Filters








66,748 Hits in 2.6 sec

Inference of S-system models of genetic networks using Product Unit Neural Networks

Hiroaki Murata, Makoto Koshino, Masatomo Mitamura, Haruhiko Kimura
2008 Conference Proceedings / IEEE International Conference on Systems, Man and Cybernetics  
The proposed method does not solve the differential equations, learns the genetic networks using Product-Unit-Neural-Network (PUNN) and infer the S-system model of genetic networks which describes a set  ...  In this study, we proposed the method of inference of genetic networks which expresses the regulation of genes.  ...  The NN model is the layered-neural-network learned the relational expression. 2) The inference method using NN model: The inference method using the NN model (call the NN model method) infers the genetic  ... 
doi:10.1109/icsmc.2008.4811480 dblp:conf/smc/MurataKMK08 fatcat:7wfysx3zgfgsfiqqx4m6webnea

Inference of Genetic Regulatory Networks with Recurrent Neural Network Models Using Particle Swarm Optimization

Rui Xu, D.C. Wunsch, R.L. Frank
2007 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
We propose a recurrent neural network (RNN) and particle swarm optimization (PSO) approach to infer genetic regulatory networks from time series gene expression data.  ...  Genetic regulatory network inference is critically important for revealing fundamental cellular processes, investigating gene functions, and understanding their relations.  ...  Although Inference of Genetic Regulatory Networks with Recurrent Neural Network Models Using Particle Swarm Optimization regulation of gene expression can occur at any step along the cellular information  ... 
doi:10.1109/tcbb.2007.1057 pmid:17975278 fatcat:ykiestf7u5aafn2wr7yi5kdntm

Function Approximation Approach to the Inference of Neural Network Models of Genetic Networks

Shuhei Kimura, Katsuki Sonoda, Soichiro Yamane, Koki Matsumura, Mariko Hatakeyama
2007 IPSJ Digital Courier  
In this study, we propose a new method for the inference of genetic networks. To describe genetic networks, the proposed method does not use models of the fixed form, but uses neural network models.  ...  Most of these inference methods use models based on a set of differential equations of the fixed form to describe genetic networks.  ...  On the basis of this problem definition, we proposed a new method to infer neural network models of genetic networks.  ... 
doi:10.2197/ipsjdc.3.153 fatcat:ldnqmb46kjbflbwbcxgnzlulsa

Inference of Genetic Network Using the Expression Profile Time Course Data of Mouse P19 Cells

Yukihiro Maki, Takanori Ueda, Masahiro Okamoto, Naoya Uematsu, Kentaro Inamura, Kazuhiko Uchida, Yoriko Takahashi, Yukihiro Eguchi
2002 Genome Informatics Series  
Using gene expression profiles during neural differentiation of P19 EC cells using mouse cDNA microarray containing of 15,000 genes, and we applied S-system model for inference of genetic network from  ...  We shall demonstrate that this strategy is useful and powerful to infer the genetic network during neural differentiation. Step-by-step strategy for the inference of a large-scale genetic network.  ... 
doi:10.11234/gi1990.13.382 fatcat:s65baa266nbttkwxx3xxpcmsna

Genetic optimization of neural network and fuzzy logic for oil bubble point pressure modeling

Mohammad Afshar, Amin Gholami, Mojtaba Asoodeh
2014 Korean Journal of Chemical Engineering  
The present study went further by optimizing fuzzy logic and neural network models using the genetic algorithm in charge of eliminating the risk of being exposed to local minima.  ...  Neural network and adaptive neuro-fuzzy inference system are powerful tools for extracting the underlying dependency of a set of input/output data.  ...  CASE STUDY Neural Network Model and Genetic Optimized Neural Network A three-layered neural network with back-propagation algorithm was used for construction of an intelligent model which is meant  ... 
doi:10.1007/s11814-013-0248-8 fatcat:ztinxjkvrzhpha7bdkeady4dfi

Hybrid Soft Computing for PVT Properties Prediction

Lahouari Ghouti, Saeed Al-Bukhitan
2010 The European Symposium on Artificial Neural Networks  
In this paper, a genetic-neuro-fuzzy inference system is proposed for estimating PVT properties of crude oil systems.  ...  These achievements of neural networks open the door to data mining techniques to play a major role in oil and gas industry.  ...  Acknowledgment The authors would like to thank King Fahd University of Petroleum and Minerals for supporting this research.  ... 
dblp:conf/esann/LahouariA10 fatcat:xvtmx3dj5vhive5wl772iouwi4

Genetic regulatory network inference using Recurrent Neural Networks trained by a multi agent system

Adel Ghazikhani, T. Mohammad Reza Akbarzadeh, Reza Monsefi
2011 2011 1st International eConference on Computer and Knowledge Engineering (ICCKE)  
Timeseries data has been frequently used for GRN modeling. Due to the function approximation and feedback nature of GRN, a Recurrent Neural Network (RNN) model is used.  ...  We propose a novel algorithm for gene regulatory network inference. Gene Regulatory Network (GRN) inference is approximating the combined effect of different genes in a specific genome data.  ...  The main form of data for GRN inference is Microarrays [1]. Much research has been done on GRN learning. One of the first methods used for GRN learning was neural networks.  ... 
doi:10.1109/iccke.2011.6413332 fatcat:xww5p6cvyba25hcp3om226fqjq

Enabling external factors for consumption electricity forecasting using hybrid genetic algorithm and fuzzy neural system

Gayatri Dwi Santika
2017 2017 4th International Conference on Computer Applications and Information Processing Technology (CAIPT)  
By using two phase on Fuzzy Inference system and Genetic algorithm for optimization, weight can improve the accuracy of electricity load forecasting.  ...  Data for a monthly load of five years has been used. The accuracy algorithm has been validated using Root Mean Square Error (RMSE).  ...  First, the use of Genetic Algorithms on neural network is used to avoid local optimum on neural network. Implement of GA is present in the input and output weights NN.  ... 
doi:10.1109/caipt.2017.8320708 fatcat:5ishfekuynenlo4lncvqti7hvy

A Hybrid System Composed of Neural Networks and Genetic Algorithms

Dumitrescu Mihaela
2012 International Journal of Asian Business and Information Management  
Thus, in neural network design can be used technology of genetic algorithms to get better results.  ...  They are connected and to build a neural network architecture is a complex activity. A neural network model can be applied to economic forecasting using back-propagation method.  ... 
doi:10.4018/jabim.2012100105 fatcat:5obtxkfkbzc3dmxil3iytcuf6y

A Comparison Study between Inferred State-Space and Neural Network Based System Identifications Using Adaptive Genetic Algorithm for Unmanned Helicopter Model

Ahmed Hosny
2012 The International Conference on Electrical Engineering  
In other words the number of inputs used in the genetic algorithm to obtain an inferred state space is almost one third of the number of inputs needed to develop the multi-layer recurrent neural network  ...  In this work an optimization approach was used to conclude an inferred state space and the multiple neural networks system identifications based on the genetic algorithms separately.  ...  This can be avoided by using black-box methods such as the neural networks.  ... 
doi:10.21608/iceeng.2012.30807 fatcat:3qrxcsbue5hlfnzcv4eafee2c4

Learning Efficient Deep Feature Representations via Transgenerational Genetic Transmission of Environmental Information During Evolutionary Synthesis of Deep Neural Networks

M. J. Shafiee, E. Barshan, F. Li, B. Chwyl, M. Karg, C. Scharfenberger, A. Wong
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
The computational complexity of deep neural networks for extracting deep features is a significant barrier to widespread adoption, particularly for use in embedded devices.  ...  synapses during training to favor the synthesis of more efficient deep neural networks over successive generations.  ...  More specifically, the architectural traits of a deep neural network are modeled by synaptic probability models that can be considered as the probabilistic 'DNA', and that are used to mimic heredity to  ... 
doi:10.1109/iccvw.2017.120 dblp:conf/iccvw/ShafieeBLCKSW17 fatcat:jfqjnwnmprcjtbqgem2nrihbmq

Genetically Optimized Hybrid Fuzzy Neural Networks Based on Simplified Fuzzy Inference Rules and Polynomial Neurons [chapter]

Sung-Kwun Oh, Byoung-Jun Park, Witold Pedrycz, Tae-Chon Ahn
2005 Lecture Notes in Computer Science  
We introduce an advanced architecture of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) and develop a comprehensive design methodology supporting their construction.  ...  The gHFNN architecture results from a synergistic usage of the hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN).  ...  This work has been supported by KESRI(R-2004-B-133-01), which is funded by MOCIE(Ministry of commerce, industry and energy). Genetically Optimized Hybrid Fuzzy Neural Networks  ... 
doi:10.1007/11428831_99 fatcat:5ueqauarozau3e6hq5sh2vbiva

Information Granulation-Based Multi-layer Hybrid Fuzzy Neural Networks: Analysis and Design [chapter]

Byoung-Jun Park, Sung-Kwun Oh, Witold Pedrycz, Tae-Chon Ahn
2004 Lecture Notes in Computer Science  
In this study, a new architecture and comprehensive design methodology of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) are introduced and a series of numeric experiments are carried out.  ...  FNN contributes to the formation of the premise part of the overall network structure of the gHFNN. The consequence part of the gHFNN is designed using PNN.  ...  Fuzzy Neural Networks and Genetic Optimization We use FNN based on two types of fuzzy inferences, that is, simplified (Scheme I) and linear fuzzy inference-based FNN (Scheme II) as shown in Fig. 1 .  ... 
doi:10.1007/978-3-540-24687-9_24 fatcat:lsjepduoone4vaonh5nrwbr3de

A Neuro-fuzzy Logic Model Application for Predicting the Result of a Football Match

Uzochukwu C. Onwuachu, Promise Enyindah
2022 European Journal of Electrical Engineering and Computer Science  
The suggested model comprises two phases: the first utilizes a neural network model to generate the primary factors that impact team performance; the second phase uses a neural network model to generate  ...  In the second phase, a fuzzy logic model is used to forecast the outcome of a football match. MatLab 2008 was used to simulate the proposed system.  ...  It also raises interest of researchers [5] , in other to solve the prediction problem we explore the use of advanced non-linear modeling techniques such as neural networks and fuzzy logic model [12]  ... 
doi:10.24018/ejece.2022.6.1.400 fatcat:xgihqwrrq5ggdbd7ozwt7irwzi

Exploring the Imposition of Synaptic Precision Restrictions For Evolutionary Synthesis of Deep Neural Networks [article]

Mohammad Javad Shafiee, Francis Li, Alexander Wong
2017 arXiv   pre-print
of deep neural networks, leading to significant improvements in modeling accuracy.  ...  We explore the synaptogenesis of deep neural networks in the formation of efficient deep neural network architectures within an evolutionary deep intelligence framework, where a probabilistic generative  ...  The genetic encoding of a deep neural network is represented by a synaptic probability model, which can be viewed as the 'DNA' of the network and is used to mimic the notion of heredity.  ... 
arXiv:1707.00095v1 fatcat:i25ncpaizbcwxjpiugqjshtzc4
« Previous Showing results 1 — 15 out of 66,748 results