Energy Efficient Integrated Mems Neural Network For Simultaneous Sensing And Computing

This paper discusses the development of smart materials, or metamaterials, that integrate sensing, actuation, and computation into one structure. An example of this is the use of a micro-electro-mechanical system (MEMS) for digital computing. This paper also introduces a MEMS neural network of three neurons that can perform simultaneous acceleration sensing and classification tasks. This computing architecture eliminates the need for complex sensors interface and a digital computing unit to perform similar computations, leading to hardware that performs machine learning methods that are no longer shallow and separate between the sensing and the computing layers.