Smart and Fast Data Processing for Deep Learning in Internet of Things: Less is More

Abstract

Recent advances of deep learning have produced encouraging results comparable to and in some cases superior to human experts. However, the large amount of data input has been a daunting task for deep learning to be widely applied in Internet of Things (IoT) with real-time processing. The goal of this paper is to develop smart and fast data processing scheme for more computational efficient deep learning to support adaptive and real-time applications, which will be able to increase the spectrum and energy efficiency in IoT. We propose to apply singular-value decomposition (SVD)-QR algorithm to preprocessing of deep learning for large scale data input. For the mass data input, we apply limited memory subspace optimization for SVD (LMSVD)-QR algorithm to increase the data processing speed. Simulation results in automated handwritten digit recognition show that SVD-QR and LMSVD-QR can tremendously reduce the number of input to deep learning neural network without losing its performance, and both can tremendously increase the data processing speed for deep learning in IoT.