By David B. Fogel
Blondie24 tells the tale of a working laptop or computer that taught itself to play checkers much better than its creators ever may through the use of a software that emulated the fundamental ideas of Darwinian evolution--random version and typical selection-- to find by itself how one can excel on the online game. not like Deep Blue, the distinguished chess laptop that beat Garry Kasparov, the previous global champion chess participant, this evolutionary software did not have entry to techniques hired via human grand masters, or to databases of strikes for the endgame strikes, or to different human services concerning the video game of chekers. With merely the main rudimentary details programmed into its "brain," Blondie24 (the program's web username) created its personal technique of comparing the complicated, altering styles of items that make up a checkers video game through evolving synthetic neural networks---mathematical versions that loosely describe how a mind works.It's becoming that Blondie24 may still look in 2001, the 12 months once we keep in mind Arthur C. Clarke's prediction that in the future we might reach making a considering computing device. during this compelling narrative, David Fogel, writer and co-creator of Blondie24, describes in convincing element how evolutionary computation can assist to convey us towards Clarke's imaginative and prescient of HAL. alongside the best way, he offers readers an inside of inspect the interesting background of AI and poses provocative questions about its destiny. * Brings probably the most interesting components of AI study to existence by means of following the tale of Blondie24's improvement within the lab via her evolution into an expert-rated checkers participant, in keeping with her amazing luck in net competition.* Explains the principles of evolutionary computation, easily and clearly.* provides advanced fabric in an attractive type for readers without heritage in computing device technological know-how or man made intelligence.* Examines foundational concerns surrounding the production of a considering machine.* Debates even if the recognized Turing attempt fairly checks for intelligence.* demanding situations deeply entrenched myths in regards to the successes and implication of a few famous AI experiments * exhibits Blondie's strikes with checkerboard diagrams that readers can simply stick to.
Read or Download Blondie24: Playing at the Edge of AI (The Morgan Kaufmann Series in Artificial Intelligence) PDF
Best intelligence & semantics books
This quantity is the direct results of a convention during which a couple of top researchers from the fields of man-made intelligence and biology amassed to ascertain no matter if there has been any flooring to imagine new AI paradigm was once forming itself and what the basic constituents of this new paradigm have been.
Emphasizing problems with computational potency, Michael Kearns and Umesh Vazirani introduce a couple of principal subject matters in computational studying concept for researchers and scholars in synthetic intelligence, neural networks, theoretical laptop technological know-how, and records. Computational studying concept is a brand new and quickly increasing sector of analysis that examines formal types of induction with the targets of learning the typical equipment underlying effective studying algorithms and picking the computational impediments to studying.
The Semantic internet has given loads of impetus to the advance of ontologies and multi-agent structures. numerous books have seemed which debate the improvement of ontologies or of multi-agent platforms individually all alone. The becoming interplay among agnets and ontologies has highlighted the necessity for built-in improvement of those.
The tough and fuzzy set ways awarded the following open up many new frontiers for endured examine and improvement. Computational Intelligence and have choice offers readers with the heritage and primary rules in the back of characteristic choice (FS), with an emphasis on concepts in keeping with tough and fuzzy units.
- Mathematics Handbook for Science and Engineering
- Advances in Image Processing and Understanding: A Festschrift for Thomas S. Huang
- Classification and Modeling with Linguistic Information Granules: Advanced Approaches to Linguistic Data Mining
- Advances in learning theory: methods, models, and applications
Additional resources for Blondie24: Playing at the Edge of AI (The Morgan Kaufmann Series in Artificial Intelligence)
The same principle holds for designing a neural network that assesses positions on a checkerboard. If a neural network has the right number of neurons and the right weights between those neurons, that network might do very well. But even if it has the right number of neurons, with the wrong weights, the neural network would play very poorly. Finding the right weights becomes the critical and vexing issue. A Sinister Task O R is a simple function. We only need three neurons, and we can figure out the right values for the weights and thresholds simply by examining the neural network and doing a little scratch work with paper and pencil.
Only then will computers be able to solve new problems in new ways. Artificial Intelligence, Emphasis on Artificial Deep Blue was a significant engineering accomplishment, but from the perspective of designing intelligent machines it was more an admission of failure. After all, almost everything Deep Blue "knew" in its evaluation function was preprogrammed by people and/or based on the knowledge accumulated from chess grand masters. 22 Even with all the knowledge of previous games, endgame strategies, and gambits, it had taken IBM millions of dollars, specially designed hardware, and years of effort to capture that knowledge and finally process it fast enough to beat the world's greatest player.
H o w can we build a computer like the W O P R that would play games like chess, teach itself the right moves, and adapt to new circumstances as it progressed without relying on people to provide the right answers? H o w can we build such an intelligent machine? One promising solution can be found by turning to evolution, nature's design'principle of random variation and selection. I'm going to tell you about some experiments that support this contention. These experiments involve the evolution of artificial neural networks, computer models of how simple brains might function.