Internship: Fault Diagnosis and Prognosis with DNN

Cambridge, Massachusetts, United States · DA · 1187 expand job description ↓


MERL is looking for a highly motivated intern to develop DNN-based methods for fault diagnosis and prognosis (i.e., prediction) problems, particularly for time series data. Successful candidate will collaborate with MERL researchers to design new algorithms, implement them, perform experiments, and prepare results for publication. The candidate should have a strong background in machine learning/statistics and deep learning. Knowledge and experience of any of the followings are desirable: generative adversarial networks, time series modeling and analysis, stochastic processes, and signal processing. The candidate should be comfortable implementing algorithms in Python. Prior experience with DNN packages such as Keras, TensorFlow, or Theano is a plus. The candidate is expected to be a PhD student in Computer Science, Statistics, Electrical Engineering, Applied Mathematics, or a related field. The duration of the internship is 12 weeks. The starting date is flexible and can be as early as April 2018.

Research Area: Data Analytics

Contact: Amir-massoud Farahmand

Do you have a LinkedIn account? Import your resume and save time!

Personal information
Your Profile
Application Details
Are you qualified to apply for an internship at MERL? Qualified applicants for MERL internships are individuals who have or can obtain full authorization to work in the U.S. and do not require export licenses to receive information about the projects they will be exposed to at MERL. The U.S. government prohibits the release of information without an export license to citizens of several countries, including, without limitation, Cuba, Iran, North Korea, Sudan and Syria (Country Group E:1 of Part 740, Supplement 1, of the U.S. Export Administration Regulations).
Have you worked at MERL before?