Neural Acceleration
Neural acceleration, is the process of speeding up approximation computation elements via artificial neural networks. [Neural Acceleration of Graph Based Utility Functions for Sparse Matrices.pdf: Page 1]
Neural Acceleration involves tuning annotated pieces of code that can be approximated into cheap artificial neural networks. It is one of the still evolving modern generalized programming model that combines accelerators and approximations is still evolving. [Neural Acceleration of Graph Based Utility Functions for Sparse Matrices.pdf: Page 1]