Slashdot Mirror

G3ckoG33k: Perhaps you're referring to Adrian Thompson's work on FGPAs. See http://considerthefuture.com/Computing/CompArticles/comp2_evolve.html for a 2001 article which was featured on Slashdot. Also check out http://www.cogs.susx.ac.uk/users/adrianth/ascot/paper/paper.html and http://www.informatics.sussex.ac.uk/users/adrianth/ices96/paper.ps for relevant papers by Thompson on FGPA-based evolution.

This article mentions how it won't work on only the FPGA it was developed on.

Maybe you should have been +5 Funny, but not +4 Insightful.

An FPGA might very well be able to do very little. See Adrian Thompson's page, especially his 1990s work on evolving FPGA circuits.

'An FPGA' could be a very limited device.

sussex university have been doing it for ages.

http://www.cogs.susx.ac.uk/users/adrianth/ade.html

A colleague of mine is looking into alternative modes of computation. Whilst fluidics has long since been overtaken by the transistor, doing computation in liquids is still a hot topic.

I saw these guys talk about their paper "Pattern Recognition in a Bucket" - doing pattern recognition with some lego, a webcam, a perceptron and a bucket of water. Things like XOR, tone distinction and letter recognition. Pretty sweet stuff.

http://www.cogs.susx.ac.uk/users/sampsas/bucket.pd f
http://en.wikipedia.org/wiki/Liquid_State_Machine

Not according to the link you provided.

Quotation marks used in this way are informally called scare quotes. Scare quotes are quotation marks placed around a word or phrase from which you, the writer, wish to distance yourself because you consider that word or phrase to be odd or inappropriate for some reason.

The use of quotation marks can be extended to cases which are not exactly direct quotations. Here is an example:

Linguists sometimes employ a technique they call "inverted reconstruction".

The phrase in quote marks is not a quotation from anyone in particular, but merely a term which is used by some people -- in this case, linguists.

Scare quotes are quotation marks placed around a word or phrase from which you, the writer, wish to distance yourself because you consider that word or phrase to be odd or inappropriate for some reason. Possibly you regard it as too colloquial for formal writing; possibly you think it's unfamiliar or mysterious; possibly you consider it to be inaccurate or misleading; possibly you believe it's just plain wrong. Quite often scare quotes are used to express irony or sarcasm[...]

Apologies for this being my first post etc, but: "Well, even my British friends say putting the period outside the quotations is wrong. So, I don't see how this debate even started. In fact, other than wikipedia, I could not find another source that says to put the period outside the quote. Since wikipedia is done by anyone who feels like it, I tend to trust my friends over some silly website." A simple google spewed out the following useful discussions upon this topic: http://www.betterwritingskills.com/articles/quotat ion-marks.txt http://www.worldwidewords.org/qa/qa-pun1.htm http://www.cogs.susx.ac.uk/doc/punctuation/node30. html (this is from a British the website of a British university, and contains a useful example at the end of the page with a well known Shakespeare quote). Detailed discussions on this point are not hard to discover. Also, I should point out that a lot of people enjoy grammar, and accordingly are not acting in a "Nazi" role when the point out minor errors to others. Personally, I did not think the original post in discussion was particularly offensive, but found your subsequent attack uneedlessly vitriolic to the extent that I registered on slashdot and posted my response. "Other then game studios tied to official developer licenses, we'd like to see various individuals participate in content creation for the PS3." That should be "other than". The attitude that everyone on the net should use American English as opposed British English (where both are equally understandable to the speakers/readers of either) is pretty arrogant in my opinion.

http://www.cogs.susx.ac.uk/users/adrianth/ices96/p aper.html

A 10kHz / 1kHz frequency discriminator circuit evolved using a genetic algorithm.

So why the random punctuation around "elected?" Most people put punctuation into a sentence for a reason, so it seemed reasonable to infer that you did as well. Since there was no indication of a direct quotation, the only punctuation construction your use of quotes resembled was scare quotes which are typically an indicator that you're distancing yourself from the idea contained in them. So was that why you used them, or was it just a malfunctioning keyboard? Perhaps your deity is angered by the use of the word "elected" when not in quotes? Since we can't make any inferences based on what appears to be standard punctuation, I think we're all at a loss to divine your meaning.

I wonder how many of the Captain Obviouses responding here have heard of scare quotes.

"Question (From an N.C. State staff member): Where in heaven's name did the habit of putting a punctuation mark within a quote become policy? When quoting something that does not especially end with a period it seems unnatural to put a period wit hin the quotation marks just because it ends a sentence. (". . . to take the food away from the cat is not always. . . ." To my way of thinking this is wrong and should be ". . . to take the food away from the cat is not always . . .". But, perhaps, I jus t don't see the logic.

Answer: You're right. American English is consistent in this punctuation policy. You can look for relief in British publications, which follow the rule you find more logical.

You are not alone in objecting to the American convention. A whole group of kindred spirits is lurking on one of the links from the N.C. State Online Writing Lab homepage. The "Frequently Asked Questions" link (on the bulleted list at the bottom of the page or directly at http://www.rt66.com/ telp/styfaq1.htm#q1) puts this question to a vote of copyeditors. The American system wins out, but the British system has surprising support. The analysis covers the reasons for the opinions."

"Finally, there remains the problem of whether to put other punctuation marks inside or outside the quotation marks. There are two schools of thought on this, which I shall call the logical view and the conventional view.

The logical view holds that the only punctuation marks which should be placed inside the quotation marks are those that form part of the quotation, while all others should be placed outside. The conventional view, in contrast, insists on placing most other punctuation marks inside a closing quote, regardless of whether they form part of the quotation. Here are two sentences punctuated according to the logical view:

        "The only thing we have to fear", said Franklin Roosevelt, "is fear itself."
        The Prime Minister condemned what he called "simple-minded solutions".

And here they are punctuated according to the conventional view:

        "The only thing we have to fear," said Franklin Roosevelt, "is fear itself."
        The Prime Minister condemned what he called "simple-minded solutions."

Note the placing of the comma after fear in the first example and of the final full stop in the second. These are not part of their quotations, and so the logical view places them outside the quote marks, while the conventional view places them inside, on the theory that a closing quote should always follow another punctuation mark."

PSP MIPS R4000 : http://www.comms.scitech.susx.ac.uk/fft/programmin g/R4400_Uman_book_Ed2.pdf

IPOD ARM7TDMI : http://www.gbadev.org/download.php?section=docs&fi lename=ARM7TDMI_Data_Sheet_'ARM_DDI_0029E'.zip

the cpu's these devices use are not all that special... it's the custom hardware that is around them that is undocumented... and it seems to me people have been quiet successful in figuring out many of the systems people actually care about.

I would say it's on the wrong track. It seems to have at least one foot on the ground at all times, and thus displays a "stable" and not a "dynamic" gait. Also, notice how it seems to walk with its knees bent all the time. For an in-depth look at more natural-like (and potentially more useful) approaches to walking, see http://www.cogs.susx.ac.uk/users/inmanh/HART2004_H arvey_etal.pdf For some amazing movies of evolved dynamic walking, see http://www.droidlogic.com/

In other words: the interfaces of a computer are (often) intended to provide immersive experiences for their users. Computer users are humans, so you would expect the processing power dedicated to each component of I/O to reflect the discernment of humans in their corresponding sense.

In yet more words: if a dog designed a computer, it would have a crappy GPU but a beast of a smell-processing system.

That *some guy* is Ken Thompson. Here, here, and here is some more info about the infamous "compiler backdoor."

I've noticed the incorrect use of hyphens a lot on Slashdot, so I thought I'd submit a hyphenation troll when I saw a misuse to try and improve things. :)

In the story text it says, "dedicated exclusively to non-classified scientific research."

1) Latin prefixes (such as "non", "un", "anti", "pre", "nano", etc.) almost never require hyphens. Thus it should be written as "nonclassified" (although I believe "unclassified" is more common).

Hyphenation Troll.

He used a Xilinx FPGA and a genetic algorithm (implemented separately) to evolve a circuit which could distinguish (IIRC) two different frequency tones on the input as a logic level output. The "program" was allowed to interconnect the FPGA configurable logic blocks in any old sort of way internally and between CLBs. This would include ways which would cause logic designers to shudder in horror :), and did not include a clock input to the circuit at all.

The result was a successful circuit that used a relatively small portion of the FPGA. But trying to work out how it was accomplished the tone discrimination was impossible. There were sub-circuits that were isolated from the rest of the circuit but when removed would cause the circuit to fail. Thompson hypothesized that the circuits were taking advantage of "out of band" communication via electromagnetic or thermal influences on adjacent CLBs.

Furthermore, the circuits turned out to be very specific to the ambient temperature during training and usage, as well as being specific to a particular FPGA used (a working circuit on one would fail on another.)

In any case it was a fascinating small-scale exploration of what reconfigurable hardware and genetic algorithms could accomplish, when not constrained by the "clock driven sequential logic" paradigm nearly all human engineered circuits use.

You sound hungry, so I'll step up.

You might feel safe in thinking that Java's sandbox protects from this kind of thing, but don't be too sure...what is a JVM written in? Those very unsafe languages you talk about.

The fact is, at some point, *somebody's* gotta manipulate the memory directly; somebody's gotta keep track of what's been alloc'ed and what's been free'd, and whether that's at an application level, or at the OS level, you're going to find the very languages that you deem as unsafe.

Abstract away and bytecode your way to a false sense of security, and you've done nothing but put up another curtain to lull you into a false sense of security. The fact is, this kind of thing is *always* going to be with us, whether intentional or by accident (Microsoft's whole KB).

Think of it this way: cars are too dangerous for people to use because there's no way to stop them from running into the ditch. So we're going to develop a system by which everyone's car runs on rails, with all the latest safety systems to make sure everything is safe and secure and drive the way we think they should drive. Now you don't have to trust your own abilities, just us. And we know what's right, right?

I am actually about to publish a paper with the aliases and team names of the 20 top contributors of the Distributed Hardware Evolution Project. The names of the circuits in the figures were also chosen by contributors. If anyone is interested in having their own island in an island based coevolutionary genetic algorithm evolving the next generation of safe hardware circuits across the internet, join DHEP! You will be contributing cutting edge research.

I am actually about to publish a paper with the aliases and team names of the 20 top contributors of the Distributed Hardware Evolution Project. The names of the circuits in the figures were also chosen by contributors. If anyone is interested in having their own island in an island based coevolutionary genetic algorithm evolving the next generation of safe hardware circuits across the internet, join DHEP! You will be contributing cutting edge research.

I am actually about to publish a paper with the aliases and team names of the 20 top contributors of the Distributed Hardware Evolution Project. The names of the circuits in the figures were also chosen by contributors. If anyone is interested in having their own island in an island based coevolutionary genetic algorithm evolving the next generation of safe hardware circuits across the internet, join DHEP! You will be contributing cutting edge research.

As founder of the Distributed Hardware Evolution Project which is written in Java, I'd like to remind you all that the Just-In-Time compiler coupled with the real time profiling and dynamic on-the-fly optimisation that goes on in the Server VM makes the difference between C and Java minimal for code which is in the critical region. This is specially the case for code which is executed over and over again, such as with these distributed processing projects. In fact the guys at Sun are doing such a good job at exploiting the ever more complex characteristics of different processors that Java code is expected to run faster than C in the future. Also, during the weeks that you would spend debugging and porting your C code, your Java code has gone miles ahead doing useful stuff! If you would like to start your own Java distributed processing project, DistrIT might help.

When I look at life, I don't see the constraints of finitely intelligent design, which arise from a designer's need to understand his creation before he can improve it. I conclude that life must have been created either by an infinitely intelligent designer (I suspect this is your position), or by a process such as evolution that can create without understanding.

I prefer the evolutionary explanation, because I see more evidence for it, because I think it explains things better, and because an understanding of it can further the reach of human abilities. Evolutionary hardware and software design experiments like Tierra and Golem convince me that the process of evolution is powerful enough to have created life. Evolution can explain, given the physics of the universe, why various species have the properties they do, for example, why humans have morals. Finally, understanding biological evolution leads to advances in medical science and technology, and the process of evolution can be applied to other fields as well.

The process of evolution depends on the attributes of the system in which it acts, and this is where I believe God might fit in. The laws of chemistry, physics, thermodynamics, and causality allow life to exist and prosper. This could be because if they didn't, we wouldn't be here to reflect upon them. Or it could be because a Creator tuned the laws of this universe in much the same way Adrian Thompson tweaks the fitness function to evolve a better circuit. I don't think its possible for inhabitants of this universe to know which it is, but the latter would be much cooler.

All of these predictions are testable. If we find life that isn't related to that life we know about, we'd need to change or abandon the theory. If there are large gaps we can't explain, we would need updated theories, like punctuated equilibrium, to explain how A can evolve into B. Evolution would be hard-pressed to explain life without self-preservation instincts or without proteins. But there haven't been, to our knowledge, any contradictions like this.

All of these predictions are based on historical evidence, which is expected because most evolution happens very slowly. But there really isn't anything wrong with "reactionary" theories - they're better than cop-out answers, which I consider creationism to be. But evolution predicts other things which can be verified in the lab - the natural selection of moths, development of antibiotic resistant strains of bacteria, and even speciation in fruit flies and the like.

Most interesting to me, evolution as a process can be applied in more ways than simply to explain life on earth. You can use it to describe market economics. You can even use it to design circuits, programs, and robotics.

I mean, not any geek could hack on a purple box.

Back in the day, I knew a lot of geeks that dreamed of being able to hack on a Silicon Graphics Indigo2 Impact or an Onyx2...

http://futuretech.mirror.vuurwerk.net/apps/i2impac t00.jpg
http://www.hpc.susx.ac.uk/images/onyx2.jpg

(Besides, how many "grape" iMacs were ever sold? It wasn't a popular flavor and the whole 5-flavors thing only lasted about a year or two).

Hmm. Interesting, since I found very few references to non-American parentheses. In fact, here's a link that kind of states otherwise (granted, it's only one link, and it's in the UK).

They're called parentheses, or round brackets. I think you'll find that it's possible "{" and "}" can be used in place of "(" and ")", but they don't appear to be referred to as the same thing.

I could be wrong, but that's what my limited research tells me.

Those points aside, I have been amazed by the research in nanotechnology and find the realm of mapping the human genome to be interesting as well. Perhaps subjects such as these would interest Amos? Perhaps these are not as obscure as other fields but these are certainly interesting studies.

How would you ever be certain code injected into your system willfully is "harmless"?

I refer you to some people who know a lot more about English than either of us. Punctuation is part of the language. Like other areas of the language it is open to artistic and stylistic variation, but it can also be just plain wrong. I don't pretend to be a language expert (although both my parents are) - but that headline is wrong, I could tell it was, and the lined document agrees with me.

That makes it, rhetorical.

That sentence is wrongly punctuated. Or maybe you can tell me which of the 4 uses of the comma it fits into? It is not seperating items of a list, it is not part of a pair of commas distinguishing items in a list, it is not joining two complete sentences and it is not indicating an absent repeated section of the sentence.

Now if only gcc was OSS, then we could vet that as well......

Oh, wait :)

BTW the compiler backdoor you mention was described by Ken Thompson. Read about it here here among other places.

• Think of a unsuspicious piece of code being the triggger
• Have a compiler/linker insert binary code directly into the bewly generated executable
• Make sure you make the compiler regenerate the inserting routine when compiling itself using the same technique

This has already been explored in a number of research projects, notably in the papers here. The guy's thesis probably explores this in greater depth but hasn't been published yet.

Be careful what you wish for. Thanks to fun things such as String Theory, Time Dilation, and Quantum Time Travel you just might get that warp drive... yesterday!

I get anoyed by people talking about the probability of intelligent life on other planets. Frank Drake's 1961 equation, is the most famous example.

We have a sample group of 1 so far. You can't predict anything from a sample of 1. Its basic math.

How about -- http://www.biols.susx.ac.uk/home/John_Gribbin/time trav.htm

John Gribbin is by far one of the best authors on "layman physics" I've ever read. Q is for Quantum is an encyclopedia of physics terms (mostly those related to quantum physics and relativity) and is a must-have as a reference. Especially while reading his other books.

The Xilinx XC6200 is the first such device ideally suited to evolutionary work

1998/05 SAN JOSE, Calif. Xilinx Inc. has stopped development work on its XC6200
line of partially reconfigurable field-programmable gate arrays (FPGAs), and
the founders of the the company's reconfigurable R&D group in Edinburgh,
Scotland, John Gray and Tom Kean, have both left the company. The remaining
engineering staff at Edinburgh has been reassigned to develop IP cores for
use by Xilinx's customers within the company's FPGAs.

"In many ways it [the XC6200] was a product ahead of its time," he said. "It
was a beautifully conceived device but not sufficiently well supported."

This thread is so old that it's probably only FortKnox who's going to read this reply, but even to just one person I would recommend Thinking in C++ . It's great for Java programmers who want to have a better knowledge about what's actually happening in an OO program.

I read T.I.C++ about 18 months before I wrote my first C++ program, but it really helped me understand features of any OO program. That's right, I learned a lot about Java from a C++ book.

I'm coding C++ now (and pretty C-ish code at that), and I miss reading T.I.J. I still flick through it every now and then for inspiration. :)

It's a little different from standard virus infection, but the techique could be easily modified. Here's a short description of the technique, and here's the full text of the speech (with slides).

Perhaps this is a dumb, ignorant question, but what is the difference between Wolfram's Cellular Automata and the relatively old conceptual tool used in artificial life (and maybe used for other things?).

Is Wolfram's idea a generalized theory of the tool used for ALife? A new application for that tool? Something completely different?

There's a lot of theories about alternatives to the big bang besides the one mentioned in the Yahoo article. The main one that is getting a lot of interest in scientific circles isn't this new one in the Yahoo article. Instead, it's the so called Ekpyrotic theory, with the name coming for the Greek word for fire. It is so intresting because it brings together two disparate areas of physics: inflation and M branes. Inflation is a weird concept that says the universe expanded from the diameter or an atom to the size of a grapefruit almost instantly - required to explain the way galaxies are clumped and clustered in the sky we see today and first postulated by a guy named Alan Guth. M branes are an offshoot of string theory postulated by Ed Whitten. There's tons of stuff on these topics on the web; all of it is facinating, enter any of these terms in a search engine and keep reading. Next stop, Google...

This was my final year project thesis. Just remember the golden rule unstructured 2 structured == convert 2 XML I wrote a [very bad] program in C++/Perl/tcsh IPC=pipes to add XML tags to English, and then index them into a search engine which would use the lingual data stored in the XML tags to help the search.

NIST does a MASSIVE competition on this annually. I don't want to be an XML-buzzword whore <Arnold Schwarzenegger accent> (XML commando eats Green berets, C++, Java, Perl, COBOL for breakfast)</Arnold Schwarzenegger accent> but you can't beat XML for easily converting anything that you can make sense out of into computer readable format. Real h3cKoRs use SGML, but us underlings have to stick with things we can understand like XML. As for expandability, if we want to encode something else into the document, then just tag-it-and-go

It took me 200 hours to fish out all these links (before the Google days), I don't want anyone to have to waste as much time as I did feeding the search engines exotic foods. It's a year old so pardon me for the odd broken link, armed with these you could probably turn jello into XML ;-)

My favourite bookmarx
PROJect[21 links]
Beginners' Guide[13 links]
Berkeley Linguistics Dept. Course Summaries, general stuffzzzzzzzzzzzzzzCryptic IR Vocabulary defined
Explanations of weird words like hypernym zzzzzzzzzzzzzzHow do we produce and understand speech
How Inverted Files are Created - Univeristy of Berkeley zzzzzzzzzzzzzzNLP Univ. of Indiana, very good basics e.g. word sense d
Simple langauge - useful.... zzzzzzzzzzzzzzWhat is Natural Language Processing, links
What is POS tagging........ zzzzzzzzzzzzzzWord Sense Disambiguation defined
Word Sense Disambiguation in detail, scroll down far zzzzzzzzzzzzzzWord Sense Disambiguator - LOLITA (tested at MUC-7 and SENSEVAL competition as best)
XML for the absolute beginner

HTML, XML stuff + parsers[19 links]
Apache plug-in that uhhh does stuff with XML zzzzzzzzzzzzzzConvert COM to XML
convert XML, HTML to Unix pipeable formats zzzzzzzzzzzzzzconverters to and from HTML
expat XML parser zzzzzzzzzzzzzzHTML Tidy - converts HTML 2 XML + source code!!
Parse DB (RDBMS, whatever) to XML zzzzzzzzzzzzzzPerl-XML Module List
PHP Manual XML parser functions - what the hell are they talking about, PHP Virtual M... zzzzzzzzzzzzzzPublic SGML-XML Software
Pyxie - XML Processor for Python, Perl, etc. zzzzzzzzzzzzzzSGML+XML tools.org
The XML Resource Centre - massive number of links zzzzzzzzzzzzzzW4F wrapper - wrapper converts XML to HTML
XFlat - convert flat file into XML zzzzzzzzzzzzzzXML Parsers and other XML stuff
XML.com - Parsers, etc. zzzzzzzzzzzzzzXML-Data Catalog System - uhhhh looks close
XTAL's general converter - convert anything 2 XML

other Background[8 links]
Is Linux ready for the Enterprise, scalable... zzzzzzzzzzzzzzLinux reliability
Linux Versus Windows NT, Mark(sysinternals bloke) zzzzzzzzzzzzzzPC reliability (pcworld)
SPEC - Standard Performance Evaluation Corp. zzzzzzzzzzzzzzSystems benchmarks
TPC - Transaction Processing Performance Council zzzzzzzzzzzzzzUnix Beats Back NT In EDA Workstation Arena
Proper TREC(-8) QA systems[2 links]

pg. 387 LIMSI-CNRS pretty deep parsing[2 links]
More links....
NLP, IR links - lots to corpii, etc.

pg. 575 U. of Ottawa and NRL (shit system, got 0%)[1 links]
LAKE Lab
pg. 607! University of Sheffield (crap system, but OPEN SOURCE!)[2 links]
GATE - FREE IE app w`source code
LaSIE - ER, coreference, template (cv)

pg. 617 Univ of Surrey (inconclusive matches)[2 links]
System Quirk - Or is this their search system..... Hmmmmmm
Univ of Surrey - pointers (hopefully this is their WILDER search system...)

SMU - Pg. 65[1 links]
Natural Language Processing Laboratory at SMU

Textract[2 links]
Cymfony - Technology
Textract - State of the Art Information Extraction

Xerox uhhhhh maybe[1 links]
Xerox Palo Alto Research Center
(OVERVIEW) 1999 TREC-8 Q&A Track Home Page
NLP bloke, Univ Sussex


Tcl-Tk[4 links] Tcl tutorial
Tcl-Tk Contributed Programs Index
Tcl-Tk Resources, sources
TclXML - manipulating XML using Tcl-Tk
Artificial Natural Language - Is this what I'm trying to parse into...
Comparison of Indexers - Prise vs. Inquery vs. MG, etc.
Eagles - Language Engineering Standards
Language Technology Group - lots of modules!
LDC - Linguistic Data Consortium, lots of corpora
Lexical Resources
Links 2 resources, indexers.....
Lots of IR stuff, University of uhhh
Managing Gigabytes Indexer
Managing Gigabytes Manuals and stuff
Htdig search system
NLP & IR (NLPIR, NIST) Group
OVERVIEW OF MUC-7-MET-2
Perl XML Indexing - XML search engine type thing
Phrasys Language Processing Software Components (money)
QA HCI bullshit
SIGIR - TREC-type thing, resources
SMART indexer system documentation
Text REtrieval Conference (TREC) Home Page
The Natural Language Software Registry
Thunderstone IE and IR products
WordNet - FREE DOWNLOADABLE lexical English database

Page created with URL+, nice utility for working with internet shortcuts

Oh right if it's in a book it has to be true! There are tonnes of clear example of augmented reality HMD's before any of Mann's publications.

Please tell me how this is worse than staring at some low resolution TV screen hooked to a motherboard under your sweater while carrying around a car battery?

And here's a link about Hough transforms ...

Simulation could take into account all of the drawbacks, by making those portions of the simulation noisy, thereby not allowing evolution to depend on those parameters. This idea is call "Minimal Simulations", and I'm sure I've not done the subject any justice whatsoever!!!

A guy called Nick Jakobi was just finishing his thesis when I was studying at Sussex, link to thesis.

It was an evolutionary robotics thesis.

Check out the CCNR - Autonomous Robots research page (A graduate research group at Sussex):
CCNR

Emergent Behaviour always seemed credible to me (I did my undergraduate degree @ Sussex Uni;), Insect like navigation has been evolved using relatively simple artificial neural networks (you can easily make a simple robot that avoids objects - which could be seen as hate - as Braitenberg said, IIRC).

See the following link for your answer: Evolution of Robustness in an Electronics Design

You found the paper, but you didn't look at any of the followup research.

Like this paper which details an experiment using an external clock and a wide variation in temperatures to evolve the same sort of circuit that Adrian evolved in his thesis paper.

And a complete list of his publications can be found here.

If you've bothered to read any of his work, you'd quickly realize that Adrian is interested in how evolution can use certain properties of the physical substrate in these chips to it's advantage. It's not looking to see if evolutionary type strategies can evolve something a human could build, but looking at how they can build things no human could imagine building.

DISCLAIMER: I am currently a Master's student at the University of Sussex, and had Adrian as a lecturer this past semester. However, I am in no way involved in his research, my interests lie in the software side of genetic algorithms.