Fuzzy automata are regarded as an important device in fuzzy systems due to the advantage
of powerful mathematical computation. This dynamic machine has been applied in various …

The central aim of this thesis is to develop novel approaches to the representation and the
refinement of event recognition models. The event recognition system is viewed as a …

Max and min operations have interesting properties that facilitate the exchange of
information between the symbolic and real-valued domains. As such, neural networks that …

In this paper, we first define the notion of a complete general fuzzyautomaton with threshold
c and construct an $ H_ {nu} $-group, as well as commutativehypergroups, on the set of …

This paper investigates the convergence theorems that are associated with a Discrete
Hopfield Neural Network (DHNN) with delay. We present two updating rules, one for serial …

In this paper, we define the notion of a bipolar general fuzzy automaton, then we construct
some closure operators on the set of states of a bipolar general fuzzy automaton. Also, we …

It is well known that canonical recurrent neural networks (RNNs) face limitations in learning
long-term dependencies, which have been addressed by memory structures in long short …

The power of abstraction lies in its ability to deal with" lack" of knowledge. In this regard,
success in modeling and simulation rests on discovering useful abstractions that can …

This paper describes preference classes and preference Moore machines as a basis for
integrating different hybrid neural representations. Preference classes are shown to provide …

An" on-line" time series prediction system EFuNN-T based on a model of evolving fuzzy
neural network------EFuNN is presented in this paper. EFuNN, as a particular type of …