Omid Madani (Under Construction.. Indefinitely!)
 |
omidmadani att yahoo dot com |
I am interested in all aspects of intelligence, especially from a computational perspective. My research has included the following threads:
- Mostly machine learning, now, for more than a decade! Key problem properties have involved and continue to revolve around large-scale learning, online learning, data mining, active learning, imperfect/noisy features/feedback, multiple (learning) systems interacting, etc.
- I am inspired by how our minds might work! In particular, the type of problems that we solve. An important feature of our intelligence that separates us humans from many other animals is the huge number of inter-related concepts that we (apparently) acquire and develop and effectively use. Here, by "concept" I mean a recurring (and useful) pattern, such as words and phrases uttered in continuous speech, or visual objects and entities such as books, faces, common action sequences, etc. What tasks and problems, processes and algorithms, and representations and data structures, support such complexity? These questions are very broad and provide a starting point. I hope to contribute to answering some such questions, in particular from the perspective of computational learning and development.
- I have been working on efficient learning algorithms for supervised learning problems with high input and output dimensionalities (potentially huge numbers of features and classes/concepts). The initial focus has been on online algorithms that can handle dynamic sets of classes, possible nonstationarities, etc.
- Another very challenging class of problems involves acquiring and working with many concepts autonomously (without explicit teaching) (keywords: unsupervised concept or feature induction, cumulative persistent learning, noisy feedback, autonomous "mental" development, computational development).
- Other related threads in my work include empirical and theoretial analyses of algorithms (in particular, inspired by AI problems, such as Markov Decision Processes (MDPs)), exploration of applications, and discovery of new problems in the applications. Past and future application areas include information retrieval, text and natural language processing, game playing, personalization, vision, and so on.
- Publications by year
- Current research: large scale learning systems
- Information
for prospective interns
- Bio
A
poem by Omar
Khayyam.
