MS Build 2017 Sessions on Artificial Intelligence and Machine Learning

Early detection of cancer: Developing NLP classifiers to analyze biomedical literature microRNAs are bio-markers, which may indicate cancer and other diseases even at early stage. Together, we developed a pipeline and an NLP classifier to detect relations between genes and micro-RNAs in medical research documents. The generalized code and leanings are open sourced and shared on Github. Sound and vision: Visual anomalies from audio data using deep learning We walk you through an effort by Sierra Systems with help from Microsoft and the Microsoft Cognitive Toolkit to detect and classify oil pipeline leaks, using audio data from a sensor ball deployed by Pure Technologies. We convert this audio data into images and use state-of-the-art Deep Learning techniques in the realm of image recognition to find'visual' anomalies and tell leaks from everyday events.