Search

An ontological extension on the frames in FrameNet is presented in this paper. The general conceptual relations between frame elements, in conjunction with existing characteristics of this lexical resource, suggest more sophisticated semantic analysis of lexical chains (e.g. predicate chains) exploited in many text understanding applications. In particular, we have investigated its benefit for meaning-aware question answering when combined with an inference strategy. The proposed knowledge representation mechanism on the frame elements of FrameNet has been shown to have an impact on answering natural language questions on the basis of our case analysis. [ABSTRACT FROM AUTHOR]

The traditional method for estimation of the parameters of Hidden Markov Model (HMM) based acoustic modeling of speech uses the Expectation-Maximization (EM) algorithm. The EM algorithm is sensitive to initial values of HMM parameters and is likely to terminate at a local maximum of likelihood function resulting in non-optimized estimation for HMM and lower recognition accuracy. In this paper, to obtain better estimation for HMM and higher recognition accuracy, several candidate HMMs are created by applying EM on multiple initial models. The best HMM is chosen from the candidate HMMs which has highest value for likelihood function. Initial models are created by varying maximum frame number in the segmentation step of HMM initialization process. A binary search is applied while creating the initial models. The proposed method has been tested on TIMIT database. Experimental results show that our approach obtains improved values for likelihood function and improved recognition accuracy. [ABSTRACT FROM AUTHOR]

In data mining we come across many problems such as function optimization problem or parameter estimation problem for classifiers for which a good learning algorithm for searching is very much necessary. In this paper we propose a stochastic based derivative free algorithm for unconstrained optimization problem. Many derivative-based local search methods exist which usually stuck into local solution for non-convex optimization problems. On the other hand global search methods are very time consuming and works for only limited number of variables. In this paper we investigate a derivative free multi search gradient based method which overcomes the problems of local minima and produces global solution in less time. We have tested the proposed method on many benchmark dataset in literature and compared the results with other existing algorithms. The results are very promising. [ABSTRACT FROM AUTHOR]

Derivative free optimization methods have recently gained a lot of attractions for neural learning. The curse of dimensionality for the neural learning problem makes local optimization methods very attractive; however the error surface contains many local minima. Discrete gradient method is a special case of derivative free methods based on bundle methods and has the ability to jump over many local minima. There are two types of problems that are associated with this when local optimization methods are used for neural learning. The first type of problems is initial sensitivity dependence problem - that is commonly solved by using a hybrid model. Our early research has shown that discrete gradient method combining with other global methods such as evolutionary algorithm makes them even more attractive. These types of hybrid models have been studied by other researchers also. Another less mentioned problem is the problem of large weight values for the synaptic connections of the network. Large synaptic weight values often lead to the problem of paralysis and convergence problem especially when a hybrid model is used for fine tuning the learning task. In this paper we study and analyse the effect of different regularization parameters for our objective function to restrict the weight values without compromising the classification accuracy. [ABSTRACT FROM AUTHOR]

Neural network learning is the main essence of ANN. There are many problems associated with the multiple local minima in neural networks. Global optimization methods are capable of finding global optimal solution. In this paper we investigate and present a comparative study for the effects of probabilistic and deterministic global search method for artificial neural network using fully connected feed forward multi-layered perceptron architecture. We investigate two probabilistic global search method namely Genetic algorithm and Simulated annealing method and a deterministic cutting angle method to find weights in neural network. Experiments were carried out on UCI benchmark dataset. [ABSTRACT FROM AUTHOR]