Main page - Introduction to Genetic Algorithms - Tutorial with Interactive Java Applets
http://www.obitko.com/tutorials/genetic-algorithms/index.php

e area of genetic algorithms is very wide, it is not possible to cover everything in these pages. But you should get some idea, what the genetic algorithms are and what they could be useful for. Do not expect any sophisticated mathematic

a lot of these i've seen before, but its pretty awe-inspiring to see them one after another...plus the comments have a bunch more!

Robot innovation continued its relentless advances during 2008. In this post we would like to showcase some of our favorite robots and robot videos of the last year or so.

Robot innovation continued its relentless advances during 2008. In this post we would like to showcase some of our favorite robots and robot videos of the last year or so. This review is heavily slanted to consumer robots and research robots. Perhaps in the future we can do a review of industrial robots. Given the sheer number of robots that are out there we know there will be several excellent robots that we have overlooked in this review. If you know of any really awesome robots or robot videos that we have missed please let us know and we will consider adding them to this post. So without further delay, lets take a look at some of the best robots and robot videos of 2008 (maybe some are from 2007 too), broken down by category: January 12th, 2009 | Published by Keith Kleiner in robotics

Robot innovation continued its relentless advances during 2008. In this post we would like to showcase some of our favorite robots and robot videos of the last year or so. (Singularity Hub)

Canvas element used to do basic image-processing on an image. Can a JS port of NumPy be far behind? What about the effects on expectations for javascript from users and engine writers? *Mind buzzes*

Breaking Captchas with a GreaseMonkey script

Interesting looking ebook. Give it a look.

Book as PDF on neural networks.

Pyevolve was developed to be a complete genetic algorithm framework written in pure python.

PyBrain

PyBrain is a modular Machine Learning Library for Python. It's goal is to offer flexible, easy-to-use yet still powerful algorithms for Machine Learning Tasks and a variety of predefined environments to test and compare your algorithms.

What do one mathematician, one artist, and one musician all have in common? Are you interested in zen Buddhism, math, fractals, logic, paradoxes, infinities, art, language, computer science, physics, music, intelligence, consciousness and unified theories? Get ready to chase me down a rabbit hole into Douglas Hofstadter's Pulitzer Prize winning book Gödel, Escher, Bach. Lectures will be a place for crazy ideas to bounce around as we try to pace our way through this enlightening tome. You will be responsible for most of the reading as lectures will consist primarily of motivating the material and encouraging discussion. I advise everyone seriously interested to buy the book, grab on and get ready for a mind-expanding voyage into higher dimensions of recursive thinking.

Carl Edward Rasmussen and Christopher K. I. Williams MIT Press, 2006. ISBN-10 0-262-18253-X, ISBN-13 978-0-262-18253-9. This book is © Copyright 2006 by Massachusetts Institute of Technology. The MIT Press have kindly agreed to allow us to make the book available on the web. The web version of the book corresponds to the 2nd printing. You can buy the book for a list price of 36.00 US$ or 23.95 UK£. The whole book as a single pdf file.

Gaussian Processes for Machine Learning

This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include: supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction, kernel methods); learning theory (bias/variance tradeoffs; VC theory; large margins); reinforcement learning and adaptive control. The course will also discuss recent applications of machine learning, such as to robotic control, data mining, autonomous navigation, bioinformatics, speech recognition, and text and web data processing.

"It's not a "Google killer" -- it does something different. It's an "answer engine" rather than a search engine."

via Nova Spivack: It doesn't simply return documents that (might) contain the answers, like Google does, and it isn't just a giant database of knowledge, like the Wikipedia. It doesn't simply parse natural language and then use that to retrieve documents, like Powerset, for example. Instead, Wolfram Alpha actually computes the answers to a wide range of questions -- like questions that have factual answers such as "What is the location of Timbuktu?" or "How many protons are in a hydrogen atom?," "What was the average rainfall in Boston last year?," "What is the 307th digit of Pi?," or "what would 80/20 vision look like?"

Wolfram Research introduces a search engine

Where Google is a system for FINDING things that we as a civilization collectively publish, Wolfram Alpha is for ANSWERING questions about what we as a civilization collectively know. It’s the next step in the distribution of knowledge and intelligence around the world — a new leap in the intelligence of our collective “Global Brain.” And like any big next-step, Wolfram Alpha works in a new way — it computes answers instead of just looking them up. Wolfram Alpha, at its heart is quite different from a brute force statistical search engine like Google. And it is not going to replace Google — it is not a general search engine: You would probably not use Wolfram Alpha to shop for a new car, find blog posts about a topic, or to choose a resort for your honeymoon. It is not a system that will understand the nuances of what you consider to be the perfect romantic getaway, for example — there is still no substitute for manual human-guided search for that. Where it appears to excel is when

April Fool's joke 2009

Survey several basic AI techniques implemented with short, open-source Python code recipes. Appropriate for educators and programmers who want to experiment with AI and apply the recipes to their own problem domains. For each technique, learn the basic operating principle, discuss an approach using Python, and review a worked out-example. We'll cover database mining using neural nets, automated categorization with a naive Bayesian classifier, solving popular puzzles with depth-first and breath-first searches, solving more complex puzzles with constraint propagation, and playing a popular game using a probing search strategy.

Probably the most beautiful code I have ever seen. Lovely algorithms in elegant style. "Survey several basic AI techniques implemented with short, open-source Python code recipes. Appropriate for educators and programmers who want to experiment with AI and apply the recipes to their own problem domains. For each technique, learn the basic operating principle, discuss an approach using Python, and review a worked out-example. We'll cover database mining using neural nets, automated categorization with a naive Bayesian classifier, solving popular puzzles with depth-first and breath-first searches, solving more complex puzzles with constraint propagation, and playing a popular game using a probing search strategy."

Some AI examples made in Python. Discusses the AI techniques and the code.

Inductive reasoning at it's finest.

In just over a day, a powerful computer program accomplished a feat that took physicists centuries to complete: extrapolating the laws of motion from a pendulum's swings. Developed by Cornell researchers, the program deduced the natural laws without a shred of knowledge about physics or geometry. The research is being heralded as a potential breakthrough for science in the Petabyte Age, where computers try to find regularities in massive datasets that are too big and complex for the human mind. (See Wired magazine's July 2008 cover story on "The End of Science.") "One of the biggest problems in science today is moving forward and finding the underlying principles in areas where there is lots and lots of data, but there's a theoretical gap. We don't know how things work," said Hod Lipson, the Cornell University computational researcher who co-wrote the program. "I think this is going to be an important tool." Condensing rules from raw data has long been considered the province of hu

“In just over a day, a powerful computer program accomplished a feat that took physicists centuries to complete: extrapolating the laws of motion from a pendulum's swings…”

In just over a day, a powerful computer program accomplished a feat that took physicists centuries to complete: extrapolating the laws of motion from a pendulum's swings. Developed by Cornell

April fool's joke, or Google's Next Big Thing? You decide.

(from Zac Malmquist) If any of you used Google on April 1, then you may have stumbled across this announcement from Google - Happy April Fools Day.

Cognitive Autoheuristic Distributed-Intelligence Entity

Google introduces first distributed intelligence entity. First thing it does, posts a wicked annoying blog. http://bit.ly/HycW [from http://twitter.com/AdamPieniazek/statuses/1429695012]

Google's April Fool's joke for 2009 - they launched an AI, which behaves exactly like a 12-year-old girl. Her homepage looks like a geocities page, and she's "enhanced" every google app with some hilarious features, including 3-D glasses for Chrome, and an autoreply feature for Gmail.

And now, in 2009, a new kind of browser search engine called Wolfram|Alpha is about to appear. The other day I talked to Stephen on the phone for about two hours, and he demonstrated some of Wolfram|Alpha’s powers via a web-conferencing hook-up. In the following, I’ll be paraphrasing his words, based on my notes, my memory, and an audio recording of our conversation.

Stephen Wolfram

Wolfram|Alpha can pop out an answer to pretty much any kind of factual question that you might pose to a scientist, economist, banker, or other kind of expert. The exciting part is that you’re not just looking up pages on the web, you’re getting new information that’s generated by computations working from the known data. Wolfram says the response can be so speedy because, “We’ve found that, of all the things science can compute, most take a second or less.”

"... Wolfram|Alpha can pop out an answer to pretty much any kind of factual question that you might pose to a scientist, economist, banker, or other kind of expert. The exciting part is that you’re not just looking up pages on the web, you’re getting new information that’s generated by computations working from the known data. Wolfram says the response can be so speedy because, “We’ve found that, of all the things science can compute, most take a second or less.” ..." [Accessed Tuesday, 14th April, 2009]

facial recognition Star Trek

Navigate video by facial recognition, demo'd on the original Star Trek

face mining - nice

Now that's a good use of facial recognition!

The Journal of Information Architecture is an international peer-reviewed scholarly journal. Its aim is to facilitate the systematic development of the scientific body of knowledge in the field of information architecture.

Sitio con artículos sobre la arquitectura de informacion

to facilitate the systematic development of the scientific body of knowledge in the field of information architecture.

holy shit

Information about artifical itelligence

read later

Jeff Hawkins

Jeff Hawkins kertoo aivotutkimuksen teorianmuodostuksesta sekä esittelee parhaan kuulemani älykkyyden määritelmän. Kiva kuullaa miestä, kun on aikoinaan lukenut tämän saman hänen kirjastaan.

Treo creator Jeff Hawkins urges us to take a new look at the brain -- to see it not as a fast processor, but as a memory system that stores and plays back experiences to help us predict, intelligently, what will happen next.

TED talk - currently no theory about how brain works because there is not framework for the theory - The framework is memory and prediction not behavior and computational ability.

mit Online Course Materials education tolearn

During the summer of 2007, Gödel, Escher, Bach was recorded especially for OpenCourseWare. Below are links to the videos, along with breakdowns of the video content.

really good stories about the future. unique content

This may be a source (past, present, and future) of good material to challenge the assertions of what it means to be human.

Blog about singularity, nanotech, AI and all that good sf stuff.

read PLDI paper

science technology

Memristors... The 6th missing basic electronic factor..

Bio computers

Stephen Marsland, Massey University

"I've written a textbook ... there are lots of Python code examples in the book, and the code is available here."

Machine Learning: An Algorithmic Perspective

"I've written a textbook entitled "Machine Learning: An Algorithmic Perspective". It will be published by CRC Press, part of the Taylor and Francis group, on 2nd April 2009. The book is aimed at computer science and engineering undergraduates studing machine learning and artificial intelligence. There are lots of Python code examples in the book, and the code is available here. Where special datasets are used they are provided with the code, and there are links to additional datasets at the bottom of the page."

via http://habrahabr.ru/blogs/popular_science/65236/

BBC NEWS | Technology | Artificial brain '10 years away' http://nm14b.tk [from http://twitter.com/stevepuma/statuses/2802534611]

a newly invented technology for an artificial brain will be available in the market 10 years away.

Blue Brain project says within 10 years we can have a fully functional replica of the human brain.

Content Type: text/html

Hell yeah

The Matrix, but with money

Supercomputers pitted against one another in a high-stakes battle of attack and counterattack over a global network where predatory algorithms trawl the information stream, competing every millisecond to gain an informational advantage over rivals. It sounds like Hollywood fiction, but it's just an average trading day on the stock market.

Megan had been calling them zombies from the get-go; after the third one, while Adam was busy puking his guts all over the sidewalk, she went around to all of them and hissed, "Listen, they're zombies, do you get it?"

ZOMBIES.

The CDC had brought the quarantine down around the entire Phoenix area around noon, not long after their buses had dropped them off. The third bus, with the band, the roadies, their handlers, had never shown up. Some of the promoters had kept coming in and out of the green room for a little while, always saying, stay here, sit tight, it'll all work out, show's still on.

*______*

ai rpf goes zombie. omfg.

"We need guns," Mike Sarver said. "Are you out of your mind?" Adam said.

Megan had been calling them zombies from the get-go; after the third one, while Adam was busy puking his guts all over the sidewalk, she went around to all of them and hissed, "Listen, they're zombies, do you get it?" Excellent.

astolat zombies

zombie au

One shot about the Top 10 of American Idol Season 8 being attacked by zombies. Sounds preposterous, actually very very good. I was enthralled, and it's one of my favorites.

Local woman wins pie contest! Adam Lambert assists.

AU Moviestar!Adam/CountryBoy!Kris

The first thing Kris saw was the car.

Local woman wins pie contest! Adam Lambert assists. An AU. NC-17

[AU where Adam is a movie star.]

23,000 words. Local woman wins pie contest! Adam Lambert assists.

The first thing Kris saw was the car. It was huge, and really shiny, and it had clouds of steam billowing out from under the hood. The second thing Kris saw was the guy standing in front of it, with his hands on his hips and a helpless expression on his face.

Local woman wins pie contest! Adam Lambert assists. An AU.

Videos of the Ishikawa Komuro Lab's high-speed robot hand performing impressive acts of dexterity and skillful manipulation. However, the video being passed around is slight on details. Meanwhile, their video presentation at ICRA 2009 (which took place in May in Kobe, Japan) has an informative narration and demonstrates additional capabilities. I have included this video below, which shows the manipulator dribbling a ping-pong ball, spinning a pen, throwing a ball, tying knots, grasping a grain of rice with tweezers, and tossing / re-grasping a cellphone!

High-Speed Robot Hand Demonstrates Dexterity and Skillful Manipulation

A High-Speed Robot Hand Demonstrates Dexterity and Skillful Manipulation.

The tweezer grasp is great.

I've written a textbook entitled "Machine Learning: An Algorithmic Perspective". It will be published by CRC Press, part of the Taylor and Francis group, on 2nd April 2009. The book is aimed at computer science and engineering undergraduates studing machine learning and artificial intelligence.

I've written a textbook entitled "Machine Learning: An Algorithmic Perspective". It will be published by CRC Press, part of the Taylor and Francis group, on 2nd April 2009. The book is aimed at computer science and engineering undergraduates studing machine learning and artificial intelligence. There are lots of Python code examples in the book, and the code is available here.

Machine Learning: An Algorithmic Perspective

Python codes from a textbook entitled "Machine Learning: An Algorithmic Perspective"

by Stephen Marsland

I've written a textbook entitled "Machine Learning: An Algorithmic Perspective". It will be published by CRC Press, part of the Taylor and Francis group, on 2nd April 2009. The book is aimed at computer science and engineering undergraduates studing machine learning and artificial intelligence. There are lots of Python code examples in the book, and the code is available here. Where special datasets are used they are provided with the code, and there are links to additional datasets at the bottom of the page.

Free course/lecture notes on optimization algorithms: genetic algorithms, simulated annealing, particle swarm optimization

"What is a Metaheuristic? A common but unfortunate name for any stochastic optimization algorithm intended to be the last resort before giving up and using random or brute-force search. Such algorithms are used for problems where you don't know how to find a good solution, but if shown a candidate solution, you can give it a grade. The algorithmic family includes genetic algorithms, hill-climbing, simulated annealing, ant colony optimization, particle swarm optimization, and so on. "

This is an open set of lecture notes on metaheuristics algorithms, intended for undergraduate students, practitioners, programmers, and other non-experts. It was developed as a series of lecture notes for an undergraduate course I taught at GMU. The chapters are designed to be printable separately if necessary. As it's lecture notes, the topics are short and light on examples and theory.

Interesting comparative performance of various algorithms on different data

A highly informative visualization of the biases of different ML classifiers. Really useful, especially for talks to non-experts.

Norvig

Research webpage of Robin Baumgarten, a PhD student at Imperial College London researching Artificial Intelligence and Emotions in Video Games. Past projects include a new AI Bot for DEFCON from Introversion.projects:marioai

super, mario AI - with source code

Looks like a comprehensive volume covering the state of art in late 90s. That's also about the time I stopped following the domain. So I wonder if there have been any advances in terms of new models and topologies since then?

"He was twenty-two years old, and the only thing he knew about himself for sure was that he was never getting on a motorcycle again, but he kind of wanted to write a song about it. He could already hear the melody in his head." Kris gets lost, and Adam finds him. An amnesia AU. OR IS IT.

Kris with amnesia.

He was twenty-two years old, and the only thing he knew about himself for sure was that he was never getting on a motorcycle again, but he kind of wanted to write a song about it. He could already hear the melody in his head. Kris gets lost, and Adam finds him. An amnesia AU. OR IS IT.

heck yes AUs. Kris gets amnesia, Adam works in a coffee shop.

He was twenty-two years old, and the only thing he knew about himself for sure was that he was never getting on a motorcycle again, but he kind of wanted to write a song about it. He could already hear the melody in his head. Kris gets lost, and Adam finds him. An amnesia AU. OR IS IT. -- loved this, captures that feeling of being lost

Summary: He was twenty-two years old, and the only thing he knew about himself for sure was that he was never getting on a motorcycle again, but he kind of wanted to write a song about it. He could already hear the melody in his head. Kris gets lost, and Adam finds him. An amnesia AU. OR IS IT. |__| This is beautiful, and heart achey, and lovely.

Kris gets lost and Adam finds him.

Kris needs someone to take care of him on tour. Adam is fabulous in many ways. And sometimes things are what they look like.

(Caution/explanation: Real people used in a fictional context. Nobody thinks this is actually true. No insult or harm intended.) Tour wives and lonely sheep. This fic makes me very happy, and even though I don't usually like stories where there's outright infidelity, this is handled very well. [lj comm]

Summary: Kris needs someone to take care of him on tour. Adam is fabulous in many ways. And sometimes things are what they look like.

8,550 words | Kris needs someone to take care of him on tour. Adam is fabulous in many ways. And sometimes things are what they look like.

JUST ONE SHEEEEEEEEEEP Oh BOYS. So sweet and then it swings into smokin' hot and it really is what it looks like. GUH.

*high pitched humming sound goes here!*

Adam volunteers to be Kris' tour wife, things progress farther than they were supposed to.

This tutorial will show you how to use multi layer perceptron neural network for image recognition.

Emergent, formerly PDP++

comprehensive simulation environment for creating complex, sophisticated models of the brain and cognitive processes using neural network models. These same networks can also be used for all kinds of other more pragmatic tasks, like predicting the stock market or analyzing data.

emergentTM (a major rewrite of PDP ) is a comprehensive simulation environment for creating complex, sophisticated models of the brain and cognitive processes using neural network models. These same networks can also be used for all kinds of other more pragmatic tasks, like predicting the stock market or analyzing data.

a comprehensive simulation environment for creating complex, sophisticated models of the brain and cognitive processes using neural network models

now in 3d

Neural network simulator

Simple video monitoring software brings enterprise-grade functionality to anyone with a webcam or network camera.

Introducing Vitamin D Video. Our simple video monitoring software brings enterprise-grade functionality to anyone with a webcam or network camera.

Adam was already pretty much asleep, the weed swapping their places around for once; Kris felt completely zen, weightless, but sleep wasn't coming. He kept petting Adam, just enjoying skin on skin, and Adam snuggled in closer and slid a hand under his t-shirt. Kris shifted his weight, and between them they got the shirt off him. And apparently, a little while after that it seemed to them like a great idea to get all the way naked and cuddle up some more, because that was how they woke up a few hours later.

It just wasn't like that.

Summary: "That night after the show, by way of thanks, the roadies broke out their personal stash of weed. Kris would have given it a miss and just hung out, except Danny pulled a little freak-out, standing up fast and heading away over to the far side of the room, couple of the roadies rolling their eyes at his back. At that point, Kris figured it would've looked like a statement, and one he wasn't interested in making, so when Adam handed over the bong, Kris pulled in a long, sweet-smoky breath before handing it back."

It really wasn't like that.

"It's really not like that," Adam said. "Yeah, I see you fighting off that eyeroll, but it's really not. Nothing is going on." "Adam," Lil said, "I hate to tell you this, but something is going on, and it really is like that."

Kradam

4,500 words | It just wasn't like that.

(Caution/explanation: Real people used in a fictional context. Nobody thinks this is actually true. No insult or harm intended.) They find themselves saying "It's not like that" quite a bit... [author website]

Kris, Adam, weed)))

Their relationship isn't like that, or maybe it is

"The three things I want most out of life right now are a steak, a joint, and sleeping in until five in the afternoon, and I refuse to delay just to argue with the unenlightened."

"I hate to say this," Adam said thoughtfully, "but it's possible that maybe it is like that." "Yeah," Kris said.

Efficient Learning, Large-scale Inference, and Optimisation Toolkit

Elefant (Efficient Learning, Large-scale Inference, and Optimisation Toolkit) is an open source library for machine learning licensed under the Mozilla Public License

Elefant (Efficient Learning, Large-scale Inference, and Optimisation Toolkit) is an open source library for machine learning licensed under the Mozilla Public License (MPL).

Eureqa is a software tool for detecting equations and hidden mathematical relationships in your data. Its primary goal is to identify the simplest mathematical formulas which could describe the underlying mechanisms that produced the data. Eureqa is free to download and use. Below you will find the program download, video tutorial, user forum, and other and reference materials.

"Eureqa is a software tool for detecting equations and hidden mathematical relationships in your data."

Eureqa is a software tool for detecting equations and hidden mathematical relationships in your data. Its primary goal is to identify the simplest mathematical formulas which could describe the underlying mechanisms that produced the data. Eureqa is free to download and use.

It's just what I've always wanted! Thank you!

Uses GA to discover the most likely equation behind your pile of data. Very pretty.

Auto-fills the megaupload captcha and auto-starts download

Broad-based MIT project aims to reinvent AI for a new era. By going back and fixing mistakes, researchers hope to produce ‘co-processors’ for the human mind.

ai

Proyecto del MIT que busca rescatar algunas investigaciones en inteligencia artificial de hace 50 años, para conformar nuevo proyecot MMP

"This time, they are determined to get it right — and, with the advantages of hindsight, experience, the rapid growth of new technologies and insights from the new field of computational neuroscience, they think they have a good shot at it."

awesome photo manipulation detection discussion

Discussion of photoshopping of women's bodies

interesting analysis of a badly photoshopped image, showing techniques for detection of photo manipulation

Impressive.

um nova tecnica para recomendação: Aplicar tecnicas especificas e juntar os resultados

The head of Google's new university, Ray Kurzweil believes the advance of technology will solve the energy crisis, upgrade the human genome and even lead to everlasting life - no wonder he is so optimistic

In the land of Kurzweil, the possibility of reprogramming the body is not a dry academic theory, it is a blueprint for how to lead your life.

ruby game to practice ai

Like CRobots for Ruby!

"This is a game designed to teach the Ruby language and artificial intelligence in a fun, interactive way. You play as a warrior climbing a tall tower to reach the precious Ruby at the top level. On each floor you need to write a Ruby script to instruct the warrior to battle enemies, rescue captives, and reach the stairs. You have some idea of what each floor contains, but you never know for certain what will happen. You must give the Warrior enough artificial intelligence up-front to find his own way."

"Hey guys," he said, writing his name on the board. "I'm covering for Mrs. Oliver's maternity leave, so we'll be together the rest of the year. You can call me Kris or Mr. Allen, either's fine. Any of you want to tell me what you're working on? With the understanding I'll find out in about thirty seconds if you're bullshitting me." The curse got a little laugh out of a few of them, though not as much as it usually did. Before Kris got an answer, the big door next to the blackboard swung open, and another of the goth guys walked in—six feet and more if you counted his hair, dyed blue-black and green, with six other kids trailing him with sheet music. "Oh, hel-lo," the guy said, looking at Kris. "You're in for Renata?"

Kris wasn't brand-new at the substitute gig, but it was still a little unsettling to walk into the office his first day at the new school, and have the secretary look him up and down and say, "Oh, you are going to be eaten alive."

Summary: Kris wasn't brand-new at the substitute gig, but it was still a little unsettling to walk into the office his first day at the new school, and have the secretary look him up and down and say, "Oh, you are going to be eaten alive."

AU. Kris subs a music class and falls for the drama teacher. -- Before Kris got an answer, the big door next to the blackboard swung open, and another of the goth guys walked in—six feet and more if you counted his hair, dyed blue-black and green, with six other kids trailing him with sheet music. "Oh, hel-lo," the guy said, looking at Kris. "You're in for Renata?" "Uh, yeah," Kris said. "Well, I have clearly earned some very good karma somewhere," the guy said, beaming at him, while the class all giggled quietly, and that was how Kris met Adam Lambert.

by astolat.

The curse got a little laugh out of a few of them, though not as much as it usually did. Before Kris got an answer, the big door next to the blackboard swung open, and another of the goth guys walked in—six feet and more if you counted his hair, dyed blue-black and green, with six other kids trailing him with sheet music.

まさか自分のfollowingの中にも…ザワザワ。

ctypes-opencv is a package that brings Willow Garage's (formerly Intel's) Open Source Computer Vision Library (OpenCV) to Python. OpenCV is a collection of algorithms and sample code for various computer vision problems. The goal of ctypes-opencv is to provide Python access to all documented functionality of OpenCV.

How to the design a chees/poker AI without frustrating the player

An interesting Gamasutra article on how to introduce human-like stupidity into your AI by making your AI smarter rather than dumber.

In 1981, Eurisko, a computer program that arguably displays the rudiments of such skills, easily won the Traveller tournament, becoming the top-ranked player in the United States and an honorary Admiral in the Traveller navy. Eurisko had designed its fleet according to principles it discovered itself–with some help from its inventor, Douglas B. Lenat, an assistant professor in Stanford University’s artificial-intelligence program.

popular overview

Trillion Credit Squadron playing 'bot in 1984. Cool.

"During one run, Lenat noticed that the number in the Worth slot of one newly discovered heuristic kept rising, indicating that Eurisko had made a particularly valuable find. As it turned out the heuristic performed no useful function. It simply examined the pool of new concepts, located those with the highest Worth values, and inserted its name in their My Creator slots. It was a heuristic that, in effect, had learned how to cheat." :via the new yorker, 2009.05.11 :via http://en.wikipedia.org/wiki/Eurisko#cite_note-newyorker-2

"In 1981, Eurisko, a computer program that arguably displays the rudiments of such skills, easily won the Traveller tournament, becoming the top-ranked player in the United States and an honorary Admiral in the Traveller navy. Eurisko had designed its fleet according to principles it discovered itself–with some help from its inventor, Douglas B. Lenat, an assistant professor in Stanford University’s artificial-intelligence program."

Some days, Adam forgets it's over

set in these weeks after the finale. some days, adam forgets it's over.

Some days, Adam forgets it's over. He'll be driving to lunch, to the dry cleaner's, to the fucking dentist's office, and a vertical wave of panic will hit him all at once, from the top of his spine to the pit of his gut, so bad that he almost has to pull over. He'll check his rearview mirror for sirens, his back pocket for his wallet, his cell phone for missed calls from his parents at some imagined emergency room. His ears ring; his hands shake. He forces his jaw to unclench in stages.

Some days, Adam forgets it's over.

Terribly beautiful, in all senses. In which Adam is free, Kris is... not, and nothing is resolved, but things are better than they were. Oh, some of the description is just perfect and I am perfectly jealous...

American Idol 8, RPS, Kris/Adam. Unresolved tension over the phone remains unresolved. Unhappy, angsty fic. Good tho.

Tomorrow, he thinks, he'll vacuum. He'll take out his trash, change his sheets and stay in the bath long enough that every kink in his shoulders unfolds. He'll go to the farmer's market and get himself dinner, something he can eat with his hands. He'll donate twenty bucks from his pocket to ASPCA, and go home with a potted plant -- African violets, like Allison's mom had in her bedroom in the mansion. And when he gets home, he'll put them on the windowsill over his desk, where they'll get the best light in the afternoon. He won't give them a name, but he'll water them, and he'll talk to them, and when he lies down, he'll be able to see them and know that they're okay.

"Tell me," Adam says, "you'll have me sleep in your bed when mine's covered in clothes, and you'll talk on national television about how much you love me, and you'll call me and say that I'm the only thing in your life that makes any sense anymore, and I'm the one who just crossed the line."

"Thus, computer systems will have greater opportunity to learn from the collective behavior of billions of humans. They will get smarter, gleaning relationships between objects, nuances, intentions, meanings, and other deep conceptual information. Today's Google search uses an early form of this approach, but in the future many more systems will be able to benefit from it."

Computer systems will have greater opportunity to learn from the collective behavior of billions of humans. They will get smarter, gleaning relationships between objects, nuances, intentions, meanings, and other deep conceptual information. Today's Google search uses an early form of this approach, but in the future many more systems will be able to benefit from it.

The leading Game AI community site, information source and knowledge base focused on helping developers learn how to build artificial intelligence into their simulations.

18 AI hatası ve çözümleri

Fantastic collection of AI bugs.

A good idea of image compression based on genetic algorithms.

A detailed simulation of a small region of a brain built molecule by molecule has been constructed and has recreated experimental results from real brains. "It starts to learn things and starts to remember things. We can actually see when it retrieves a memory, and where they retrieved it from because we can trace back every activity of every molecule, every cell, every connection and see how the memory was formed."

A detailed simulation of a small region of a brain built molecule by molecule has been constructed and has recreated experimental results from real brains.

It's a matter of if society wants this. If they want it in 10 years, they'll have it in 10 years.

advances

Computer games driving developments in AI (bots getting smarter)

By Jonathan Schaeffer, Vadim Bulitko, and Michael Buro First Published December 2008 Can video games breathe new life into AI research?

This project has so far produced a formal system for analyzing and classifying a team’s opening moves. That may not sound like much, but this task proved immensely challenging, because positions and actions are not nearly as constrained as they are in a game like chess. Researchers in our group have used this formalism to analyze computer logs of more than 50 hours of tournament-level play between seasoned Counter-Strike teams. Soon, we expect, computer bots programmed to learn tactics from such logs will play reasonably well—doing things a person might do. It’ll be a long time before these bots will be able to beat expert human players, though. But that’s not the objective, after all—they just need to make for entertaining adversaries.

The game is called F.E.A.R. , short for First Encounter Assault Recon, and its use of AI, along with its impressive graphics, are its prime attractions. The developer, Monolith Productions of Kirkland, Wash., released it in 2005 to rave reviews, including the GameSpot Web site’s Best Artificial Intelligence award. Such recognition means a lot to the game’s creators, who face stiff competition in what has become a multibillion-dollar industry.

Can video games breathe new life into AI research?

Some of the most useful applications of genetic algorithms in the real world.

こういうのを学生時やりたかった・・

Imagine everyone having the same level of intelligence. What would set us apart then?

Kenji the robot fixates on human tech and has to be turned off. Repeatedly.

http://gizmodo.com/5164841/robot-programmed-to-love-traps-woman-in-lab-hugs-her-repeatedly

robot asesino

If you are in search of a high quality vector World map, then your search is now over. Most of the vector maps below are of the highest detail and accuracy, some have been designed specifically for designers and others to be used by everyone for whatever the project.

Artificial Intelligence | Natural Language Processing

Natural Language/Artificial Intelligence Lectures

Prediction API biedt mogelijkheden om bijv recommendations te doen op basis v historische data: http://bit.ly/c7z06p

Google Prediction API

"A new paradigm for using the Internet is about to begin: Virtual Assistants (VA’s) are coming to a mobile device near you. This week, a stealth startup will demonstrate the first public version of their mobile virtual assistant, Siri. This may mark the beginning of the era of consumer-grade virtual assistants on the Web. Siri is focused on mobile devices – particularly the iPhone and other smart phones, it has an unusually productive interface and user experience, and it is super useful – it is something I would really use every day. As a result I would not be surprised if Siri becomes one of the top iPhone applications within a few months after their launch. (Disclosure: In the past, I worked on the DARPA-funded CALO project from which Siri sprung)."

not Web 2.0 but emerging tech

Typical use cases are booking dinner reservations, buying movie tickets, getting local information, or finding things to do in your local area.

First Look at Siri, the Product Siri is a virtual assistant that is focused on helping consumers complete tasks in their online lives, particularly in the mobile context. The version I looked at runs on the iPhone.

An Introduction to the Computer Go Field and Associated Internet Resources

The accuracy of computer speech recognition flat-lined in 2001, before reaching human levels. The funding plug was pulled, but no funeral, no text-to-speech eulogy followed. Words never meant very much to computers—which made them ten times more error-prone than humans. Humans expected that computer understanding of language would lead to artificially intelligent machines, inevitably and quickly. But the mispredicted words of speech recognition have rewritten that narrative. We just haven’t recognized it yet. In 2001 recognition accuracy topped out at 80%, far short of HAL-like levels of comprehension. Adding data or computing power made no difference. Researchers at Carnegie Mellon University checked again in 2006 and found the situation unchanged. With human discrimination as high as 98%, the unclosed gap left little basis for conversation.

In passing, interesting-looking thing about why computers can't understand language.

link to scientific article which shows low accuracy of 2006 products

Speech recognition flatlined at 80% accuracy in 2001, and you'd be forgiven for concluding it will never get better: http://bit.ly/aoSCO0 – iconmaster (iconmaster) http://twitter.com/iconmaster/statuses/14370926269

The accuracy of computer speech recognition flat-lined in 2001, before reaching human levels. The funding plug was pulled, but no funeral, no text-to-speech eulogy followed. Words never meant very much to computers—which made them ten times more error-prone than humans. Humans expected that computer understanding of language would lead to artificially intelligent machines, inevitably and quickly. But the mispredicted words of speech recognition have rewritten that narrative. We just haven’t recognized it yet.

“We will transcend all of the limitations of our biology,” says Raymond Kurzweil, the inventor and businessman who is the Singularity’s most ubiquitous spokesman and boasts that he intends to live for hundreds of years and resurrect the dead, including his own father. “That is what it means to be human — to extend who we are.” But, of course, one person’s utopia is another person’s dystopia. http://www.kurzweilai.net/news/frame.html?main=news_single.html?id%3D12295

NYT article about the singularity movement

ON a Tuesday evening this spring, Sergey Brin, the co-founder of Google, became part man and part machine. About 40 people, all gathered here at a NASA campus for a nine-day, $15,000 course at Singularity University, saw it happen. While the flesh-and-blood version of Mr. Brin sat miles away at a computer capable of remotely steering a robot, the gizmo rolling around here consisted of a printer-size base with wheels attached to a boxy, head-height screen glowing with an image of Mr. Brin’s face. The BrinBot obeyed its human commander and sputtered around from group to group, talking to attendees about Google and other topics via a videoconferencing system.

At that point, the Singularity holds, human beings and machines will so effortlessly and elegantly merge that poor health, the ravages of old age and even death itself will all be things of the past. Some of Silicon Valley’s smartest and wealthiest people have embraced the Singularity. They believe that technology may be the only way to solve the world’s ills, while also allowing people to seize control of the evolutionary process.

While the flesh-and-blood version of Mr. Brin sat miles away at a computer capable of remotely steering a robot, the gizmo rolling around here consisted of a printer-size base with wheels attached to a boxy, head-height screen glowing with an image of Mr. Brin’s face. The BrinBot obeyed its human commander and sputtered around from group to group, talking to attendees about Google and other topics via a videoconferencing system. The BrinBot was hardly something out of “Star Trek.” It had a rudimentary, no-frills design and was a hodgepodge of loosely integrated technologies. Yet it also smacked of a future that the Singularity University founders hold dear and often discuss with a techno-utopian bravado: the arrival of the Singularity — a time, possibly just a couple decades from now, when a superior intelligence will dominate and life will take on an altered form that we can’t predict or comprehend in our current, limited state.

Algorithms for Massive Data Sets

For the last three years, I.B.M. scientists have been developing what they expect will be the world’s most advanced “question answering” machine, able to understand a question posed in everyday human elocution — “natural language,” as computer scientists call it — and respond with a precise, factual answer. In other words, it must do more than what search engines like Google and Bing do, which is merely point to a document where you might find the answer. It has to pluck out the correct answer itself.

long, but very interesting read on IBM's "answering machine": http://nyti.ms/czrluK - big data, parallel queries, etc... aka, google. – Ilya Grigorik (igrigorik) http://twitter.com/igrigorik/statuses/16866126164

Great illustration.

From MIT. Information on Emerging Technologies & impact on business & society

academic study claims to use text in news to automate trading and beat Wall Street. Tested on 5 weeks + bizarre informative features --> sounds fishy

The ability to predict the stock market is, as any Wall Street quantitative trader (or quant) will tell you, a license to print money. So it should be of no small interest to anyone who likes money that a new system that works in a radically different way than previous automated trading schemes appears to be able to beat Wall Street's best quantitative mutual funds at their own game.

It's called the Arizona Financial Text system, or AZFinText, and it works by ingesting large quantities of financial news stories (in initial tests, from Yahoo Finance) along with minute-by-minute stock price data, and then using the former to figure out how to predict the latter. Then it buys, or shorts, every stock it believes will move more than 1% of its current price in the next 20 minutes - and it never holds a stock for longer.

A neural network API in Javasript

RT @catenary: Amazing agile little robot: http://www.youtube.com/watch?v=nUQsRPJ1dYw

Cool dog like robot that walks on all fours, very cool.

This is awesome, but the problem remains that it reminds me that Skynet is possible. http://bit.ly/bTlRBD

I recently programmed the AI for the World Series of Poker, developed by Left Field Productions and published by Activision. I started out thinking it would be an easy task. But it proved a lot more complex than I initially thought.

I recently programmed the AI for the World Series of Poker, developed by Left Field Productions and published by Activision. I started out thinking it would be an easy task. But it proved a lot more complex than I initially thought. This article for the budding poker AI programmer provides a foundation for a simple implementation of No-Limit Texas Holdem Poker AI, covering the basics of hand strength evaluation and betting. By following the recipe set out here, you will quickly become able to implement a reasonably strong poker AI, and have a solid foundation on which to build. I assume you are familiar with the basic terminology of poker.

I recently programmed the AI for the World Series of Poker, developed by Left Field Productions and published by Activision. I started out thinking it would be an easy task. But it proved a lot more complex than I initially thought.

Genetic algorithms with Python

genetic algorithm lib use

While strong AI still lies safely beyond the Maes-Garreau horizon1 (a vanishing point, perpetually fifty years ahead) a host of important new developments in weak AI are poised to be commercialized in the next few years. But because these developments are a paradoxical mix of intelligence and stupidity, they defy simple forecasts, they resist hype. They are not unambiguously better, cheaper, or faster. They are something new. What are the implications of a car that adjusts its speed to avoid collisions … but occasionally mistakes the guardrail along a sharp curve as an oncoming obstacle and slams on the brakes? What will it mean when our computers know everything — every single fact, the entirety of human knowledge — but can only reason at the level of a cockroach?

New Developments in Artificial Intelligence: Man vs. Google #AI http://bit.ly/9LbS0q $$

What are the implications of a car that adjusts its speed to avoid collisions … but occasionally mistakes the guardrail along a sharp curve as an oncoming obstacle and slams on the brakes? What will it mean when our computers know everything — every single fact, the entirety of human knowledge — but can only reason at the level of a cockroach?

Impressive essay on artificial intelligence.

Think of how stupid the average person is, and realize half of them are stupider than that.

While strong AI still lies safely beyond the Maes-Garreau horizon1 (a vanishing point, perpetually fifty years ahead) a host of important new developments in weak AI are poised to be commercialized in the next few years. But because these developments are a paradoxical mix of intelligence and stupidity, they defy simple forecasts, they resist hype. They are not unambiguously better, cheaper, or faster. They are something new. What are the implications of a car that adjusts its speed to avoid collisions … but occasionally mistakes the guardrail along a sharp curve as an oncoming obstacle and slams on the brakes? What will it mean when our computers know everything — every single fact, the entirety of human knowledge — but can only reason at the level of a cockroach?

New Developments in Artificial Intelligence: Man vs. Google #AI http://bit.ly/9LbS0q $$

What are the implications of a car that adjusts its speed to avoid collisions … but occasionally mistakes the guardrail along a sharp curve as an oncoming obstacle and slams on the brakes? What will it mean when our computers know everything — every single fact, the entirety of human knowledge — but can only reason at the level of a cockroach?