Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstruction

no code implementations • 28 May 2022 • Dongjie Wang, Yanjie Fu, Kunpeng Liu, Xiaolin Li, Yan Solihin

We reformulate representation space reconstruction into an interactive process of nested feature generation and selection, where feature generation is to generate new meaningful and explicit features, and feature selection is to eliminate redundant features to control feature sizes.

Feature Engineering feature selection +1

MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of CNNs

no code implementations • 28 Oct 2020 • Jonathan Ponader, Sandip Kundu, Yan Solihin

The increased use of Convolutional Neural Networks (CNN) in mission critical systems has increased the need for robust and resilient networks in the face of both naturally occurring faults as well as security attacks.