Search

Target-level sentiment analysis (TLSA) is a classification task to extract sentiments from targets in text. In this paper, we propose t arget-dependent c onvolutional n eural n etwork (TCNN) tailored to the task of TLSA. The TCNN leverages the distance information between the target word and its neighboring words to learn the importance of each word to the target. Experimental results show that the TCNN achieves state-of-the-art performance on both single- and multi-target datasets. Qualitative evaluations were conducted to demonstrate the limitations of previous TLSA methods and also to verify that distance information is crucial for TLSA. Furthermore, by exploiting a convolutional neural network (CNN), the TCNN trains six times faster per epoch than other baselines based on recurrent neural networks. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel Lebesgue-integral-based approach to investigate the stability for neural networks with additive time-varying delay components. Based on the Lebesgue integral theory, a new Lyapunov–Krasovskii functional (LKF), which involves Lebesgue integral terms, is constructed, and the corresponding stability theorem is derived. More information on the neuron activation functions and fewer matrix variables are involved in the constructed LKF. Then, on the basis of the above method, an improved stability criterion is developed. Compared with the existing results, the derived stability condition is with less conservatism and computational burden. Moreover, the obtained criterion is extended to study the system with a single time-varying delay. Finally, numerical examples are given to illustrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes a hybrid modeling approach based on two familiar non-linear methods of mathematical modeling; the group method of data handling (GMDH) and differential evolution (DE) population-based algorithm. The proposed method constructs a GMDH self-organizing network model of a population of promising DE solutions. The new hybrid implementation is then applied to modeling tool wear in milling operations and also applied to two representative time series prediction problems of exchange rates of three international currencies and the well-studied Box-Jenkins gas furnace process data. The results of the proposed DE–GMDH approach are compared with the results obtained by the standard GMDH algorithm and its variants. Results presented show that the proposed DE–GMDH algorithm appears to perform better than the standard GMDH algorithm and the polynomial neural network (PNN) model for the tool wear problem. For the exchange rate problem, the results of the proposed DE–GMDH algorithm are competitive with all other approaches except in one case. For the Box-Jenkins gas furnace data, the experimental results clearly demonstrates that the proposed DE–GMDH-type network outperforms the existing models both in terms of better approximation capabilities as well as generalization abilities. Consequently, this self-organizing modeling approach may be useful in modeling advanced manufacturing systems where it is necessary to model tool wear during machining operations, and in time series applications such as in prediction of time series exchange rate and industrial gas furnace problems. [Copyright &y& Elsevier]

Abstract: This paper addresses robust exponential stability as well as domains of attraction in a class of interval neural networks. A sufficient condition for an equilibrium point to be exponentially stable is established. And an estimate on the domains of attraction of exponentially stable equilibrium points is presented. Both the condition and the estimate are formulated in terms of the parameter intervals, the neurons’ activation functions and the equilibrium point. Hence, they are easily checkable. In addition, our results neither depend on monotonicity of the activation functions nor on coupling conditions between the neurons. Consequently, these results are of practical importance in evaluating the performance of interval associative memory networks. [Copyright &y& Elsevier]

Abstract: In this paper, we first sttidy the distribution of the zeros of a fourth degree exponential polynomial. Then we apply the obtained results to a neural network model consisting of four neurons with delays. By regarding the sum of the delays as a parameter, it is shown that under certain assumptions the steady state of the neural network model is absolutely stable. Under another set of conditions, there is a critical value of the delay, the steady state is stable when the parameter is less than the critical value and unstable when the parameter is greater than the critical value. Thus, oscillations via Hopf bifurcation occur at the steady state when the parameter passes through the critical value. Numerical simulations are presented to illustrate the results. [Copyright &y& Elsevier]

In this paper a modified algorithm is suggested for developing polynomial neural network (PN N) models. Optimal partial description (PD) modeling is introduced at each layer of the PNN expansion, a task accomplished using the orthogonal least squares (OLS) method. Based on the initial PD models determined by the polynomial order and the number of PD inputs, OLS selects the most significant regressor terms reducing the output error variance. The method produces PN N models exhibiting a high level of accuracy and superior generalization capabilities. Additionally, parsimonious models are obtained comprising a considerably smaller number of parameters compared to the ones generated by means of the conventional PNN algorithm. Three benchmark examples are elaborated, including modeling of the gas furnace process as well as the iris and wine classification problems. Extensive simulation results and comparison with other methods in the literature, demonstrate the effectiveness of the suggested modeling approach. [ABSTRACT FROM AUTHOR]

In this paper, exponential periodicity and stability of delayed neural networks is investigated. Without assuming the boundedness and differentiability of the activation functions, some new sufficient conditions ensuring existence and uniqueness of periodic solution for a general class of neural systems are obtained. The delayed Hopfield network, bidirectional associative memory network, and cellular neural network are special cases of the neural system model considered. [Copyright &y& Elsevier]

In this paper, we present a tabu search technique to approximately solve fuzzy optimization problems. We demonstrate the performance of the proposed method by applying it to an elementary fuzzy optimization problem. Other applications of the method to fuzzy linear programming, fuzzy regression and the training of fuzzy neural networks are also presented. [Copyright &y& Elsevier]