Neural Network Driven Artificial Intelligence: Decision Making Based On Fuzzy Logic
With today’s growing and overloading volume of information, it is becoming tremendously challenging to analyze the vast amounts of data that contain this information. Therefore, introducing an appropriate decision-making methodology fast enough to be considered real-time makes it very strenuous and inconvenient. Moreover, the demand for real-time processing information and related data – both structured and unstructured – is increasing, making it harder and harder to implement correct decision-making at the enterprise level to keep the organization robust and resilient against artificial threats or natural disasters.
Neural networking and fuzzy systems combined to show how these combinations can drive Artificial Intelligence (AI) as a trainable system that is more dynamic than static when it comes to machine and deep learning language to deal with adversary and friendly events in real-time. Furthermore, dynamic systems of AI built around such an innovative approach allow future robots to be more adaptive with mechanisms such as principle adoption, self-organization, and the convergence of global stability from the viewpoint of business and intelligence security needed in today’s cyber world.
Lofti A. Zadeh introduced fuzzy sets and fuzzy logic to deal with uncertainty, vagueness, and imprecision. In the present book, fuzzy classification is applied to extend portfolio analysis, scoring methods, customer segmentation, and performance measurement, and thus improves managerial decisions. As an integral part of the book, case studies show how fuzzy classification – with its query facilities – can extend customer equity, enable mass customization, and refine marketing campaigns.
This book shows the interoperability between the two sciences/techniques show how:
- To utilize the fuzzy theory of the first and second kind to an adaptive control; and
- How to invent a structured fuzzy system and robots of the future, with unsupervised neural network techniques to face an unstructured world of big data and unpredictable global events all in real-time
An essential aspect of this approach is to examine biological neural systems and study how artificial neural networks are, how they are based on them, and how they drive them. Key areas discussed include:
1) Structural diversity;
2) Temporal lobe;
3) Origins of artificial neural systems;
4) Brain structure and function;
5) Biological nerve cells;
6) Synapses;
7) Random and fixed positions in the brain’s neural networks; and
8) How do biological systems compare to computational neural networks. (Imprint: Nova)
Reviews
There are no reviews yet.