Data science is ubiquitous to advanced statistical and machine learning techniques. As long as there is data to analyze, the need to explore is obvious.Yet, an important key component to any data science task frequently undervalued is the exploratory data analysis (EDA).
A few weeks ago, a colleague asked me - “How Machine Learning is Applicable in Material Science?”. It got me interested, because these are two topics, I understand very well. We both studied Computational Material Science (Material Informatics), utilized python and other tools to build models, evaluated terabytes of data from simulations, used statistical mechanics and numerical methods to extract useful insights on the structure-property relationships of material. Indeed, machine learning methods sound familiar to a computational material scientist, but it is an elusive familiarity. In this blog, I will examine areas in which machine learning and material science intertwine.
Our everyday existence is influenced by materials, from Silicon chips storage of data in billionths of a second, to new alloys for automobile engines, to solar panels for renewable energy. Indeed, advances in materials shape our day-to-day lives and drive economic growth. Simply put materials make things happen.
I draw inspiration from creativity in science, and the ability to take and manipulate the science to benefit society. I also draw creativity from great leaders of our times. Phil Jackson, he brought Zen into the chaotic environment, Colin Powel, Madeline Albright.
Well! I finally got around to putting this old website together. Welcome to my all things data journal. Here, you can read posts about data and learn with me as I explore the exciting word of machine learning technologies and big data. I am passionate about exploring the root issues behind relevant problems, and then using data to help build innovative products or find impactful solutions for millions of people around the world to improve the way people work and think. Let’s learn together.