a large number of actuators, a rhythmic activity, and the fact that efficient motion is only obtained when the actuators are well coordinated. The task of the control mechanism is therefore to transform commands concerning the speed and direction of motion into the signals sent to the multiple actuators. We define a fitness function, based on several simulations of the controller with different commands settings, that rewards the capacity of modulating the speed and the direction of swimming in response to simple, varying input signals. Central pattern generators are thus evolved capable of producing the relatively complex patterns of oscillations necessary for swimming. The best solutions generate traveling waves of neural activity, and propagate, similarly to the swimming of a real lamprey, undulations of the body from head to tail propelling the lamprey forward through water. By simply varying the amplitude of two input signals, the speed and the direction of swimming can be modulated.
30
Fang, Le-Heng, Wei Lin, and Qiang Luo. "Brain-Inspired Constructive Learning Algorithms with Evolutionally Additive Nonlinear Neurons." International Journal of Bifurcation and Chaos 28, no. 05 (May 2018): 1850068. http://dx.doi.org/10.1142/s0218127418500682.
Full textAbstract:
In this article, inspired partially by the physiological evidence of brain’s growth and development, we developed a new type of constructive learning algorithm with evolutionally additive nonlinear neurons. The new algorithms have remarkable ability in effective regression and accurate classification. In particular, the algorithms are able to sustain a certain reduction of the loss function when the dynamics of the trained network are bogged down in the vicinity of the local minima. The algorithm augments the neural network by adding only a few connections as well as neurons whose activation functions are nonlinear, nonmonotonic, and self-adapted to the dynamics of the loss functions. Indeed, we analytically demonstrate the reduction dynamics of the algorithm for different problems, and further modify the algorithms so as to obtain an improved generalization capability for the augmented neural networks. Finally, through comparing with the classical algorithm and architecture for neural network construction, we show that our constructive learning algorithms as well as their modified versions have better performances, such as faster training speed and smaller network size, on several representative benchmark datasets including the MNIST dataset for handwriting digits.
31
Guo, Lin, Qian Jiang, Xin Jin, Lin Liu, Wei Zhou, Shaowen Yao, Min Wu, and Yun Wang. "A Deep Convolutional Neural Network to Improve the Prediction of Protein Secondary Structure." Current Bioinformatics 15, no. 7 (December 15, 2020): 767–77. http://dx.doi.org/10.2174/1574893615666200120103050.
Full textAbstract:
Background: Protein secondary structure prediction (PSSP) is a fundamental task in bioinformatics that is helpful for understanding the three-dimensional structure and biological function of proteins. Many neural network-based prediction methods have been developed for protein secondary structures. Deep learning and multiple features are two obvious means to improve prediction accuracy. Objective: To promote the development of PSSP, a deep convolutional neural network-based method is proposed to predict both the eight-state and three-state of protein secondary structure. Methods: In this model, sequence and evolutionary information of proteins are combined as multiple input features after preprocessing. A deep convolutional neural network with no pooling layer and connection layer is then constructed to predict the secondary structure of proteins. L2 regularization, batch normalization, and dropout techniques are employed to avoid over-fitting and obtain better prediction performance, and an improved cross-entropy is used as the loss function. Results: Our proposed model can obtain Q3 prediction results of 86.2%, 84.5%, 87.8%, and 84.7%, respectively, on CullPDB, CB513, CASP10 and CASP11 datasets, with corresponding Q8 prediction results of 74.1%, 70.5%, 74.9%, and 71.3%. Conclusion: We have proposed the DCNN-SS deep convolutional-network-based PSSP method, and experimental results show that DCNN-SS performs competitively with other methods.
32
Nor Ashikin Megat Yunus, Puteri, Shahril Irwan Sulaiman, and Ahmad Maliki Omar. "Online Performance Monitoring of Grid-Connected Photovoltaic System using Hybrid Improved Fast Evolutionary Programming and Artificial Neural Network." Indonesian Journal of Electrical Engineering and Computer Science 8, no. 2 (November 1, 2017): 399. http://dx.doi.org/10.11591/ijeecs.v8.i2.pp399-406.
Full textAbstract:
<p>This paper presents the development of online performance monitoring methods for grid-connected photovoltaic (GCPV) system based on hybrid Improved Fast Evolutionary Programming and Artificial Neural Network (IFEP-ANN). The approach has been developed and validated using previous predicted data measurement. Solar radiation (SR), module temperature (MT) and ambient temperature (AT) has been employed as the inputs, and AC output power (PAC) as the sole output to the neural network model. The actual data from the server has been called and uploaded every five minute interval into Matlab by using FTP (File Transfer Protocol) and the predicted AC output power has been produced based on the prediction developed in the training stages. It is then compared with the actual AC output power by using Average Test Ratio, AR. Any predicted AC output power less than the threshold set up, indicates an error has been occurred in the system. The obtained results show that the hybrid IFEP-ANN gives good performance by producing a sufficiently high correlation coefficient, R value of 0.9885. Besides, the proposed technique can analyse and monitor the system in online mode. </p>
33
Ellenblum, Gali, Jeremy J. Purcell, Xiaowei Song, and Brenda Rapp. "High-level Integrative Networks: A Resting-state fMRI Investigation of Reading and Spelling." Journal of Cognitive Neuroscience 31, no. 7 (July 2019): 961–77. http://dx.doi.org/10.1162/jocn_a_01405.
Full textAbstract:
Orthographic processing skills (reading and spelling) are evolutionarily recent and mastered late in development, providing an opportunity to investigate how the properties of the neural networks supporting skills of this type compare to those supporting evolutionarily older, well-established “reference” networks. Although there has been extensive research using task-based fMRI to study the neural substrates of reading, there has been very little using resting-state fMRI to examine the properties of orthographic networks. In this investigation using resting-state fMRI, we compare the within-network and across-network coherence properties of reading and spelling networks directly to these properties of reference networks, and we also compare the network properties of the key node of the orthographic networks—the visual word form area—to those of the other nodes of the orthographic and reference networks. Consistent with previous results, we find that orthographic processing networks do not exhibit certain basic network coherence properties displayed by other networks. However, we identify novel distinctive properties of the orthographic processing networks and establish that the visual word form area has unusually high levels of connectivity with a broad range of brain areas. These characteristics form the basis of our proposal that orthographic networks represent a class of “high-level integrative networks” with distinctive properties that allow them to recruit and integrate multiple, lower level processes.
34
Manoharan, Malini, Sayyed Auwn Muhammad, and Ramanathan Sowdhamini. "Sequence Analysis and Evolutionary Studies of Reelin Proteins." Bioinformatics and Biology Insights 9 (January 2015): BBI.S26530. http://dx.doi.org/10.4137/bbi.s26530.
Full textAbstract:
The reelin gene is conserved across many vertebrate species, including humans. The protein product of this gene plays several important roles in early brain development and regulation of neural network plasticity of a matured brain structure. With an extended structure of 3461 amino acid sequences, consisting of eight reelin repeats, the human reelin sequence stands out as an exceptional model for evolutionary studies. In this study, sequence analysis of the human reelin and its homologues and reelin sequences from 104 other species is described in detail. Interesting sequence conservation patterns of individual repeats have been highlighted. Sequence phylogeny of the reelin sequences indicates a pattern similar to the evolution of the species, thereby serving as a highly conserved family for evolutionary purposes. Multiple sequence alignment of different reelin domain repeats, derived from homologues, suggests specific functions for individual repeats and high sequence conservation across reelin repeats from different organisms, albeit with few unusual domain architectures. A three-dimensional structural model of the full-length human reelin is now available that provides clues on residues at the dimer interface.
35
Hejnol, Andreas, and Christopher J. Lowe. "Embracing the comparative approach: how robust phylogenies and broader developmental sampling impacts the understanding of nervous system evolution." Philosophical Transactions of the Royal Society B: Biological Sciences 370, no. 1684 (December 19, 2015): 20150045. http://dx.doi.org/10.1098/rstb.2015.0045.
Full textAbstract:
Molecular biology has provided a rich dataset to develop hypotheses of nervous system evolution. The startling patterning similarities between distantly related animals during the development of their central nervous system (CNS) have resulted in the hypothesis that a CNS with a single centralized medullary cord and a partitioned brain is homologous across bilaterians. However, the ability to precisely reconstruct ancestral neural architectures from molecular genetic information requires that these gene networks specifically map with particular neural anatomies. A growing body of literature representing the development of a wider range of metazoan neural architectures demonstrates that patterning gene network complexity is maintained in animals with more modest levels of neural complexity. Furthermore, a robust phylogenetic framework that provides the basis for testing the congruence of these homology hypotheses has been lacking since the advent of the field of ‘evo-devo’. Recent progress in molecular phylogenetics is refining the necessary framework to test previous homology statements that span large evolutionary distances. In this review, we describe recent advances in animal phylogeny and exemplify for two neural characters—the partitioned brain of arthropods and the ventral centralized nerve cords of annelids—a test for congruence using this framework. The sequential sister taxa at the base of Ecdysozoa and Spiralia comprise small, interstitial groups. This topology is not consistent with the hypothesis of homology of tripartitioned brain of arthropods and vertebrates as well as the ventral arthropod and rope-like ladder nervous system of annelids. There can be exquisite conservation of gene regulatory networks between distantly related groups with contrasting levels of nervous system centralization and complexity. Consequently, the utility of molecular characters to reconstruct ancestral neural organization in deep time is limited.
36
Gašperlin, M., F. Podlogar, and R. Šibanc. "Evolutionary Artificial Neural Networks as Tools for Predicting the Internal Structure of Microemulsions." Journal of Pharmacy & Pharmaceutical Sciences 11, no. 1 (March 24, 2008): 67. http://dx.doi.org/10.18433/j3f594.
Full textAbstract:
PURPOSE. The purpose of this study was to predict microemulsion structures by creating two artificial evolutionary neural networks (ANN) combined with a genetic algorithm. The first ANN would be able to determine the type of microemulsion from the desired composition, and the second to determine the type of microemulsion directly from a differential scanning calorimetry (DSC) curve. METHODS. The algorithms and the structures for each ANN were constructed and programmed in C++ computer language. The ANNs had a feed forward structure with one hidden level and were trained using a genetic algorithm. DSC was used to determine the microemulsion type. RESULTS. The ANNs showed very encouraging accuracy in predicting the microemulsion type from its composition and also directly from the DSC curve. The percentage success, calculated over the tested data, was over 90%. This enabled us, with satisfactory accuracy, to construct several pseudoternary diagrams that could facilitate the selection of the microemulsion composition to obtain the optimal desired drug carrier. CONCLUSIONS. The ANN constructed here, enhanced with a genetic algorithm, is an effective tool for predicting the type of microemulsion. These findings provide the basis for reducing research time and development cost for characterizing microemulsion properties. Its application would stimulate the further development of such colloidal drug delivery systems, exploit their advantages and, to a certain extent, avoid their disadvantages.
37
von Wysocki, Timo, Frank Rieger, Dimitrios Ernst Tsokaktsidis, and Frank Gauterin. "Generating Component Designs for an Improved NVH Performance by Using an Artificial Neural Network as an Optimization Metamodel." Designs 5, no. 2 (June 3, 2021): 36. http://dx.doi.org/10.3390/designs5020036.
Full textAbstract:
In modern vehicle development, suspension components have to meet many boundary conditions. In noise, vibration, and harshness (NVH) development these are for example eigenfrequencies and frequency response function (FRF) amplitudes. Component geometry parameters, for example kinematic hard points, often affect multiple of these targets in a non intuitive way. In this article, we present a practical approach to find optimized parameters for a component design, which fulfills an FRF target curve. By morphing an initial component finite element model we create training data for an artificial neural network (ANN) which predicts FRFs from geometry parameter input. Then the ANN serves as a metamodel for an evolutionary algorithm optimizer which identifies fitting geometry parameter sets, meeting an FRF target curve. The methodology enables a component design which considers an FRF as a component target. In multiple simulation examples we demonstrate the capability of identifying component designs modifying specific eigenfrequency or amplitude features of the FRFs.
38
Abbaszadeh, Peyman, Atieh Alipour, and Shahrokh Asadi. "Development of a coupled wavelet transform and evolutionary Levenberg-Marquardt neural networks for hydrological process modeling." Computational Intelligence 34, no. 1 (June 28, 2017): 175–99. http://dx.doi.org/10.1111/coin.12124.
Full text
39
Bede-Fazekas, Ákos. "Modeling the Impacts of Climate Change on Phytogeographical Units. A Case Study of the Moesz Line." Journal of Environmental Geography 6, no. 1-2 (April 1, 2013): 21–27. http://dx.doi.org/10.2478/v10326-012-0003-3.
Full textAbstract:
Abstract Regional climate models (RCMs) provide reliable climatic predictions for the next 90 years with high horizontal and temporal resolution. In the 21st century northward latitudinal and upward altitudinal shift of the distribution of plant species and phytogeographical units is expected. It is discussed how the modeling of phytogeographical unit can be reduced to modeling plant distributions. Predicted shift of the Moesz line is studied as case study (with three different modeling approaches) using 36 parameters of REMO regional climate dataset, ArcGIS geographic information software, and periods of 1961-1990 (reference period), 2011-2040, and 2041-2070. The disadvantages of this relatively simple climate envelope modeling (CEM) approach are then discussed and several ways of model improvement are suggested. Some statistical and artificial intelligence (AI) methods (logistic regression, cluster analysis and other clustering methods, decision tree, evolutionary algorithm, artificial neural network) are able to provide development of the model. Among them artificial neural networks (ANN) seems to be the most suitable algorithm for this purpose, which provides a black box method for distribution modeling.
40
Sarma, Jhumpa. "Role of Artificial Intelligence in Medicine and Clinical Research." International Journal for Research in Applied Science and Engineering Technology 9, no. 8 (August 31, 2021): 1512–18. http://dx.doi.org/10.22214/ijraset.2021.37617.
Full textAbstract:
Abstract: Artificial Intelligence is a branch of computer science that enables to analyse complex medical data. The proficiency of artificial intelligence techniques has been explored to a great extent in the field of medicine. Most of the medications go to the business sector after a long tedious process of drug development. It can take a period of 10-15 years or more to convey a medication from its introductory revelation to the hands of the patients. Artificial Intelligence can significantly reduce the time required and can also cut down the expenses by half. Among the methods, artificial neural network is the most widely used analytical tool while other techniques like fuzzy expert systems, natural language processing, robotic process automation and evolutionary computation have been used in different clinical settings. The aim of this paper is to discuss the different artificial intelligence techniques and provide a perspective on the benefits, future opportunities and risks of established artificial intelligence applications in clinical practice on medical education, physicians, healthcare institutions and bioethics. Keywords: Artificial intelligence, clinical trials, medical technologies, artificial neural networks, diagnosis.
41
Xu, Qi, Hubin Liu, Yulong Liu, and Shan Wu. "Innovative Design of Intangible Cultural Heritage Elements in Fashion Design Based on Interactive Evolutionary Computation." Mathematical Problems in Engineering 2021 (June 7, 2021): 1–11. http://dx.doi.org/10.1155/2021/9913161.
Full textAbstract:
The application of intangible cultural heritage cultural elements and traditional crafts in modern design, especially in modern fashion design, is not to flatter the public but to integrate the artistic language of intangible cultural heritage into modern fashion on the basis of deeply understanding the connotation of intangible cultural heritage and mastering its traditional crafts, so as to meet people’s demand for fashion and aesthetics. It can also promote the inheritance and development of traditional intangible cultural heritage culture and technology. The purpose of this study is to analyze the intangible cultural heritage elements in the innovative design of fashion design by using interactive evolutionary computation. According to the composition characteristics of cultural elements, this research uses interactive evolutionary calculation to analyze the current status of intangible cultural heritage elements in clothing design. Then, 30 fashion designers are selected to evaluate the design situation and judge the effect of the method on the design. The results show that the neural network has evaluated 36 generations, that is, 256 times of moderate value. Compared with the general IGA algorithm, adding neural network IGA can reduce the fatigue caused by user reference score and improve the quality of the optimal solution, and the cultural image attributes whose perception frequency is more than 50% are favored. It is concluded that the research method in the intangible cultural heritage elements in fashion design can improve user satisfaction and the effect is good. This research contributes to the application of intelligent algorithm in the field of fashion design.
42
Kakoudakis, Konstantinos, Raziyeh Farmani, and David Butler. "Pipeline failure prediction in water distribution networks using weather conditions as explanatory factors." Journal of Hydroinformatics 20, no. 5 (July 25, 2018): 1191–200. http://dx.doi.org/10.2166/hydro.2018.152.
Full textAbstract:
Abstract This paper examines the impact of weather conditions on pipe failure in water distribution networks using artificial neural network (ANN) and evolutionary polynomial regression (EPR). A number of weather-related factors over 4 consecutive days are the input of the binary ANN model while the output is the occurrence or not of at least a failure during the following 2 days. The model is able to correctly distinguish the majority (87%) of the days with failure(s). The EPR is employed to predict the annual number of failures. Initially, the network is divided into six clusters based on pipe diameter and age. The last year of the monitoring period is used for testing while the remaining years since the beginning are retained for model development. An EPR model is developed for each cluster based on the relevant training data. The results indicate a strong relationship between the annual number of failures and frequency and intensity of low temperatures. The outputs from the EPR models are used to calculate the failures of the homogenous groups within each cluster proportionally to their length.
43
Ghalambaz, Nasim, Jabbar Ganji, and Pejman Shabani. "The development of a neural network model for the structural improvement of perovskite solar cells using an evolutionary particle swarm optimization algorithm." Journal of Computational Electronics 20, no. 2 (January 19, 2021): 966–73. http://dx.doi.org/10.1007/s10825-020-01654-8.
Full text
44
Szilágyi, András, István Zachar, Anna Fedor, Harold P. de Vladar, and Eörs Szathmáry. "Breeding novel solutions in the brain: a model of Darwinian neurodynamics." F1000Research 5 (September 28, 2016): 2416. http://dx.doi.org/10.12688/f1000research.9630.1.
Full textAbstract:
Background: The fact that surplus connections and neurons are pruned during development is well established. We complement this selectionist picture by a proof-of-principle model of evolutionary search in the brain, that accounts for new variations in theory space. We present a model for Darwinian evolutionary search for candidate solutions in the brain. Methods: We combine known components of the brain – recurrent neural networks (acting as attractors), the action selection loop and implicit working memory – to provide the appropriate Darwinian architecture. We employ a population of attractor networks with palimpsest memory. The action selection loop is employed with winners-share-all dynamics to select for candidate solutions that are transiently stored in implicit working memory. Results: We document two processes: selection of stored solutions and evolutionary search for novel solutions. During the replication of candidate solutions attractor networks occasionally produce recombinant patterns, increasing variation on which selection can act. Combinatorial search acts on multiplying units (activity patterns) with hereditary variation and novel variants appear due to (i) noisy recall of patterns from the attractor networks, (ii) noise during transmission of candidate solutions as messages between networks, and, (iii) spontaneously generated, untrained patterns in spurious attractors. Conclusions: Attractor dynamics of recurrent neural networks can be used to model Darwinian search. The proposed architecture can be used for fast search among stored solutions (by selection) and for evolutionary search when novel candidate solutions are generated in successive iterations. Since all the suggested components are present in advanced nervous systems, we hypothesize that the brain could implement a truly evolutionary combinatorial search system, capable of generating novel variants.
45
Szilágyi, András, István Zachar, Anna Fedor, Harold P. de Vladar, and Eörs Szathmáry. "Breeding novel solutions in the brain: A model of Darwinian neurodynamics." F1000Research 5 (June 29, 2017): 2416. http://dx.doi.org/10.12688/f1000research.9630.2.
Full textAbstract:
Background: The fact that surplus connections and neurons are pruned during development is well established. We complement this selectionist picture by a proof-of-principle model of evolutionary search in the brain, that accounts for new variations in theory space. We present a model for Darwinian evolutionary search for candidate solutions in the brain. Methods: We combine known components of the brain – recurrent neural networks (acting as attractors), the action selection loop and implicit working memory – to provide the appropriate Darwinian architecture. We employ a population of attractor networks with palimpsest memory. The action selection loop is employed with winners-share-all dynamics to select for candidate solutions that are transiently stored in implicit working memory. Results: We document two processes: selection of stored solutions and evolutionary search for novel solutions. During the replication of candidate solutions attractor networks occasionally produce recombinant patterns, increasing variation on which selection can act. Combinatorial search acts on multiplying units (activity patterns) with hereditary variation and novel variants appear due to (i) noisy recall of patterns from the attractor networks, (ii) noise during transmission of candidate solutions as messages between networks, and, (iii) spontaneously generated, untrained patterns in spurious attractors. Conclusions: Attractor dynamics of recurrent neural networks can be used to model Darwinian search. The proposed architecture can be used for fast search among stored solutions (by selection) and for evolutionary search when novel candidate solutions are generated in successive iterations. Since all the suggested components are present in advanced nervous systems, we hypothesize that the brain could implement a truly evolutionary combinatorial search system, capable of generating novel variants.
46
Onisawa, Takehisa. "Special Issue on Selected Papers in SCIS & ISIS 2004 – No.2." Journal of Advanced Computational Intelligence and Intelligent Informatics 9, no. 3 (May 20, 2005): 225. http://dx.doi.org/10.20965/jaciii.2005.p0225.
Full textAbstract:
The Joint Conference of the 2nd International Conference on Soft Computing and Intelligent Systems and the 5th International Symposium on Advanced Intelligent Systems (SCIS & ISIS 2004) held at Keio University in Yokohama, Japan, on September 21-24, 2004, attracted over 300 papers in fields such as mathematics, urban and transport planning, entertainment, intelligent control, learning, image processing, clustering, neural networks applications, evolutionary computation, system modeling, fuzzy measures, and robotics. The Program Committee requested reviewers in SCIS & ISIS 2004 to select papers for a special issue of the Journal of Advanced Computational Intelligence & Intelligent Informatics (JACIII), with 27 papers accepted for publication in a two-part SCIS & ISIS 2004 special – Vol.9, No.2, containing 13 and the second part containing 14. Paper 1 details tap-changer control using neural networks. Papers 2-5 deal with image processing and recognition – Paper 2 proposing a model of saliency-driven scene learning and recognition and applying its model to robotics, paper 3 discussing breast cancer recognition using evolutionary algorithms, paper 4 covering a revised GMDH-typed neural network model applied to medical image recognition, paper 5 presenting how to compensate for missing information in the acquisition of visual information applied to autonomous soccer robot control. Paper 6 details gene expressions networks for 4 fruit fly development stages. Paper 7 proposes an α-constrained particle swarm optimized for solving constrained optimization problem. Paper 8 develops a fuzzy-neuro multilayer perceptron using genetic algorithms for recognizing odor mixtures. Paper 9 discusses how to integrate symbols into neural networks for the fusion of computational and symbolic processing and its effectiveness demonstrated through simulations. Paper 10 proposes an electric dictionary using a set of nodes and links whose usefulness is verified in experiments. Paper 11 presents a multi-agent algorithm for a class scheduling problem, showing its feasibility through computer simulation. Paper 12 proposes inductive temporal formula specification in system verification, reducing memory and time in the task of system verification. Paper 13 applies an agent-based approach to modeling transport using inductive learning by travelers and an evolutionary approach. The last paper analyzes architectural floor plans using a proposed index classifying floor plans from the user's point of view. We thank reviewers for their time and effort in making these special issues available so quickly, and thank the JACIII editorial board, especially Editor-in-Chief Profs. Hirota and Fukuda and Managing Editor Kenta Uchino, for their invaluable aid and advice in putting these special issues together.
47
Astor, J. C., and C. Adami. "A Developmental Model for the Evolution of Artificial Neural Networks." Artificial Life 6, no. 3 (July 2000): 189–218. http://dx.doi.org/10.1162/106454600568834.
Full textAbstract:
We present a model of decentralized growth and development for artificial neural networks (ANNs), inspired by developmental biology and the physiology of nervous systems. In this model, each individual artificial neuron is an autonomous unit whose behavior is determined only by the genetic information it harbors and local concentrations of substrates. The chemicals and substrates, in turn, are modeled by a simple artificial chemistry. While the system is designed to allow for the evolution of complex networks, we demonstrate the power of the artificial chemistry by analyzing engineered (handwritten) genomes that lead to the growth of simple networks with behaviors known from physiology. To evolve more complex structures, a Java-based, platform-independent, asynchronous, distributed genetic algorithm (GA) has been implemented that allows users to participate in evolutionary experiments via the World Wide Web.
48
ROHLF, THIMO, and CHRISTOPHER R. WINKLER. "EMERGENT NETWORK STRUCTURE, EVOLVABLE ROBUSTNESS, AND NONLINEAR EFFECTS OF POINT MUTATIONS IN AN ARTIFICIAL GENOME MODEL." Advances in Complex Systems 12, no. 03 (June 2009): 293–310. http://dx.doi.org/10.1142/s0219525909002210.
Full textAbstract:
Genetic regulation is a key component in development, but a clear understanding of the structure and dynamics of genetic networks is not yet at hand. In this paper we investigate these properties within an artificial genome model originally introduced by Reil [Proc. 5th European Conf. Artificial Life (Springer, 1999), pp. 457–466]. We analyze statistical properties of randomly generated genomes both on the sequence and network level, and show that this model correctly predicts the frequency of genes in genomes as found in experimental data. Using an evolutionary algorithm based on stabilizing selection for a phenotype, we show that dynamical robustness against single base mutations, as against random changes in initial states of regulatory dynamics that mimic stochastic fluctuations in environmental conditions, can emerge in parallel. Point mutations at the sequence level can have strongly nonlinear effects on network wiring, including structurally neutral mutations and simultaneous rewiring of multiple connections, which occasionally lead to strong reorganization of the attractor landscape and metastability of evolutionary dynamics. Similar to real genomes, evolved artificial genomes exhibit both highly conserved regions, as well as regions that are characterized by a high rate of accepted base substitutions.
49
Wang, Xu, and Shi Fei Ding. "An Overview of Quotient Space Theory." Advanced Materials Research 187 (February 2011): 326–31. http://dx.doi.org/10.4028/www.scientific.net/amr.187.326.
Full textAbstract:
Granular computing (GrC) is another solving method of artificial intelligence problems after neural network, fuzzy set theory, genetic algorithm, evolutionary algorithm and so on. GrC involves all the theories, methodologies and techniques of granularity, providing a powerful tool for the solution of complex problems, massive data mining, and fuzzy information processing. Quotient space theory is a representative model of granular computing. In this paper, first the current situation and the development prospects of quotient space theory are introduced, then the basic theory of quotient space granular computing are presented and the stratified and synthesis principle of granularity are summarized. Finally we discuss some important issues such as the application and promotion of quotient space
50
Schmickl, Thomas, Payam Zahadat, and Heiko Hamann. "Wankelmut: A Simple Benchmark for the Evolvability of Behavioral Complexity." Applied Sciences 11, no. 5 (February 24, 2021): 1994. http://dx.doi.org/10.3390/app11051994.
Full textAbstract:
In evolutionary robotics, an encoding of the control software that maps sensor data (input) to motor control values (output) is shaped by stochastic optimization methods to complete a predefined task. This approach is assumed to be beneficial compared to standard methods of controller design in those cases where no a priori model is available that could help to optimize performance. For robots that have to operate in unpredictable environments as well, an evolutionary robotics approach is favorable. We present here a simple-to-implement, but hard-to-pass benchmark to allow for quantifying the “evolvability” of such evolving robot control software towards increasing behavioral complexity. We demonstrate that such a model-free approach is not a free lunch, as already simple tasks can be unsolvable barriers for fully open-ended uninformed evolutionary computation techniques. We propose the “Wankelmut” task as an objective for an evolutionary approach that starts from scratch without pre-shaped controller software or any other informed approach that would force the behavior to be evolved in a desired way. Our main claim is that “Wankelmut” represents the simplest set of problems that makes plain-vanilla evolutionary computation fail. We demonstrate this by a series of simple standard evolutionary approaches using different fitness functions and standard artificial neural networks, as well as continuous-time recurrent neural networks. All our tested approaches failed. From our observations, we conclude that other evolutionary approaches will also fail if they do not per se favor or enforce the modularity of the evolved structures and if they do not freeze or protect already evolved functionalities from being destroyed again in the later evolutionary process. However, such a protection would require a priori knowledge of the solution of the task and contradict the “no a priori model” approach that is often claimed in evolutionary computation. Thus, we propose a hard-to-pass benchmark in order to make a strong statement for self-complexifying and generative approaches in evolutionary computation in general and in evolutionary robotics specifically. We anticipate that defining such a benchmark by seeking the simplest task that causes the evolutionary process to fail can be a valuable benchmark for promoting future development in the fields of artificial intelligence, evolutionary robotics, and artificial life.