New Paper: Stigmergic Dimensions of Online Creative Interaction

I published a recent paper in the Cognitive Systems Research Journal (ok, not totally recent, it’s been a few months and I am finally getting around to posting it) about stigmergic interaction in online creative communities.  The paper borrows evidence heavily from my work on Picbreeder, an online system for the interactive evolution of images.  From the abstract:

While current cognitive research in creativity places significant emphasis of the personal traits and cognitive structures that give rise to creative thought, Picbreeder highlights the potential for the emergence of creativity through stigmergic interaction. Picbreeder offers a rich data set for analysis of collaborative interaction with over 155,000 inputs from hundreds of users combined to create over 7,500 images. It is hoped that the insights offered in this paper will influence both the understanding of collaborative creativity and the development of new modes of online creative interaction.

Posted in Uncategorized | Leave a comment

A camera controlled raspberry pi projector game system

Ok, so like many nerds, I had to have a Raspberry Pi in my life.  It is a great piece of technology begging for an application.  It has some worthwhile graphics hardware, as well as some reasonable processing power.  It wasn’t long before I figured out what I wanted to do.  Make a project based game system with an awesome computer vision component!

First, I started with an AAXA pico projector, which can run for about an hour off of its battery, and has a decent display resolution.  It also has an HDMI port, which the Pi can use.  Next, I found an external cell phone battery charger that connected to micro USB to power the Pi itself.  Finally, I took an old webcam that I had lying around, and voila, I had the hardware for a portable, projector based gaming system.  Now I just needed some software to run on it.

Thankfully, I had a couple of options.  First of all, I did manage to get OpenCV packages to install on Raspbian.  As you can imagine, many of the OpenCV demos did not run blazingly fast on the Pi, but I could see the potential.  Because all I really wanted was a proof of concept, I discovered that I could get PyGame’s built in camera module working quickly.  So, I put together some frankencode from this guy’s PyGame camera tutorial and a Python pong demo.  Of course, I cheated by making the camera just follow the white in my socks, but you get the idea.  If I had more time to put into a complicated OpenCV algorithm, I could make it track arbitrary feet.  This seems to work at a few frames a second, which, if we were to add some interpolation, could be fast enough to interact with some basic games.  Here is the result:

Please forgive the bad video capture. But you can imagine the possibilities. All of the parts were portable and light weight. We could potentially package all of these parts together into a single sleek case (I’m thinking a small, white pyramid, but I guess I’ll leave that to the designers). Kids could bring this around the house and interact with it on floors and walls.

Posted in Uncategorized | Leave a comment

Technical report on using interaction design to battle narcissism

I’ve posted a new paper titled “Ripples in the Reflection Pond: Interaction as a Tool to Neutralize Narcissism.”  I could never really find the right venue to publish this, but I thought somebody might find it interesting.  From the abstract:

In The Narcissism Epidemic, authors Twenge and Campbell describe an alarming trend of narcissism developing in the United States and abroad.  Technology plays a major role in the expression of this social development: users are co-opting social networking and other applications to further self-admiration and self-absorption.  The MySpace and Facebook pages that are popular among both teenagers and adults have, in some cases, become personal shrines.  These pages can contain thousands of photos and videos capturing the page’s owner from every conceivable angle.  At the same time, a user can post countless tweets every day, dramatically describing every minute detail of his or her day.  While these technologies likely did not cause the narcissism epidemic, they serve as ideal vectors for its spread.  Narcissism is a serious problem, and is on the rise, impacting everything from the ability to have healthy relationships to the United States’ educational competitiveness as a nation.   However, society can potentially leverage these same technologies to combat narcissism and promote a healthy sense of self.  In this paper, I discuss emerging trends of narcissism as well as technology’s role in promoting it.   I also explore ways that information technology in general and interaction technologies specifically can help stem the tide of narcissism, with the ultimate hope of encouraging a surge of research and development within this vital area.

Posted in Uncategorized | Leave a comment

When can I have my $99 3-d printer?

First, I want to take a moment to congratulate my new friend Jeff Clune, for having his site, featured on the front page of slashdot. Hopefully this is the beginning of a vibrant creative community, even larger than the one that had created. Their site integrates with shapeways, which allows users to have their creations, or anybody else’s creations for that matter, printed in 3-d and sent to them.  This amazing capability has gotten me to think more about 3-d printing in general, and what kind of transforming economic effect it might have.  Right now, 3-d printing technologies have come a long way, with open source 3-d printers like Fab@Home, Makerbot, and others.  While many are now available for under $1000, and some for around the $500 mark, this still is not quite there for the wider consumer market.  Getting things made by a company like Shapeways makes designing and ordering small pieces practical and relatively cost effective, but I believe the real potential is in the commodity, $99 3-d printer.  Suppose for a minute that some large manufacturer could swoop in, and create a slick and shiny 3-d printer inexpensively enough to make a profit on it at $99.  Or, even if the printer itself is sold at a loss, they can make up their money by selling the resin that is the analog of expensive ink cartridges in today’s printers.  This could be a very hot Christmas gift.  Interestingly enough a prize for building a better 3-d printer, with part costs under $200 comes close to this, but I think casts the net too wide (requiring for instance, the ability to print circuit board and reproduce its own parts).

However, I believe the real magic starts when this is coupled with something like picbreeder or endlessforms.  Inevitably, when endlessforms was posted to slashdot, one of the commenters asked a question to the effect “Why do we need this, when there are seemingly endless amounts of free, and much better, 3-d models available on the Internet?”  This is a point that is easy to miss.  While the first generation of interaction evolution sites are simple, the hope is that after some improvement they will continue to make better, more interesting models and images in less time.  And the reason why these types of sites are important is that they help to democratize design.  Most of those 3-d models out there on the Internet, and I would bet many on sites like Shapeways, are made by professional or semi-professional 3-d designers.  Despite the availability of software like Google Sketchup, 3-d design still has a high barrier to entry.  Making any sufficiently advanced 3-d design is difficult.  However, with the assistive power of evolutionary algorithms, good taste is good enough.  That is, designers don’t have to know how to design in 3-d, they just have to know what they like.  And when this is coupled with a marketplace like Shapeways, the implications are far reaching.  Imagine a future where a mom comes home before the kids get home from school.  In about a half an hour, she has evolved a new hair clasp design.  She prints it out and shows it to her daughter, who loves it.  She then posts the idea on a site like shapeways, where it becomes an instant success, yielding royalties on tens of thousands of purchases.  This kind of possibility alone is worth my $99.

Posted in Uncategorized | Tagged , , , | Leave a comment

Semi-Automated Creativity Workshop

I am putting on a workshop at the Creativity and Cognition 2011 conference called Semi-Automated Creativity.  The workshop will focus on software can leverage techniques like machine learning, data mining and AI to elevate software to the level of a creative collaborator.  Please send your submissions to if you are interested!

Posted in Uncategorized | Leave a comment

Technical report on privacy-preserving probabilistic neural network

I’ve just uploaded a technical report that describes a set of algorithms implementing a distributed, privacy-preserving version of the probabilistic neural network.  From the abstract:

“The Probabilistic Neural Network (PNN) is a popular and powerful neural network for mining data. This paper discusses a family of PNN algorithms that are capable of mining distributed databases that are either horizontally or vertically partitioned. It does so in a way that is privacy-preserving: that is, a query can be made to the algorithm without revealing a party’s training data to any other party. These algorithms will allow the PNN to be evaluated on data sets that span multiple, geographically distributed organizations, while at the same time respecting the privacy of the records. The performance/security tradeo ffs of the diff erent privacy preserving PNN implementations are discussed, and detailed results are provided for the algorithms, evaluated over large (128K point) data sets.”

Download the full paper here:

Privacy Preserving Probabilistic Neural Networks for Vertically and Horizontally Partitioned Training Sets

Posted in Uncategorized | Tagged , | Leave a comment

Mesh networks and civil unrest in Egypt

The civil unrest in Egypt, and the subsequent shutting off of Internet access reinforces the need for ad hoc network technologies on mobile devices. The recent work I did in this area (see here) was conceived with natural disasters in mind, but it can be just as useful for manmade disasters and the intentional disabling of communications infrastructure. The sooner phones can communicate without centralized infrastructure, the safer we will all be. There is an interesting article about mobile phone mesh networks and the Egyptian situation here: How Phone-Powered Mesh Networks Could Help in Egypt.

Posted in Uncategorized | Tagged | Leave a comment

Re-thinking WikiLeaks

Yahoo News reported a few days back that the New York times has discussed creating a Wiki-Leaks style for potential whistle-blowers to submit documents to the site. I think that this gives us a good opportunity to rethink WikiLeaks-style reporting, to keep what we like and to get rid of what we don’t. The controversy over Wikileaks is not just about specific documents on the site, but over the larger question of how much sensitive information should be accessible to the public.

The debate is more complex than simply the tired-old “There should be no secrets” versus “We should trust our government to withhold information for our own protection” battle. For instance, leaked information pertaining to toxic dumping by an agent of Trafigura off of the Ivory Coast was something that we all should be glad has come to light. But in other cases, weighing value of the information versus its potential damage is more difficult. When the names of several Afghan informants were plainly available in documents leaked about the war in Afghanistan, there was cause for significant concern. Although WikiLeaks the Pentagon and activist groups alike to help redact potentially compromising information from the documents, no one was willing to cooperate. By Assange’s own admission, this kind of unfettered exposure could lead to blood on the hands of the group. There must be a way where we can have our cake and eat it too.

It may be no great surprise that I would suggest we “crowdsource” the task of filtering this information. However, this approach immediately presents problems. For one, if individuals are reading the documents to filter them, that means that compromised information may have been leaked in the very act of that filtering. Who is going to do this filtering, and for what reasons? To solve some of these problems, we can borrow some techniques from privacy and security. Let us start with some large document to be redacted. First, split it up into numerous paragraph-sized pieces. When a new user logs in (who is appropriately throttled in terms of number of requests, to prevent spidering) he is given a piece of the document. He reads it and marks both what should be redacted and what should be highlighted as worth further review. He submits this piece and receives the next one. This same piece of the document is given to several users to gain confidence in the accuracy of their assessment. Interspersed with the bits of the actual document are paragraphs from a corpus that has either been randomly generated or taken from existing declassified documentation. The more of these “straw men” there are, the more secure the system is. If the generated bits of document are convincing enough, then the a user won’t know if he is learning genuine, never before seen information, or bogus distraction. If, therefore, he learns something potentially compromising, it won’t be confirmed unless that portion of the document is released.

Of course, even the best crowdsourcing infrastructure is useless without a committed core of users. Why would people be interested in such a system, you may ask. For the same reasons that they are willing to change a wiki page back and fourth to promote their view. WikiLeaks has sparked passionate debate, and if that energy is harnessed in the online world, it could be just the balance of tensions necessary to ensure that important documents are leaked while preserving information that is truly sensitive.

Posted in Idea Incubator, Uncategorized | Tagged , , | Leave a comment

New Paper on Collaborative Filtering for Crisis Informatics

Just added a publication to the list about using collaborative filtering techniques for crisis informatics. It is for conference paper for the CogSIMA 2011 conference. You can download the paper here: “Collaborative Filtering of Spatial-Temporal Information for Crisis Informatics”

In this paper, I explore the possibility that, with the prevalence of smart phones, that they could form an ad-hoc network in times of crisis. The paper proposes an algorithm that aggregate observations gathered from these phones (e.g. like a downed powerline or temporary shelter). I hope that in the future, systems like this empower victims of disasters to share vital information.

Posted in Uncategorized | Tagged | Leave a comment

Creativity and Cognition 2011

I’ve been asked to be on the program committee for the Creativity and Cognition Conference 2011, and as such now I am asked to promote it.  Creativity and Cognition is an interdisciplinary conference that covers topics from neural models of creativity to computer interaction techniques to enhance creative development. Right now, this conference only comes along every other year, so it is a good opportunity to submit if you haven’t. I think that exploring and enhancing the role of creativity is becoming increasingly important in almost every area in our lives, and I’d love to see more researchers get into this area.

Posted in Uncategorized | Tagged | Leave a comment