Abstract: An embodiment includes performing a dedicated training process on a non-polynomial neural network resulting in a trained polynomial neural network, where the training process includes performing a plurality of training iterations on the neural network, and performing, between the training iterations, loss processing that (i) minimizes a loss of the neural network and (ii) reduces a range of values to a non-polynomial layer (NPL) of the neural network. The embodiment estimates a range of input values to the NPL of the thus trained neural network. The embodiment forms a replacement layer for the NPL, where the replacement layer comprises a polynomial approximation of an operation performed by the NPL. The embodiment also generates a revised neural network by replacing the NPL of the trained neural network with the replacement layer.

Abstract: A skip-connections analysis method, system, and computer program product for accelerating neural networks by removing skip-connections and efficient skip-connection realization.

Abstract: An example system includes a processor to receive a non-homomorphic encryption (HE)-friendly analytics model including a non-polynomial element. The processor is to train a substitution model in which the non-polynomial element of the non-homomorphic encryption (HE)-friendly analytics model is replaced with a sub-network including a polynomial replacement element.