Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies (Intelligent Robotics and Autonomous Agents series)

Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies (Intelligent Robotics and Autonomous Agents series)

Dario Floreano, Claudio Mattiussi

Language: English

Pages: 659

ISBN: 0262062712

Format: PDF / Kindle (mobi) / ePub


New approaches to artificial intelligence spring from the idea that intelligence emerges as much from cells, bodies, and societies as it does from evolution, development, and learning. Traditionally, artificial intelligence has been concerned with reproducing the abilities of human brains; newer approaches take inspiration from a wider range of biological structures that that are capable of autonomous self-organization. Examples of these new approaches include evolutionary computation and evolutionary electronics, artificial neural networks, immune systems, biorobotics, and swarm intelligence -- to mention only a few. This book offers a comprehensive introduction to the emerging field of biologically inspired artificial intelligence that can be used as an upper-level text or as a reference for researchers. Each chapter presents computational approaches inspired by a different biological system; each begins with background information about the biological system and then proceeds to develop computational models that make use of biological concepts. The chapters cover evolutionary computation and electronics; cellular systems; neural systems, including neuromorphic engineering; developmental systems; immune systems; behavioral systems -- including several approaches to robotics, including behavior-based, bio-mimetic, epigenetic, and evolutionary robots; and collective systems, including swarm robotics as well as cooperative and competitive co-evolving systems. Chapters end with a concluding overview and suggested reading.

Essentials of Error-Control Coding

Computer Networking: A Top-Down Approach (5th Edition)

Debugging by Thinking: A Multidisciplinary Approach (HP Technologies)

Digital Signal Processing: A Modern Introduction

Experimentation in Software Engineering

 

 

 

 

 

 

 

 

 

 

 

 

 

 

even if the signal has finite duration, whereas that conveyed by a digital signal is necessarily finite. Let us first consider the issue in the time domain. The sampling theorem (Shannon 1949) tells us that a band-limited signal, that is, a signal whose frequency content is confined to a finite frequency interval of width W , can be reconstructed with the information represented by a sequence of signal samples that is discrete in time. Since all actual signals are band limited, we can conclude that in

(2004). The Major Transitions in Evolution by MaynardSmith and Szathmáry (1995) is unique in that it explains key facts in molecular biology and evolution within the perspective of how information is stored and transmitted through generations. According to the authors, there have been eight major transitions in evolutionary history starting from molecular replicators all the way to human societies and language. Although the book requires good knowledge of some biological and chemical aspects, it

advance only if the destination cell is free. This rule can be represented with the transition table shown in figure 2.7e). We assign periodic boundary conditions, so that vehicles leaving the cellular space from the right reenter it from the left (figure 2.7f)). To run the simulations we must now assign the initial conditions. We use as the initial condition a random distribution of cars of density ρ that can vary from 0 (empty road) to 1 (each cell is occupied by a vehicle). Note that the

speaking, these implementations are always CAs rather than CMLs. Still, it is more useful to consider them as approximate implementations of CMLs rather than CAs because the state space is typically too large to make the CA point of view useful, whereas the results of the CML perspective still hold, albeit in an approximate way. Cellular Neural Networks Cellular neural networks (CNNs) were introduced by Chua and Yang (1988b). They are cellular systems where both the state and the time variable

1987), retrieval resembles the way in which humans operate: more familiar patterns are recognized faster than items that are different or seen less frequently. Instead, in conventional computer systems, data are retrieved using the address of the electronic memory cells. If that number is corrupted or lost, the entire memory is lost. 3.3 Neuron Models An artificial neuron is characterized by a set of connection strengths, a threshold, and an activation function (figure 3.10). If we ignore

Download sample

Download