Postdoc

Postdoc: Symmetries and their Breaking in Deep Learning - Faculty of Science Are you interested in understanding the dynamics of deep learning using general mathematical principles, such as symmetry and universality? Are you interested in using deep learning to tackle difficult scientific problems? AMLab is hiring a 2-year postdoc to work with Dr. Nabil Iqbal on a project supported by the Simons Foundation grant Symmetries and their breaking in deep learning. Postdoc: Symmetries and their Breaking in Deep Learning - Faculty of Science - 08-12-2026 Postdoc: Symmetries and their Breaking in Deep Learning - Faculty of Science - PhD - 38 hours - 15627 - €3,706 - €5,760 - Closes on 08-12-2026 Are you interested in understanding the dynamics of deep learning using general mathematical principles, such as symmetry and universality? Are you interested in using deep learning to tackle difficult scientific problems? AMLab is hiring a 2-year postdoc to work with Dr. Nabil Iqbal on a project supported by the Simons Foundation grant Symmetries and their breaking in deep learning. Postdoc: Symmetries and their Breaking in Deep Learning - Faculty of Science - 15627 - PhD - €3,706 - €5,760 - 38 hours - Closes on 08-12-2026 Join Us! Artificial neural networks models are made out of many individually simple constituents which assemble together into emergent entities with remarkable capabilities, including the ability to converse, reason, and accomplish difficult tasks. How can stacks of matrices and non-linearities accomplish such amazing feats? The task of developing a theoretical framework for this emergence - and to then using this understanding to construct more robust, efficient, controllable, and generally better machine learning models - is currently a focus of extremely intense study. Philosophically similar problems involving the emergence of non-trivial collective behavior from simple mi...