Intel Research, Santa Clara, CA
An internship position is available for a Ph.D. student in the areas of machine learning, human activity recognition, decision making under uncertainty and online learning with experts. At Intel research, a project titled "Everyday Sensing and Perception" (ESP), which is composed of 12 research scientists, is chartered at developing technology for recognizing everyday human activity context with high accuracy and most of the time. An integral part of the project is context guidance, which we have termed as "Interaction Planning". Interaction planning systems interact with humans over a period of time to help them achieve desired goals. Such systems could be a virtual teacher/coach, a task assistant, or an entertainer. Depending on the user's level of expertise/familiarity, attentiveness, willingness to reach her goals, preferred interaction style (e.g., hands-off vs. hands-on), cognitive capacities (e.g. child vs. adult vs. senile), perceived relationship (e.g. teacher vs. entertainer), level of urgency (e.g. tight schedule vs. relaxed), the system picks different content, frequency and tones for message delivery. A conventional approach to the problem is to model users explicitly at this level of detail. In practice, detailed modeling may not be feasible or tractable. The focus of the research is to develop techniques that achieve the quality of models that represent humans mental state in great detail while avoiding the modeling overhead and slowdown of such models. The desired qualities of an applicant are: * Experience in implementing real life machine learning systems. * Expert in decision making approaches under uncertainty, such as partially observable Markov decision process (POMDPs). * Knowledgeable in online learning with expert advice algorithms. * Expert with learning and inference in graphical models such as DBNs. * Classical machine learning expertise. Internships are expected to be at least 10-12 weeks long during the summer months. The successful candidate will participate in implementing a real life interaction planning system , perform experiments, develop new algorithms and theory for interaction planning, and finally submit a paper to one of the premier AI and machine learning conferences. To apply: * Request two short reference letters from your advisor or from someone you have interned with before. * Email your CV, the reference letters and the dates you will be able to join to: [EMAIL PROTECTED]
_______________________________________________ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
