Yuqi Zhang


I am a visiting research student coming from China. I am new comer here and is getting familiar with the teammates now.

My research area was mainly focused on data mining in my home university, and I used to be a web tool tester(.Net/C#) intern in Intel, but I love to try new things.

BID really interests me, and is also a new challenge to me.I hope to learn as much as I can during the stay here and become good friends with everyoneO(∩_∩)O

I love vegetable and fruit, but having few fight of  meat+_+

If you are interested in China or Chinese Language or anything about China, please feel free to talk to me(*^__^*)



Mikhail Jacob

Mikhail Jacob

I’m a second year Master’s student in Computer Science, specialising in Interactive Intelligence. I have worked on the GAIA project since my first semester, working on adapting agents for Tic Tac Toe and its variants. I believe that games are the perfect test bed for all kinds of serious research and this is one such project involving self-adaptation and meta-thinking in game playing agents.

In general, I am interested in how creative AI systems can foster an understanding of creativity and its role in cognition and the human experience. I am also deeply interested in the interplay between affect and creativity and a firm believer in AI’s original dream of Artificial General Intelligence.

Daniel Connelly

Daniel completed his master’s degree in computer science in the Design & Intelligence Laboratory.

He completed his bachelor’s degree in Applied Mathematics at Georgia Tech, worked full-time at MIT’s Lincoln Laboratory on defense research projects, and twice taught an advanced high school mathematics course at a charter school in Atlanta.  He also works with Georgia Tech’s Center for Education Integrating Science, Mathematics, and Computing on course design and evaluation.

His academic interests include software engineering, programming languages and compilers, and artificial intelligence.  He conducted his master’s project work on software development process and language implementation for the GAIA meta-reasoning project.

Daniel’s personal web site and blog can be found at dhconnelly.com.  He now works at Google as a full-time software engineer.


Marshall Gillson

I’m working to complete my Master’s degree in the Design & Intelligence Lab with research into game playing adaptations. I’ve been designing software agents to play a number of different games and examining the differences between those agents. In this way, I aim to determine what kinds of strategy adaptations are compelled by different kinds of rule changes. These exercises should  lead to the development of generalized guidelines for and theories of adaptation in games, which in their turn serve as a microcosm for more broad notions of strategy and plan modification.

More generally, I am interested in Artificial Intelligence as a method for investigating cognition and consciousness as abstract phenomena. Right now, human intelligence is our only exemplar for them; cognitive systems hold the promise of creating more data points and empirically testing hypotheses. Which hypotheses we should test and how those systems should be designed, however, are big questions. In pursuit of answers, I’ve been overdosing on Cognitive Science classes.

From Design Cases to Generic Mechanisms

Analogical reasoning plays an important role in design. In particular, cross-domain analogies appear to be important in innovative and creative design. However, making cross-domain analogiesis hard and often requires abstractions common to the source and target domains. Recent work in case-based design suggests that generic mechanisms are one type of abstractions useful in adapting past designs. However, one important yet unexplored issue is where these generic mechanisms come from. We hypothesize that they are acquired incrementally from design experiences in familiar domains by generalization over patterns of regularity. Three important issues in generalization from experiences are what to generalize from an experience, how far to generalize, and what methods to use. In this paper, we describe how structure-behaviorfunction models of designs in a familiar domain provide the content, and togetherwith the problem-solving context in which learning occurs, also provide the constraints for learning generic mechanismsfrom design experiences. In particular, we describe the model-based learning method with a scenario of learning of feedback mechanism.