Infusing Structure into Machine Learning Algorithms | Anima Anandkumar | WiDS 2019
About This Video
Anima Anandkumar, Professor of Computing and Mathematical Sciences at CalTech and Director of Research in Machine Learning, NVIDIA.
Standard deep-learning algorithms are based on a function-fitting approach that do not exploit any domain knowledge or constraints. This makes them unsuitable in applications that have limited data or require safety or stability guarantees, such as robotics. By infusing structure and physics into deep-learning algorithms, we can overcome these limitations. There are several ways to do this. For instance, we use tensorized neural networks to encode multidimensional data and higher-order correlations. We infuse symbolic expressions into deep learning to obtain strong generalization. We utilize spectral normalization of neural networks to guarantee stability and apply it to stable landing of quadrotor drones. These instances demonstrate that building structure into ML algorithms can lead to significant gains.