Undergraduate and Graduate Summer Research Experiences in Artificial Intelligence and Machine Learning at Bryn Mawr College Apply by *March 1, 2013* for full consideration. We will continue to accept applications after this date until all positions are filled. Spend ten weeks of your summer working on exciting projects in artificial intelligence and machine learning at Bryn Mawr College! We have openings for several undergraduate or graduate research assistants to work on two grant-sponsored research projects this summer. Student participants will join a research team with other students, Prof. Eric Eaton, and one postdoctoral researcher to carry out a detailed program of research toward scholarly publications. Students will present the results of their research during the final week of the program at Bryn Mawr College, and (if appropriate) at their home institutions and/or other academic venues, such as research conferences. All students who are beginning their junior or senior undergraduate year in Fall 2013 or who will graduate during the Spring 2013 semester, and all graduate students are eligible to apply. To be considered, you should have a background in either computer science, mathematics, physics, or statistics and have strong grades in your major. Although it is not required, it would be beneficial if you have taken and done well in at least one course related to artificial intelligence, machine learning, robotics, statistics, or topology. Brief descriptions of the two sponsored research projects are listed below: LIFELONG MACHINE LEARNING -- Most current machine learning methods learn a model for a single data set, and then forget that model completely when they are applied to another data set. In contrast, human learning retains information between learning tasks, developing skills over a lifetime of experience. This project will focus on developing methods for computers to learn continually from and transfer knowledge between multiple learning tasks, enabling the continual development of skills through lifelong machine learning. The development of lifelong machine learning has the potential to enable a new class of learning systems capable of learning a diverse set of skills over time and then adapting those skills as needed to changes in the environment. Within this project, we are also developing methods for users to instruct learning systems, enabling the users to teach and shape behaviors over time. We are applying these lifelong learning methods to a variety of domains, including robotic control and coordination in a multi-agent simulator, and facial expression recognition from images. SOCIAL NETWORK ANALYSIS -- Networks occur in many different applications, including social networks, corporate organizations, chemical interactions, and biological regulatory networks. Relational networks represent the connections between entities as a graph, providing an intuitive and structured representation of this knowledge. Often, these networks contain natural communities of entities, such as groups of friends or project teams, that is useful for analyzing the structure of the network. This project focuses on automatically identifying these natural community structures in heterogeneous networks that contain more than one type of entity (e.g., a graph of connections between individuals, corporations, and locations). We will then apply these natural community structures to learning and dimensionality reduction (i.e., compression) in the graph. This project builds on concepts from topology and statistical physics. On-campus housing and meals are available for student participants, along with a variety of professional development workshops and summer activities. Application instructions and further details are available online at http://cs.brynmawr.edu/~eeaton/openpositions.html Bryn Mawr College is an affirmative action/equal-opportunity employer. Minority candidates and women are especially encouraged to apply. Hiring is contingent upon eligibility to work in the United States. Bryn Mawr College is located in the suburbs of Philadelphia and is convenient to major air and train transportation hubs.