The evolution of Soft Computing - From neural networks to cellular automata
4/5
()
About this ebook
Read more from Marco Casella
Bretton Woods: History of a monetary system Rating: 3 out of 5 stars3/5Nanotechnologies - The challenges of the future Rating: 0 out of 5 stars0 ratingsE-didactics and practices for e-learning Rating: 0 out of 5 stars0 ratingsNanomedicine - Overview of a new science Rating: 0 out of 5 stars0 ratingsCharles Darwin and the evolution of species - From the origins to Darwinism Rating: 0 out of 5 stars0 ratingsThe social networks: an introduction Rating: 0 out of 5 stars0 ratingsGoogle - The revolution of Internet Rating: 0 out of 5 stars0 ratingsFundamentals of librarianship Rating: 1 out of 5 stars1/5
Related to The evolution of Soft Computing - From neural networks to cellular automata
Related ebooks
How to Create Machine Superintelligence (Second Edition) Rating: 0 out of 5 stars0 ratingsModels of the Mind: How Physics, Engineering and Mathematics Have Shaped Our Understanding of the Brain Rating: 3 out of 5 stars3/5Machine Learning - A Complete Exploration of Highly Advanced Machine Learning Concepts, Best Practices and Techniques: 4 Rating: 0 out of 5 stars0 ratingsArtificial Intelligence Foundations: Learning from experience Rating: 0 out of 5 stars0 ratingsFuzzy Logic: Fundamentals and Applications Rating: 0 out of 5 stars0 ratingsMachine Learning: Adaptive Behaviour Through Experience: Thinking Machines Rating: 4 out of 5 stars4/5An Introduction to Information Theory: Symbols, Signals and Noise Rating: 4 out of 5 stars4/5Invitation to Dynamical Systems Rating: 5 out of 5 stars5/5Python Machine Learning Rating: 5 out of 5 stars5/5Artificial Neural Systems: Principle and Practice Rating: 0 out of 5 stars0 ratingsNatural Computing with Python: Learn to implement genetic and evolutionary algorithms to solve problems in a pythonic way Rating: 0 out of 5 stars0 ratingsMachine Learning Concepts with Python and the Jupyter Notebook Environment: Using Tensorflow 2.0 Rating: 0 out of 5 stars0 ratingsNeural Networks: Neural Networks Tools and Techniques for Beginners Rating: 5 out of 5 stars5/5Building Software for Simulation: Theory and Algorithms, with Applications in C++ Rating: 0 out of 5 stars0 ratingsA First Course in Artificial Intelligence Rating: 0 out of 5 stars0 ratingsIntroduction to Quantum Computing & Machine Learning Technologies: 1, #1 Rating: 0 out of 5 stars0 ratingsHidden Markov Processes: Theory and Applications to Biology Rating: 5 out of 5 stars5/5AIQ: How People and Machines Are Smarter Together Rating: 4 out of 5 stars4/5Quantum Computing A Complete Guide - 2020 Edition Rating: 0 out of 5 stars0 ratingsArtificial Intelligence in Practice: How 50 Successful Companies Used AI and Machine Learning to Solve Problems Rating: 0 out of 5 stars0 ratingsMathematical Methods of Statistics Rating: 3 out of 5 stars3/5Artificial Intelligence: Understanding Business Applications, Automation, and the Job Market Rating: 0 out of 5 stars0 ratingsConvolutional neural network Second Edition Rating: 0 out of 5 stars0 ratingsDigital Image Processing: Fundamentals and Applications Rating: 0 out of 5 stars0 ratingsConvolutional Neural Networks in Python: Beginner's Guide to Convolutional Neural Networks in Python Rating: 0 out of 5 stars0 ratingsComplex Binary Number System: Algorithms and Circuits Rating: 0 out of 5 stars0 ratingsProfessional CUDA C Programming Rating: 5 out of 5 stars5/5Artificial Intelligence: Data Analytics and Innovation for Beginners Rating: 5 out of 5 stars5/5Learning OpenCV 3 Computer Vision with Python - Second Edition Rating: 0 out of 5 stars0 ratings
Intelligence (AI) & Semantics For You
2084: Artificial Intelligence and the Future of Humanity Rating: 4 out of 5 stars4/5ChatGPT For Fiction Writing: AI for Authors Rating: 5 out of 5 stars5/5Summary of Super-Intelligence From Nick Bostrom Rating: 5 out of 5 stars5/5The Secrets of ChatGPT Prompt Engineering for Non-Developers Rating: 5 out of 5 stars5/5Dark Aeon: Transhumanism and the War Against Humanity Rating: 5 out of 5 stars5/5Artificial Intelligence: A Guide for Thinking Humans Rating: 4 out of 5 stars4/5Mastering ChatGPT: 21 Prompts Templates for Effortless Writing Rating: 5 out of 5 stars5/5Midjourney Mastery - The Ultimate Handbook of Prompts Rating: 5 out of 5 stars5/5Creating Online Courses with ChatGPT | A Step-by-Step Guide with Prompt Templates Rating: 4 out of 5 stars4/5The Algorithm of the Universe (A New Perspective to Cognitive AI) Rating: 5 out of 5 stars5/5Enterprise AI For Dummies Rating: 3 out of 5 stars3/5Writing AI Prompts For Dummies Rating: 0 out of 5 stars0 ratingsPrompt Engineering ; The Future Of Language Generation Rating: 4 out of 5 stars4/5ChatGPT For Dummies Rating: 4 out of 5 stars4/5AI for Educators: AI for Educators Rating: 5 out of 5 stars5/5101 Midjourney Prompt Secrets Rating: 3 out of 5 stars3/5Chat-GPT Income Ideas: Pioneering Monetization Concepts Utilizing Conversational AI for Profitable Ventures Rating: 3 out of 5 stars3/5Build a Career in Data Science Rating: 5 out of 5 stars5/5A Brief History of Artificial Intelligence: What It Is, Where We Are, and Where We Are Going Rating: 4 out of 5 stars4/5Killer ChatGPT Prompts: Harness the Power of AI for Success and Profit Rating: 2 out of 5 stars2/5
Reviews for The evolution of Soft Computing - From neural networks to cellular automata
1 rating0 reviews
Book preview
The evolution of Soft Computing - From neural networks to cellular automata - Marco Casella
MARCO CASELLA
THE EVOLUTION OF SOFT COMPUTING
UUID: 8ed36edc-7e20-11e4-96fe-9df0ffa51115
This ebook was created with BackTypo (http://backtypo.com)
by Simplicissimus Book Farm
Table of contents
Introduction
History of neural networks
History of fuzzy logic
History of the genetic algorithms
History of cellular automata
Introduction
This book wants to give a historical overview of the techniques at the basis of what is defined soft computing.
Coined in 1965 by Lotfi Zadeh, the term soft computing indicates a series of methods that enable to treat some problems whose we have an uncertain or partial knowledge finding rough solutions, opposed to the hard computing methods, based on the research of right solutions.
In particular, the soft computing techniques aim to evaluate, decide, control and calculate in an imprecise domain emulating and using the human beings’ capability to carry out these activities on the basis of their experience. In fact, the model of the soft computing is human mind, with its perplexities, emotions and subjectivities.
The soft computing makes use of the features of its three main branches:
the possibility to shape and to control uncertain and complex systems, as well as to represent efficiently the knowledge through the linguistic descriptions typical of the fuzzy set theory;
the optimization capability of the genetic algorithms whose computation is inspired by the selection and mutation laws typical of living organisms;
the learning capability of complex functional relationships of the neural neutworks, inspired by those of the cerebral tissues;
the capability to describe the evolution of complex systems by means of the mathematic model of the cellular automata.
The complementarity of these techniques has important consequences: a problem can often be resolved more efficiently using them combined rather than separate.
According to Lotfi Zadeh
«a growing visibility trend is set up by the use of the fuzzy logic in combination with the neural calculus and the genetic algorithms. More in general, fuzzy logic, neural networks and genetic algorithms can be regarded as the main constituent of what could be defined as soft calculus. Alike the traditional or hard calculus methods, the soft computing aims to be adapted to the pervasive imprecision of the real world. Its main principle can be expressed as follows: to exploit the tolerance for the imprecision, the uncertainty and the partial truths so as to obtain treatability, robustness and low cost solutions. In the next years, the soft computing is likely to be destined to play a more and more important role in the conception and design of systems whose MIQ (Machine Intelligent Quotient) is far higher than conventional systems. Among the various combinations of soft computing methods, the one that has greater visibility in this domain is the fusion of fuzzy logic and neural calculus that leads to the so-called neuro-fuzzy systems. In the context of the fuzzy logic, these systems play a particularly important role in the induction process of rules starting from observation".
According to Kohonen, it can be stated that
«soft computing, real-world computing, etc. are common denominations for certain forms of information and natural elaboration that have their origin in biology. On the other hand, fuzzy and probabilistic logics, neural networks, genetic algorithms, etc., are alternative theoretical formalisms through which computational schemes and algorithms can be defined for these purposes».
In general, the soft computing techniques resemble to biologic processes more close to the traditional techniques, mostly based on formal logic systems, like propositional logic and predicate logic, or they rely upon the computerized numeric analysis.
The different application of soft computing suggest that its impact will grow in the next years.
History of neural networks
The study of neural networks dates back to the first attempts to translate the principles of the biologic processing in mathematic models. The most ancient theories of the brain and the mental processes have been conceived by the Greek philosophers Plato (427-347 B.C.) and Aristotle (384-322 B.C.). These theories have been drawn by René Descartes (1586-1650) and in the 18th century