Overview

Several postdoctoral positions are available in the theory of deep learning, adversarial learning, subspace clustering, non-convex optimization for machine learning, learning and control, semantic scene interpretation, vision and language, and activity recognition. Specifically:

– AI and Machine Learning: theory of deep learning (optimization landscape, learning dynamics, neural architecture search, overparametrization): http://www.vision.jhu.edu/deeplearningtheory.htm
– AI and Machine Learning: non-convex optimization and subspace clustering: http://www.vision.jhu.edu/dpcp.htm
– Computer vision: semantic scene understanding, scene graphs, deep generative models for vision: http://www.vision.jhu.edu/infopursuit/
– Computer vision: vision and language, action recognition in video, adversarial defenses for video, few shot learning

These opportunities will involve multidisciplinary collaborations as part of
– NSF-Simons Math of Deep Learning: https://www.minds.jhu.edu/theorinet/
– NSF-TRIPODS Foundations of Graph and Deep Learning: https://www.minds.jhu.edu/tripods/
– DARPA Guaranteeing AI Robustness against Deception (GARD)
– DARPA Reverse Engineering Deception Based Attacks (RED)
– ARO MURI Semantic Information http://www.vision.jhu.edu/infopursuit/
– ONR MURI Control and Learning Enabled Verifiable Robust AI (CLEVR-AI)
– IARPA Deep Video Analytics (DIVA): https://www.iarpa.gov/index.php/research-programs/diva

Before applying for this opportunity you need to submit your online profile. Click the button below to continue.