Eventi in programma (1)
Optimization is a major topic in the world of data science. Most machine learning algorithms rely on optimization processes to obtain the parameters that minimize a certain measure of error (e.g. loss). In addition, optimization can help to solve various business problems such as portfolio optimization, energy efficiency, production or transportation models.
In today’s presentation we will describe two uncommon and fascinating applications of optimization in the field of controlling a set of ordinary differential equations, both applied within a complex and promising R&D project at Eni. While the first methodology is based on an evolutionary algorithm called differential evolution, the second one is based on reinforcement learning. In addition to the theoretical aspects we will discuss a concrete application on a toy problem, including some code snippets in Python.
Salvatore Guastella works as a data scientist in Eni’s data science center of excellence. He works on the development of machine learning models in industrial and research and development projects. Previously he worked as a biostatistician in the field of medical research dealing mainly with survival analysis, cox regression and comparison of classification techniques.
Salvatore has a bachelor and a master’s degree in statistics from the university of Palermo.
Alberto Prospero is the lead data scientist of Eni, working in the development of advanced solutions aimed at improving business decisions and processes. He also provides the technical lead to the team in defining best practices, data models and tools. Previously, he worked as both lead and senior data scientist in Pirelli, focusing on the data modeling of telemetric information and the optimization of factory processes. He started his career at Nextbit, a consulting company based in Milan. Alberto received a Master’s Degree in Mathematics in 2013 from the Catholic University and completed his academic career in 2014, graduating in Interdisciplinary Mathematics at the University of Warwick.
Topics: reinforcement learning, differential equations, genetic algorithms.
This event will be held in English and will be streamed live via our Youtube channel (https://www.youtube.com/c/DataScienceMilan). The live streaming will be listed before the event starts.
During the event, you will be able to interact and ask questions in the embedded Youtube live chat or via the #general channel in our slack workspace. You can request an invite via our website, at the get in touch section, or by following this direct link: https://app.slack.com/client/T1K880GR0/C1K7XRKJ9.
18:30 Data Science Milan community opening
Would you be happy to host one of our events? Increase your popularity and be known by our community by hosting one of our interesting events. Contact us at [masked].
If you are interested in doing a lightning talk or want to propose an event, hackathon, panel discussion, roundtable, or any sort of initiative please submit your proposal by getting in touch with a member of the staff. More info at www.datasciencemilan.org.
This event is supported by IAML (Italian Association of Machine Learning).