Postdoctoral Position; Machine Learning: Lifelong Streaming Anomaly Detection
This work will take place in the context of DARPA’s L2M program (www.darpa.mil/program/lifelong-learning-machines). The successful candidate will expand American University team’s Lifelong Learning model and integrate it with SRI International’s model on both a Reinforcement Learning Task and unsupervised and one-class anomaly detection problems (in the context of cybersecurity, medical imaging, social media security, and many other applications). This work will be carried on in collaboration with Computer Science professors Nathalie Japkowicz and Roberto Corizzo and Statistics professor Michael Baron. The work will combine neural network (deep learning) and other machine learning techniques with statistical change-point detection methods. The resulting system will automatically recognize anomalies from stream data in real time, identify them as part of a concept drift, novelty, or accident/attack, and adapt to them according to their identification.
The successful candidate will be affiliated with the Department of Computer Science at American University in Washington, DC. The candidate will be working with Professors Nathalie Japkowicz, Roberto Corizzo, and other students affiliated with the lab. The candidate will also be working with Professor Michael Baron in the Statistics department.
The appointment is a 12-month term position (renewable for 12 months pending successful completion of the work and funding) and will commence on January 4, 2021.
The principal duties to be carried out include:
- Integration of the current American University (AU) team’s Lifelong Learning approach with SRI International’s approach to the Starcraft application.
- Helping in the design and implementation of the new components of AU team’s approach.
- Adapting the approach to the various domains of application considered by the team.
- Thoroughly evaluating the performance of the system on these domains.
- Co-supervising Senior or Master’s students’ implementations (with testing and refinement) of sub-components or specific applications of the project.
- Preparing conference and journal manuscripts in collaboration with Drs. Japkowicz, Corizzo, and Baron and the students involved in the projects.
- Assisting in the preparation of additional grant proposals to continue the project or develop new ideas emanating from the project.
American University is a private institution within easy reach of the many centers of government, business, research, and the arts located within the nation’s capital. For more information about American University, visit www.american.edu.
The ideal candidate will hold a Ph.D. in Computer Science in the area of Machine Learning and Neural Networks. The candidate must have an interest and some experience in a variety of machine learning techniques such as reinforcement learning, unsupervised or one-class learning, outlier detection, time-series analysis, and data stream learning techniques. The candidate must have experience or interest in integrating statistical methods in the system and be interested in collaborating with a team of statisticians. The candidate will have a record of publications in well-recognized conference and/or journal venues.
Salary is competitive. Review of applications will begin immediately and will continue until October 22nd or until the position is filled, subject to ongoing budgetary approval. Include a letter of application, curriculum vita, three letters of recommendation, and copies of recent published papers or working papers. Please contact Nathalie Japkowicz, at firstname.lastname@example.org if you have any questions.
More searches like this
- Faculty Positions Not specified Full Time jobs in Washington D.C.
- Education Not specified Full Time jobs in Washington D.C.
- Instructional Technology & Design Not specified Full Time jobs in Washington D.C.
- Science, Technology & Mathematics Not specified Full Time jobs in Washington D.C.
- Computer Sciences & Technology Not specified Full Time jobs in Washington D.C.