Learning to recognize a new object after having learned other objects may be simple task for human, but not machines. The present go-to approaches teaching machine set of are based on the use deep neural networks (DNN). So, intuitively, solution fly should DNN. problem is that trained DNN weights used classify initial extremely fragile, meaning any change those can severely damage capacity perf...

Traditional trial-and-error approach to design neural networks is time consuming and does not guarantee yielding the best neural network feasible for a specific application. Therefore automatic approaches have gained more importance and popularity. In addition, traditional (non-modular) neural networks can not solve complex problems since these problems introduce wide range of overlap which, in...

In voice-activated teleservices, two types of speech recognition systems are commonly used, (tri)phone-based and wholeword model recognizers. While the first type of systems exhibits a convenient implementation to recognize any new vocabulary word, the second achieves a higher performance level when the necessary and specific training data is available. In order to bridge the performance gap be...

(ABSTRACT) This dissertation explores the modular learning in artificial neural networks that mainly driven by the inspiration from the neurobiological basis of the human learning. The presented modu-larization approaches to the neural network design and learning are inspired by the engineering, complexity, psychological and neurobiological aspects. The main theme of this dissertation is to exp...

Modular neural network is a popular neural network model which has many successful applications. In this paper, a sequential Bayesian learning (SBL) is proposed for modular neural networks aiming at efficiently aggregating the outputs of members of the ensemble. The experimental results on eight benchmark problems have demonstrated that the proposed method can perform information aggregation ef...

In this chapter, we focus on two important areas in neural computation, i.e., deep and modular neural networks, given the fact that both deep and modular neural networks have been among the most powerful machine learning and pattern recognition techniques for complex AI problem solving. We begin by providing a general overview of deep and modular neural networks to describe the general motivati...

The neural network is a powerful computing framework that has been exploited by biological evolution and by humans for solving diverse problems. Although the computational capabilities of neural networks are determined by their structure, the current understanding of the relationships between a neural network’s architecture and function is still primitive. Here we reveal that neural network’s m...

Modular neural networks integrate several neural networks and possibly standard processing methods. Tackling such models is a challenge, since various modules have to be combined, either sequentially or in parallel, and the simulations are time critical in many cases. For this, specific tools are prerequisite that are both flexible and efficient. We have developed the MONNET software system tha...