DeepX: A Software Accelerator for Embedded Deep Learning

Deep learning has revolutionized the way sensor measurements are interpreted and application of deep learning has seen a great leap in inference accuracies in a number of fields. However, significant requirement of memory and computational power have been the main bottlenecks in wide scale adoption of these novel computational techniques on resource constrained wearable and mobile platforms. In this demonstration we present DeepX, a software accelerator for efficiently running deep neu- ral networks and convolutional neural networks on resource constrained embedded platforms, e.g., Nvidia Tegra K1 and Qualcomm Snapdragon 800.