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 application that emulated the elemental ideas of Darwinian evolution--random version and ordinary selection-- to find by itself find out how to excel on the video game. in contrast to Deep Blue, the distinguished chess computer that beat Garry Kasparov, the previous global champion chess participant, this evolutionary application did not have entry to techniques hired by way of human grand masters, or to databases of strikes for the endgame strikes, or to different human services in regards to the video game of chekers. With simply the main rudimentary details programmed into its "brain," Blondie24 (the program's web username) created its personal technique of comparing the advanced, altering styles of items that make up a checkers online game by means of evolving synthetic neural networks---mathematical versions that loosely describe how a mind works.It's becoming that Blondie24 may still seem in 2001, the yr after we take note Arthur C. Clarke's prediction that in the future we might reach making a pondering laptop. during this compelling narrative, David Fogel, writer and co-creator of Blondie24, describes in convincing aspect how evolutionary computation can assist to convey us in the direction of Clarke's imaginative and prescient of HAL. alongside the best way, he provides readers an inside of look at the interesting historical past of AI and poses provocative questions about its destiny. * Brings some of the most intriguing components of AI study to lifestyles via following the tale of Blondie24's improvement within the lab via her evolution into an expert-rated checkers participant, in accordance with her notable good fortune in web competition.* Explains the rules of evolutionary computation, easily and clearly.* offers advanced fabric in an enticing type for readers without heritage in laptop technological know-how or synthetic intelligence.* Examines foundational concerns surrounding the production of a pondering machine.* Debates no matter if the well-known Turing try out fairly checks for intelligence.* demanding situations deeply entrenched myths in regards to the successes and implication of a few recognized AI experiments * indicates Blondie's strikes with checkerboard diagrams that readers can simply keep on with.
Read or Download Blondie24: Playing at the Edge of AI (The Morgan Kaufmann Series in Artificial Intelligence) PDF
Similar intelligence & semantics books
An Introduction to Computational Learning Theory
Emphasizing problems with computational potency, Michael Kearns and Umesh Vazirani introduce a few important subject matters in computational studying thought for researchers and scholars in synthetic intelligence, neural networks, theoretical desktop technological know-how, and statistics. Computational studying idea is a brand new and quickly increasing zone of analysis that examines formal types of induction with the objectives of getting to know the typical tools underlying effective studying algorithms and deciding upon the computational impediments to studying.
Minimum Error Entropy Classification
This booklet explains the minimal errors entropy (MEE) proposal utilized to information category machines. Theoretical effects at the internal workings of the MEE thought, in its program to fixing quite a few category difficulties, are offered within the wider realm of possibility functionals. Researchers and practitioners additionally locate within the ebook an in depth presentation of sensible information classifiers utilizing MEE.
Artificial Intelligence for Humans, Volume 1: Fundamental Algorithms
An excellent construction calls for a powerful beginning. This publication teaches easy man made Intelligence algorithms corresponding to dimensionality, distance metrics, clustering, mistakes calculation, hill hiking, Nelder Mead, and linear regression. those aren't simply foundational algorithms for the remainder of the sequence, yet are very important of their personal correct.
Advances in Personalized Web-Based Education
This ebook goals to supply very important information regarding adaptivity in computer-based and/or web-based academic structures. which will make the coed modeling strategy transparent, a literature assessment bearing on scholar modeling suggestions and techniques in the past decade is gifted in a distinct bankruptcy.
- Learning kernel classifiers: theory and algorithms
- Reasoning with Probabilistic and Deterministic Graphical Models: Exact Algorithms
- Computational Intelligence and Feature Selection: Rough and Fuzzy Approaches
- The Efficiency of Theorem Proving Strategies: A Comparative and Asymptotic Analysis
- The quest for artificial intelligence: A history of ideas and achievements
- Knowledge in Formation: A Computational Theory of Interpretation
Extra info for Blondie24: Playing at the Edge of AI (The Morgan Kaufmann Series in Artificial Intelligence)
Example text
Each parameter had to be weighted in terms of its importance relative to the other parameters. The traditional way to find appropriate settings of these parameters was by hand tuning: The Deep Blue team used this approach, playing games with various parameter settings and adjusting them through trial and error. But the team also tried an alternative to hand tuning. They gathered nine hundred games from chess masters, then used an algorithm to adjust the parameters so that the evaluation from their function would produce the greatest match between the moves that the machine thought were best and those actually played by the masters.
Let's see how the neural network would respond to (I,o). The first hidden neuron would have o stimulus, because the input value of I would be multiplied by o. Likewise, the second hidden neu- 44 S E T T I N G T H E STAGE ron would also have o stimulus as its corresponding input value of o was multiplied by o. Since the activation at both hidden nodes would be less than their respective thresholds, neither neuron would fire. This would then send two o signals on the output node. Each of these signals would again be multiplied by o.
I 'r 1E7 Processor Speed (Millions of instructions per second) FIGU RE 4 The increase in the rating of chess programs as a function of computer processor speed. the increase in chess program ratings is independent of the evaluation function that each program used (despite considerable time and effort spent crafting each function). They all used reasonable variations on what to measure with regard to material (number and types of pieces) and position, butperhaps that didn't make much difference.