Educational CyberPlayGround ®☰ Menu

CHATTERBOTS: Talking Computers and teaching HTML Computer Language

Dr. Kenneth Mark Colby, a psychiatrist known for his work with artificial intelligence, died on April 20 at his home in Malibu, Calif. He was 81. Dr. Colby, a founder and chairman of Malibu Artifactual Intelligence Works, a software company, was an emeritus professor of psychiatry and behavioral sciences at the University of California at Los Angeles. He created one of the early software programs known as chatterbots, which simulate conversations with people. His program, called Parry, for paranoia, appeared in 1971 and is said to be the only one to have passed the "Turing test," named for the British mathematician Alan M. Turing, who in 1950 suggested that if a computer could successfully impersonate a human by carrying on a typed conversation with a person, it could be called intelligent.


"Talking" helps computer programs develop better hunting strategies

2 FEBRUARY 2001 Penn State University Park, PA

An NEC Institute/Penn State study shows that computer programs, known as autonomous agents, not only can evolve their own language and talk with one another, but also can use communication to improve their performance in solving the classic predator-prey problem. Like kids playing hide and seek, the autonomous agents used in the study hunted for and found their prey faster and more efficiently if they communicated with one another.

"Talking," via a message board, enabled the agents to perform better than in all previous predator-prey studies -better even than when they had been programmed with a hunting strategy by humans. Dr. C. Lee Giles, the David Reese Professor of Information Sciences and Technology and co-author of the study, says, "The findings have a number of possible applications, for example, smart web crawlers that communicate with one another as they scour the web automatically retrieving information. One can also imagine military applications or intelligent robots that explore other planets or the sea bed in groups while talking to one another."

The findings are detailed in a paper, "Talking Helps: Evolving Communicating Agents for the Predate-Prey Pursuit Problem," published in the current (6:3) issue of the journal, Artificial Life. The work was performed when Giles and co-author Kam-Chuen Jim were both at NEC Research Institute, Inc. Jim is currently at Physiome Sciences, Inc. Giles joined Penn State's new School of Information Sciences and Technology in Fall 2000.

In the study, four predator agents inhabiting a virtual, four-sided, two-dimensional-grid world, were set in pursuit of a fifth agent who served as the prey. The agents all moved simultaneously, at the same speed in north, south, east or west directions. No diagonal shortcuts were permitted. The predators could not see each other and did not know each other's location. The researchers write that this scenario is
probably more difficult for the predators than any considered in previous studies of the predator-prey problem.

The predator agents' goal was to capture the prey by surrounding it on all four sides. Each of the predator agents could "speak" a short string of zeros and ones, the binary alphabet, simultaneously. The communicated strings of symbols were placed on a message board. Each agent could then read all the strings communicated by all the  predators in order to determine the next move and what to say next. The researchers explain that the agents created their own vocabulary, the strings of zeros and ones, in a random manner. Self-organization into meaningful "language" occurred because the agents are coupled in the sense that they must conform to a common vocabulary in order to cooperate through communication. Since the predators cannot see each other and do not know each other's location, the predators have to evolve a language that can represent such information. The researchers found that as the size of the language increased, the performance of the predators improved. Using this observation, the researchers developed a method for incrementally increasing the language size that results in a coarse-to-fine search that significantly reduces the time required to find a solution.

The researchers write that "Future work could focus on the semantics of the evolved languages." Giles notes that "We can compute the upper bound of the number of useful meanings that the predators can evolve. The actual number of useful meanings that they did evolve was much smaller."

Jim added, "We found that in the evolved languages each word can have multiple meanings, with the meaning determined by the semantic context. This phenomenon is also observed in natural languages."

"As the size of the language increases, the average number of meanings assigned to each word decreases," he said.

The researchers conclude by writing, "It would be an important step to extend the analysis introduced here to other forms of multi-agent communication structures, such as a system of agents that communicate asynchronously or only to their nearest neighbors.

Dr. Giles
[p] 814-865-3528




HTML is an excellent language to teach languages

Date: Thu, 11 Dec 1997 14:38:44 -0200
From: NA Webmaster <webmaster@NALEJANDRIA.COM.AR>
Subject: Useractive WebSite

Dear friends,

OK for all your comments on the benefits of using Web Editors for building web pages. It is obvious that if you want to produce a nice paper you should use a word processor, and that there is no need to know a jot of its intricacies.

But... aren't we supposed to be discussing the "educational uses of technology" instead of talking about the "applications of technology"?

In my opinion HTML is an excellent language to teach languages at the elementary school level. It exemplifies a lot of interesting points, and incidentally... it also produces nice web pages! You cannot do this with a text processor, because the coding is too complex and the macros are difficult to unravel for a, say, ten year old kid. But my fourth grade students proved able to program simple pages in HTML, had fun doing it, and their reasoning has improved notoriously ever since! Besides, they now have an insight into "computing" that they never suspected was there, i.e. they now know how at least some processes are controlled!

Hugo M. Castellano (Webmaster)

Nueva Alejandria Internet
Lideres en Conexiones Educativas en Latinoamerica
Buenos Aires, Argentina


It's great to have such a Web site for JavaScript -- but it's time to do our best to move entirely away from all HTML tagging. It was necessary when few (or no) good Web-page editors were available. Thank goodness, this has changed.

Date: Tue, 9 Dec 1997 01:45:17 -0600
From: Scott Gray<scotty@CM.MATH.UIUC.EDU>

Gary Kindly replied:

Scott Mills Gray
Date:Mon, 8 Dec 1997 07:38:07 -0700 "I hear and I forget, I see and I forget, I do and I forget" -- confused. From: "Gary E. Karcz" <Gary.Karcz@NAU.EDU>

Subject: Re: A UserActive WebSite

It's great to have such a Web site for JavaScript -- but it's time to do our best to move entirely away from all HTML tagging. It was necessary when few (or no) good Web-page editors were available. Thank goodness, this has changed.

Also, designing a Web site one page at a time tempts the creation of a 'spaghetti site': one that lacks good internal structure or organization.

Several, excellent site-management tools are helping us dig out of the Web's information avalanche. One of the best I've used is NetObjects'

Fusion <> --
available for both Mac and PC. It approaches Web publishing from a site-management perspective and has a nice editor: no HTML required! A 30-day trial version is available from its site. --Gary



Sure, but if you don't know HTML you can't do JavaScript. If you can't do JavaScript, then you are bound to merely making a 'clickable book' rather than an interactive experience.

Thanks, I'm going to give NetObjects a try!

Scott Gray


Date: Tue, 9 Dec 1997 17:08:50 -0500

From: Science Department <science@SCNC.CPS.K12.MI.US>

Subject: Re: A UserActive WebSite

Gary Karcz's contention that we should move "entirely" away from HTML is a bit too overstated for me. I don't think I'm ready to accept the premise that knowledge of HTML is no longer necessary or desirable just because the quality of Webpage editing software has improved.

This sounds too much like the unacceptable (to me) premise that as electronic calculators become more powerful and inexpensive we no longer need to concern ourselves with the development of basic arithmetic skills.

Has the improvement of word processors made handwriting ability valueless?

I am convinced that it will always be important to have the users of technology understand at least some of "the basics", the fundamental processes that the technology is carrying out for us; and that we should apply this principle as we design curriculum and help our students learn to use technology.

Of course we don't want to get so wrapped up in "the basics" that we and our students don't get to take advantage of new technology. That happens all too often in the educational system overall; we've become sort of notorious for it.

BTW, both Gary Karcz and Scott Gray have excellent sites regardless of their different approaches to getting there. I am a big fan of clean, quick-loading, attractive pages with valuable goodies for their intended audiences. Hope my webspinning looks so good when I get around to it.

Best wishes,

Larry Cartwright
Physics and Physical Science Teacher
Charlotte High School, Charlotte MI 48813


© Educational CyberPlayGround ® All rights reserved world wide.