7 November 2018
Our kdb+ machine learning night will feature three speakers talking about kdb+ powered ML applications and a new ML-Toolkit.
"Teaching kdb+ to read Japanese"
Mark Lefevre's talk will focuse on utilizing neural networks and how supervised learning can be used in q to teach a machine to recognize Japanese characters from handwritten images.
"Feature Engineering ML-Toolkit"
Conor McCarthy will present the latest ML-Toolkit, which includes both utility functions for general use and an implementation of the FRESH (Feature Extraction based on Scalable Hypothesis tests) algorithm.
"Patient ML app demo using Python, R & kdb+"
Nataraj Dasgupta will demonstrate how a high-performance data mining, visualization and machine learning application built with kdb+, can analyze tens of millions of patient IoT signals from every hospital bed in the US using a single kdb+ instance.
Mark Lefevre is a VP at Nomura where he is a Python and kdb+ developer for the equity derivatives desk. He has worked in financial technology for over a decade, much of which was spent in Japan working at the Bank of Tokyo Mitsubishi UFJ.
Conor McCarthy is a machine learning engineer for Kx Systems working on the development of machine learning capabilities through the development of ML algorithms and feature extraction procedures currently based in London.
Nataraj Dasgupta is VP of Advanced Analytics and Data Science at RxDataScience. He has two decades of experience building cutting edge analytics platforms for Big Data and Data Science, including over eight years at UBS, IBM and Philip Morris.