Search results for: Bi-directional associative memory (BAM) neural networks
2726 Dual-Network Memory Model for Temporal Sequences
Authors: Motonobu Hattori, Rina Suzuki
Abstract:
In neural networks, when new patters are learned by a network, they radically interfere with previously stored patterns. This drawback is called catastrophic forgetting. We have already proposed a biologically inspired dual-network memory model which can much reduce this forgetting for static patterns. In this model, information is first stored in the hippocampal network, and thereafter, it is transferred to the neocortical network using pseudopatterns. Because temporal sequence learning is more important than static pattern learning in the real world, in this study, we improve our conventional dual-network memory model so that it can deal with temporal sequences without catastrophic forgetting. The computer simulation results show the effectiveness of the proposed dual-network memory model.
Keywords: Catastrophic forgetting, dual-network, temporal sequences.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14162725 Exponential Passivity Criteria for BAM Neural Networks with Time-Varying Delays
Authors: Qingqing Wang, Baocheng Chen, Shouming Zhong
Abstract:
In this paper,the exponential passivity criteria for BAM neural networks with time-varying delays is studied.By constructing new Lyapunov-Krasovskii functional and dividing the delay interval into multiple segments,a novel sufficient condition is established to guarantee the exponential stability of the considered system.Finally,a numerical example is provided to illustrate the usefulness of the proposed main results
Keywords: BAM neural networks, Exponential passivity, LMI approach, Time-varying delays.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18972724 Neural Network Imputation in Complex Survey Design
Authors: Safaa R. Amer
Abstract:
Missing data yields many analysis challenges. In case of complex survey design, in addition to dealing with missing data, researchers need to account for the sampling design to achieve useful inferences. Methods for incorporating sampling weights in neural network imputation were investigated to account for complex survey designs. An estimate of variance to account for the imputation uncertainty as well as the sampling design using neural networks will be provided. A simulation study was conducted to compare estimation results based on complete case analysis, multiple imputation using a Markov Chain Monte Carlo, and neural network imputation. Furthermore, a public-use dataset was used as an example to illustrate neural networks imputation under a complex survey design
Keywords: Complex survey, estimate, imputation, neural networks, variance.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19612723 Exponential State Estimation for Neural Networks with Leakage, Discrete and Distributed Delays
Authors: Liyuan Wang, Shouming Zhong
Abstract:
In this paper, the design problem of state estimator for neural networks with the mixed time-varying delays are investigated by constructing appropriate Lyapunov-Krasovskii functionals and using some effective mathematical techniques. In order to derive several conditions to guarantee the estimation error systems to be globally exponential stable, we transform the considered systems into the neural-type time-delay systems. Then with a set of linear inequalities(LMIs), we can obtain the stable criteria. Finally, three numerical examples are given to show the effectiveness and less conservatism of the proposed criterion.
Keywords: State estimator, Neural networks, Globally exponential stability.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16552722 Identity Formation and Autobiographical Memory: Two Interrelated Concepts of Development
Authors: Anna R. Alyusheva, Veronika V. Nourkova
Abstract:
The aim of the present paper is to investigate the interdependency among ego-identity status, autobiographical memory and cultural life story schema. The study shows considerable differences between autobiographical memory characteristics and “family script", which is typical for participants (adolescents, M age years = 17.84, SD = 1.18, N = 58), with different ego-identity statuses. Participants with diffused ego-identity status recalled fewer autobiographical memories. Additionally, this group of participants recalled fewer events from their parents- life. Participants with moratorium ego-identity status dated their first recollections to a later age than others, and recalled fewer memories relating to their childhood. Participants with achieved identity status recalled more self-defining memories and events from their parents- life. They used more functions from the autobiographical memory. There weren-t any significant differences between the foreclosed identity status group and the others. These findings support the idea of a bidirectional relation between culture, memory and self.Keywords: Autobiographical memory, autobiographical narrative, cultural life script, ego-identity
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22572721 Globally Exponential Stability for Hopfield Neural Networks with Delays and Impulsive Perturbations
Authors: Adnene Arbi, Chaouki Aouiti, Abderrahmane Touati
Abstract:
In this paper, we consider the global exponential stability of the equilibrium point of Hopfield neural networks with delays and impulsive perturbation. Some new exponential stability criteria of the system are derived by using the Lyapunov functional method and the linear matrix inequality approach for estimating the upper bound of the derivative of Lyapunov functional. Finally, we illustrate two numerical examples showing the effectiveness of our theoretical results.
Keywords: Hopfield Neural Networks, Exponential stability.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 23382720 Representing Collective Unconsciousness Using Neural Networks
Authors: Pierre Abou-Haila, Richard Hall, Mark Dawes
Abstract:
Instead of representing individual cognition only, population cognition is represented using artificial neural networks whilst maintaining individuality. This population network trains continuously, simulating adaptation. An implementation of two coexisting populations is compared to the Lotka-Volterra model of predator-prey interaction. Applications include multi-agent systems such as artificial life or computer games.
Keywords: Collective unconsciousness, neural networks, adaptation, predator-prey simulation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18102719 Existence and Stability Analysis of Discrete-time Fuzzy BAM Neural Networks with Delays and Impulses
Authors: Chao Wang, Yongkun Li
Abstract:
In this paper, the discrete-time fuzzy BAM neural network with delays and impulses is studied. Sufficient conditions are obtained for the existence and global stability of a unique equilibrium of this class of fuzzy BAM neural networks with Lipschitzian activation functions without assuming their boundedness, monotonicity or differentiability and subjected to impulsive state displacements at fixed instants of time. Some numerical examples are given to demonstrate the effectiveness of the obtained results.
Keywords: Discrete-time fuzzy BAM neural networks, ımpulses, global exponential stability, global asymptotical stability, equilibrium point.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14932718 Self-evolving Neural Networks Based On PSO and JPSO Algorithms
Authors: Abdussamad Ismail, Dong-Sheng Jeng
Abstract:
A self-evolution algorithm for optimizing neural networks using a combination of PSO and JPSO is proposed. The algorithm optimizes both the network topology and parameters simultaneously with the aim of achieving desired accuracy with less complicated networks. The performance of the proposed approach is compared with conventional back-propagation networks using several synthetic functions, with better results in the case of the former. The proposed algorithm is also implemented on slope stability problem to estimate the critical factor of safety. Based on the results obtained, the proposed self evolving network produced a better estimate of critical safety factor in comparison to conventional BPN network.
Keywords: Neural networks, Topology evolution, Particle swarm optimization.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17962717 A Model-following Adaptive Controller for Linear/Nonlinear Plantsusing Radial Basis Function Neural Networks
Authors: Yuichi Masukake, Yoshihisa Ishida
Abstract:
In this paper, we proposed a method to design a model-following adaptive controller for linear/nonlinear plants. Radial basis function neural networks (RBF-NNs), which are known for their stable learning capability and fast training, are used to identify linear/nonlinear plants. Simulation results show that the proposed method is effective in controlling both linear and nonlinear plants with disturbance in the plant input.Keywords: Linear/nonlinear plants, neural networks, radial basisfunction networks.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14702716 Investigation of Artificial Neural Networks Performance to Predict Net Heating Value of Crude Oil by Its Properties
Authors: Mousavian, M. Moghimi Mofrad, M. H. Vakili, D. Ashouri, R. Alizadeh
Abstract:
The aim of this research is to use artificial neural networks computing technology for estimating the net heating value (NHV) of crude oil by its Properties. The approach is based on training the neural network simulator uses back-propagation as the learning algorithm for a predefined range of analytically generated well test response. The network with 8 neurons in one hidden layer was selected and prediction of this network has been good agreement with experimental data.
Keywords: Neural Network, Net Heating Value, Crude Oil, Experimental, Modeling.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15712715 Daily Global Solar Radiation Modeling Using Multi-Layer Perceptron (MLP) Neural Networks
Authors: Seyed Fazel Ziaei Asl, Ali Karami, Gholamreza Ashari, Azam Behrang, Arezoo Assareh, N.Hedayat
Abstract:
Predict daily global solar radiation (GSR) based on meteorological variables, using Multi-layer perceptron (MLP) neural networks is the main objective of this study. Daily mean air temperature, relative humidity, sunshine hours, evaporation, wind speed, and soil temperature values between 2002 and 2006 for Dezful city in Iran (32° 16' N, 48° 25' E), are used in this study. The measured data between 2002 and 2005 are used to train the neural networks while the data for 214 days from 2006 are used as testing data.
Keywords: Multi-layer Perceptron (MLP) Neural Networks;Global Solar Radiation (GSR), Meteorological Parameters, Prediction.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 29712714 Solving Partially Monotone Problems with Neural Networks
Authors: Marina Velikova, Hennie Daniels, Ad Feelders
Abstract:
In many applications, it is a priori known that the target function should satisfy certain constraints imposed by, for example, economic theory or a human-decision maker. Here we consider partially monotone problems, where the target variable depends monotonically on some of the predictor variables but not all. We propose an approach to build partially monotone models based on the convolution of monotone neural networks and kernel functions. The results from simulations and a real case study on house pricing show that our approach has significantly better performance than partially monotone linear models. Furthermore, the incorporation of partial monotonicity constraints not only leads to models that are in accordance with the decision maker's expertise, but also reduces considerably the model variance in comparison to standard neural networks with weight decay.Keywords: Mixture models, monotone neural networks, partially monotone models, partially monotone problems.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16112713 Stability Analysis of Impulsive Stochastic Fuzzy Cellular Neural Networks with Time-varying Delays and Reaction-diffusion Terms
Authors: Xinhua Zhang, Kelin Li
Abstract:
In this paper, the problem of stability analysis for a class of impulsive stochastic fuzzy neural networks with timevarying delays and reaction-diffusion is considered. By utilizing suitable Lyapunov-Krasovskii funcational, the inequality technique and stochastic analysis technique, some sufficient conditions ensuring global exponential stability of equilibrium point for impulsive stochastic fuzzy cellular neural networks with time-varying delays and diffusion are obtained. In particular, the estimate of the exponential convergence rate is also provided, which depends on system parameters, diffusion effect and impulsive disturbed intention. It is believed that these results are significant and useful for the design and applications of fuzzy neural networks. An example is given to show the effectiveness of the obtained results.
Keywords: Exponential stability, stochastic fuzzy cellular neural networks, time-varying delays, impulses, reaction-diffusion terms.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13652712 Fast Forecasting of Stock Market Prices by using New High Speed Time Delay Neural Networks
Authors: Hazem M. El-Bakry, Nikos Mastorakis
Abstract:
Fast forecasting of stock market prices is very important for strategic planning. In this paper, a new approach for fast forecasting of stock market prices is presented. Such algorithm uses new high speed time delay neural networks (HSTDNNs). The operation of these networks relies on performing cross correlation in the frequency domain between the input data and the input weights of neural networks. It is proved mathematically and practically that the number of computation steps required for the presented HSTDNNs is less than that needed by traditional time delay neural networks (TTDNNs). Simulation results using MATLAB confirm the theoretical computations.Keywords: Fast Forecasting, Stock Market Prices, Time Delay NeuralNetworks, Cross Correlation, Frequency Domain.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20572711 Mean Square Exponential Synchronization of Stochastic Neutral Type Chaotic Neural Networks with Mixed Delay
Authors: Zixin Liu, Huawei Yang, Fangwei Chen
Abstract:
This paper studies the mean square exponential synchronization problem of a class of stochastic neutral type chaotic neural networks with mixed delay. On the Basis of Lyapunov stability theory, some sufficient conditions ensuring the mean square exponential synchronization of two identical chaotic neural networks are obtained by using stochastic analysis and inequality technique. These conditions are expressed in the form of linear matrix inequalities (LMIs), whose feasibility can be easily checked by using Matlab LMI Toolbox. The feedback controller used in this paper is more general than those used in previous literatures. One simulation example is presented to demonstrate the effectiveness of the derived results.
Keywords: Exponential synchronization, stochastic analysis, chaotic neural networks, neutral type system.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15512710 Estimating Reaction Rate Constants with Neural Networks
Authors: Benedek Kovacs, Janos Toth
Abstract:
Solutions are proposed for the central problem of estimating the reaction rate coefficients in homogeneous kinetics. The first is based upon the fact that the right hand side of a kinetic differential equation is linear in the rate constants, whereas the second one uses the technique of neural networks. This second one is discussed deeply and its advantages, disadvantages and conditions of applicability are analyzed in the mirror of the first one. Numerical analysis carried out on practical models using simulated data, and our programs written in Mathematica.
Keywords: Neural networks, parameter estimation, linear regression, kinetic models, reaction rate coefficients.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19802709 Modeling and Analysis of Concrete Slump Using Hybrid Artificial Neural Networks
Authors: Vinay Chandwani, Vinay Agrawal, Ravindra Nagar
Abstract:
Artificial Neural Networks (ANN) trained using backpropagation (BP) algorithm are commonly used for modeling material behavior associated with non-linear, complex or unknown interactions among the material constituents. Despite multidisciplinary applications of back-propagation neural networks (BPNN), the BP algorithm possesses the inherent drawback of getting trapped in local minima and slowly converging to a global optimum. The paper present a hybrid artificial neural networks and genetic algorithm approach for modeling slump of ready mix concrete based on its design mix constituents. Genetic algorithms (GA) global search is employed for evolving the initial weights and biases for training of neural networks, which are further fine tuned using the BP algorithm. The study showed that, hybrid ANN-GA model provided consistent predictions in comparison to commonly used BPNN model. In comparison to BPNN model, the hybrid ANNGA model was able to reach the desired performance goal quickly. Apart from the modeling slump of ready mix concrete, the synaptic weights of neural networks were harnessed for analyzing the relative importance of concrete design mix constituents on the slump value. The sand and water constituents of the concrete design mix were found to exhibit maximum importance on the concrete slump value.
Keywords: Artificial neural networks, Genetic algorithms, Back-propagation algorithm, Ready Mix Concrete, Slump value.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 28912708 Neural Networks for Short Term Wind Speed Prediction
Authors: K. Sreelakshmi, P. Ramakanthkumar
Abstract:
Predicting short term wind speed is essential in order to prevent systems in-action from the effects of strong winds. It also helps in using wind energy as an alternative source of energy, mainly for Electrical power generation. Wind speed prediction has applications in Military and civilian fields for air traffic control, rocket launch, ship navigation etc. The wind speed in near future depends on the values of other meteorological variables, such as atmospheric pressure, moisture content, humidity, rainfall etc. The values of these parameters are obtained from a nearest weather station and are used to train various forms of neural networks. The trained model of neural networks is validated using a similar set of data. The model is then used to predict the wind speed, using the same meteorological information. This paper reports an Artificial Neural Network model for short term wind speed prediction, which uses back propagation algorithm.Keywords: Short term wind speed prediction, Neural networks, Back propagation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 30532707 Modeling and Prediction of Zinc Extraction Efficiency from Concentrate by Operating Condition and Using Artificial Neural Networks
Authors: S. Mousavian, D. Ashouri, F. Mousavian, V. Nikkhah Rashidabad, N. Ghazinia
Abstract:
PH, temperature and time of extraction of each stage, agitation speed and delay time between stages effect on efficiency of zinc extraction from concentrate. In this research, efficiency of zinc extraction was predicted as a function of mentioned variable by artificial neural networks (ANN). ANN with different layer was employed and the result show that the networks with 8 neurons in hidden layer has good agreement with experimental data.
Keywords: Zinc extraction, Efficiency, Neural networks, Operating condition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15772706 Power Forecasting of Photovoltaic Generation
Authors: S. H. Oudjana, A. Hellal, I. Hadj Mahammed
Abstract:
Photovoltaic power generation forecasting is an important task in renewable energy power system planning and operating. This paper explores the application of neural networks (NN) to study the design of photovoltaic power generation forecasting systems for one week ahead using weather databases include the global irradiance, and temperature of Ghardaia city (south of Algeria) using a data acquisition system. Simulations were run and the results are discussed showing that neural networks Technique is capable to decrease the photovoltaic power generation forecasting error.Keywords: Photovoltaic Power Forecasting, Regression, Neural Networks.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 37482705 A Sentence-to-Sentence Relation Network for Recognizing Textual Entailment
Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee
Abstract:
Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.Keywords: Deep neural models, natural language inference, recognizing textual entailment, sentence-to-sentence relation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14422704 Improving Co-integration Trading Rule Profitability with Forecasts from an Artificial Neural Network
Authors: Paul Lajbcygier, Seng Lee
Abstract:
Co-integration models the long-term, equilibrium relationship of two or more related financial variables. Even if cointegration is found, in the short run, there may be deviations from the long run equilibrium relationship. The aim of this work is to forecast these deviations using neural networks and create a trading strategy based on them. A case study is used: co-integration residuals from Australian Bank Bill futures are forecast and traded using various exogenous input variables combined with neural networks. The choice of the optimal exogenous input variables chosen for each neural network, undertaken in previous work [1], is validated by comparing the forecasts and corresponding profitability of each, using a trading strategy.
Keywords: Artificial neural networks, co-integration, forecasting, trading rule.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 12342703 Delay-Dependent Stability Analysis for Neural Networks with Distributed Delays
Authors: Qingqing Wang, Shouming Zhong
Abstract:
This paper deals with the problem of delay-dependent stability for neural networks with distributed delays. Some new sufficient condition are derived by constructing a novel Lyapunov-Krasovskii functional approach. The criteria are formulated in terms of a set of linear matrix inequalities, this is convenient for numerically checking the system stability using the powerful MATLAB LMI Toolbox. Moreover, in order to show the stability condition in this paper gives much less conservative results than those in the literature, numerical examples are considered.
Keywords: Neural networks, Globally asymptotic stability , LMI approach, Distributed delays.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15592702 Artificial Neural Network Approach for Short Term Load Forecasting for Illam Region
Authors: Mohsen Hayati, Yazdan Shirvany
Abstract:
In this paper, the application of neural networks to study the design of short-term load forecasting (STLF) Systems for Illam state located in west of Iran was explored. One important architecture of neural networks named Multi-Layer Perceptron (MLP) to model STLF systems was used. Our study based on MLP was trained and tested using three years (2004-2006) data. The results show that MLP network has the minimum forecasting error and can be considered as a good method to model the STLF systems.Keywords: Artificial neural networks, Forecasting, Multi-layer perceptron.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27582701 A New Recognition Scheme for Machine- Printed Arabic Texts based on Neural Networks
Authors: Z. Shaaban
Abstract:
This paper presents a new approach to tackle the problem of recognizing machine-printed Arabic texts. Because of the difficulty of recognizing cursive Arabic words, the text has to be normalized and segmented to be ready for the recognition stage. The new scheme for recognizing Arabic characters depends on multiple parallel neural networks classifier. The classifier has two phases. The first phase categories the input character into one of eight groups. The second phase classifies the character into one of the Arabic character classes in the group. The system achieved high recognition rate.
Keywords: Neural Networks, character recognition, feature extraction, multiple networks, Arabic text.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14692700 New PTH Moment Stable Criteria of Stochastic Neural Networks
Authors: Zixin Liu, Huawei Yang, Fangwei Chen
Abstract:
In this paper, the issue of pth moment stability of a class of stochastic neural networks with mixed delays is investigated. By establishing two integro-differential inequalities, some new sufficient conditions ensuring pth moment exponential stability are obtained. Compared with some previous publications, our results generalize some earlier works reported in the literature, and remove some strict constraints of time delays and kernel functions. Two numerical examples are presented to illustrate the validity of the main results.
Keywords: Neural networks, stochastic, PTH moment stable, time varying delays, distributed delays.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14582699 Exponential Stability and Periodicity of a Class of Cellular Neural Networks with Time-Varying Delays
Authors: Zixin Liu, Shu Lü, Shouming Zhong, Mao Ye
Abstract:
The problem of exponential stability and periodicity for a class of cellular neural networks (DCNNs) with time-varying delays is investigated. By dividing the network state variables into subgroups according to the characters of the neural networks, some sufficient conditions for exponential stability and periodicity are derived via the methods of variation parameters and inequality techniques. These conditions are represented by some blocks of the interconnection matrices. Compared with some previous methods, the method used in this paper does not resort to any Lyapunov function, and the results derived in this paper improve and generalize some earlier criteria established in the literature cited therein. Two examples are discussed to illustrate the main results.
Keywords: Cellular neural networks, exponential stability, time varying delays, partitioned matrices, periodic solution.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15132698 A New Sufficient Conditions of Stability for Discrete Time Non-autonomous Delayed Hopfield Neural Networks
Authors: Adnene Arbi, Chaouki Aouiti, Abderrahmane Touati
Abstract:
In this paper, we consider the uniform asymptotic stability, global asymptotic stability and global exponential stability of the equilibrium point of discrete Hopfield neural networks with delays. Some new stability criteria for system are derived by using the Lyapunov functional method and the linear matrix inequality approach, for estimating the upper bound of Lyapunov functional derivative.
Keywords: Hopfield neural networks, uniform asymptotic stability, global asymptotic stability, exponential stability.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19552697 Causal Relation Identification Using Convolutional Neural Networks and Knowledge Based Features
Authors: Tharini N. de Silva, Xiao Zhibo, Zhao Rui, Mao Kezhi
Abstract:
Causal relation identification is a crucial task in information extraction and knowledge discovery. In this work, we present two approaches to causal relation identification. The first is a classification model trained on a set of knowledge-based features. The second is a deep learning based approach training a model using convolutional neural networks to classify causal relations. We experiment with several different convolutional neural networks (CNN) models based on previous work on relation extraction as well as our own research. Our models are able to identify both explicit and implicit causal relations as well as the direction of the causal relation. The results of our experiments show a higher accuracy than previously achieved for causal relation identification tasks.
Keywords: Causal relation identification, convolutional neural networks, natural Language Processing, Machine Learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2244