Learn More
Incremental learning has been widely addressed in the machine learning literature to cope with learning tasks where the learning environment is ever changing or training samples become available over time. However, most research work explores incremental learning with statistical algorithms or neural networks, rather than evolutionary algorithms. The work(More)
Task decomposition with pattern distributor (PD) is a new task decomposition method for multilayered feedforward neural networks (NNs). Pattern distributor network is proposed that implements this new task decomposition method. We propose a theoretical model to analyze the performance of pattern distributor network. A method named reduced pattern training(More)
This paper presents a novel golden-template self-generating technique for detecting possible defects in periodic two-dimensional wafer images. A golden template of the patterned wafer image under inspection can be obtained from the wafer image itself and no other prior knowledge is needed. It is a bridge between the existing self-reference methods and(More)
Neural networks are generally exposed to a dynamic environment where the training patterns or the input attributes (features) will likely be introduced into the current domain incrementally. This Letter considers the situation where a new set of input attributes must be considered and added into the existing neural network. The conventional method is to(More)
Cellular automata (CA) has been used in pseudorandom number generation for over a decade. Recent studies show that two-dimensional (2-D) CA pseudorandom number generators (PRNGs) may generate better random sequences than conventional one-dimensional (1-D) CA PRNGs, but they are more complex to implement in hardware than 1-D CA PRNGs. In this paper, we(More)
We propose a new class of cellular automata, self-programming cellular automata (SPCA), with specific application to pseudorandom number generation. By changing a cell's state transition rules in relation to factors such as its neighboring cell's states, behavioral complexity can be increased and utilized. Interplay between the state transition neighborhood(More)
Incremental training has been used for GA-based classifiers in a dynamic environment where training samples or new attributes/classes become available over time. In this paper, ordered incremental genetic algorithms (OIGAs) are proposed to address the incremental training of input attributes for classifiers. Rather than learning input attributes in batch as(More)
In order to find an appropriate architecture for a large-scale real-world application automatically and efficiently, a natural method is to divide the original problem into a set of subproblems. In this paper, we propose a simple neural-network task decomposition method based on output parallelism. By using this method, a problem can be divided flexibly(More)
The achievement of media synchronization has been dealt with in the Object Composition Petri Net (OCPN) model and the extended OCPN (XOCPN) model. Yet these two models are not enough for synchronization of computers in a distributed environment. This paper proposes a new Petri Net model—Prioritized Petri Net (Pnet). The modeling power and properties of(More)