Sai Ravela presents at Shell, arguing for theory-data symbiosis, which includes:

• Models from theory suffer from nonlinearity, dimensionality and uncertainty
• Models from data suffer from the above plus issues of generalization, extrapolation, and the representation of theory
• Can we do better than either source alone? Three ideas:
  • Machines complied from theory and adapted with data -- using models to accelerate learnng
  • Using theory to configure RKHS, stabilize and constrain learning
  •  Using learning to accelerate solutions to inverse problems 
• Optimizing stability of hybrid systems
• New class of Neural Flow Kernels