Visualization of Neuro-Fuzzy Networks Training Algorithms

Abstract

The fusion of Artificial Neural Networks and Fuzzy Logic Systems allows researchers to model real world problems through the development of intelligent and adaptive systems. Artificial Neural networks are able to adapt and learn by adjusting the interconnections between layers while fuzzy logic inference systems provide a computing framework based on the concept of fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. The combined use of those adaptive structures is known as “Neuro-Fuzzy” systems. In this chapter, the basic elements of both approaches are analyzed while neuro-fuzzy networks learning algorithms are presented. Here, we combine the use of neuro-fuzzy algorithms with multimedia-based signals for training. Ultimately this process may be employed for automatic identification of patterns introduced in medical applications and more specifically for analysis of content produced by brain imaging processes.

A dynamical thermostat approach to financial asset price dynamics

“…f (r τ ) ∼ |r τ | −α , with α > 2. This result has been confirmed throughout the 1990s and the exponent is nowadays believed to be close to α = 3 [3].…”

Model for correlations in stock markets

“…There has been growing interest of physicists in economic systems. They exhibit various interesting complex behaviors, e.g., a power-law distribution of the variations of financial market indices [1][2][3], and many efforts have been devoted to understanding the temporal correlations [4][5][6]. The economic systems are composed of a large number of interacting units.…”

Performance Comparison of Pid Controller and Fuzzy Logic Controller for Water Level Control With Applying Time Delay

“…FL is based on fuzzy set theory, which is a generalization of classical set theory, which means that classical sets are a special case of fuzzy sets. In classical sets, the element either belongs to the set or does not at all, while in fuzzy sets, the same element can belong to several sets at the same time (Plerou et al, 2016). The FL controller consists of four main components shown in Figure 5: the Fuzzification, the Rules, the Inference Engine, and the Defuzzification (Boada et al, 2005).…”