Hot-air balloon pilot Richard Varney typically spends his weekends transporting tourists around central Massachusetts in a huge, multicolored balloon. But on a recent Sunday, Varney drove to a local community college and learned to fly a different type of aerial vehicle. "I want to try something new," he said as he watched an instructor demonstrate how to steer a $2,000 drone equipped with a camera. "This could help me launch a side business taking aerial photos of local towns." At least 15 community colleges across the country now have courses that teach people how to pilot drones, according to research conducted by MIT Technology Review.

In the following section we introduce the back-propagation learning algorithm and use mini-batching to express the most compute intensive equations in matrix form. Once expressed in matrix form, hardware optimized numerical linear algebra routines are used to achieve an efficient mapping of the algorithm on to the Intel Xeon Phi co-processor. Section 3 describes the preparation of the data used to train the DNN. Section 4 describes the implementation of the deep neural networks. Section 5 then presents results measuring the performance of a DNN. Finally in Section 6, we demonstrate the application of DNNs to backtesting using a walk forward methodology, and provide performance results for a simple buy-hold-sell strategy.