Research I, Room 81 Campus Ring 28759 Bremen Germany
My current research is supported by the EU project NeuRam Cube, of which the purpose is to fabricate a chip implementing a neuromorphic architecture that supports state-of-the-art machine learning and spike-based learning mechanisms. Neuromorphic hardwares, like other unconventional computing substrates, are non-digital, unclocked, low-precision, exhibit static and dynamic parameter drift, and may have limited lifetime. Taking inspirations from human brains, my research focus is to develop theories and algorithms to harness such non-classical devices for computation, despite of their challenging properties.
X. He, H. Jaeger (2017): Overcoming Catastrophic Forgetting by Conceptors Jacobs University Technical Reports(35) ArXiv:1707.04853
F. Hadaeghi, X. He, H. Jaeger. (2017): Unconventional Information Processing Systems, Novel Hardware: A Tour d’Horizon Jacobs University Technical Reports(36) (Preprint pdf)
EP3136340 Non Metric Calibration of Unified Camera Projection Model