Conferences and supporting programme
Sorting Through the Many Options for Machine Learning at the Edge
The data explosion combined with an increasing level of processor performance has led to a tremendous level of interest and capability to deliver machine learning at the edge. What's most amazing is that machine learning can now be accomplished on a wide range of device categories, from MCUs with Arm Cortex-M4 and M7 cores to complex SoCs with high-end A-class cores, GPUs, and machine learning accelerators. The key to success is learning how to utilize proper training techniques, but beyond that how to generate the most optimized inference engines that will be used to perform classifications and make the right decisions. This presentation will highlight some basic training techniques, such as data augmentation, but the focus will be on various ways to deploy neural network frameworks and classical machine learning algorithms. We will demonstrate these techniques with some real use cases such as face recognition and anomaly detection.
--- Date: 26.02.2019 Time: 3:00 PM - 3:30 PM Location: Conference Counter NCC Ost