Introduction to Machine Learning
Machine learning is a collection of computer algorithms that iteratively learn from data how to solve problems with minimal human intervention. This technique has been used successfully to predict exploration targets, classify rocks, and generate automatic 3D geological interpretations, among other applications. Its popularity in the mining industry is growing at an accelerated rate and will become an essential tool in the near future. We will demonstrate the basics of machine learning techniques and workflows, including when and how to use and prepare data. As a participant of the course, you will quickly recognise that datasets have limitations to solve certain machine learning problems. Our facilitator will explore how to select features in the dataset, and will showcase how to test, interpret results and how to select and create meaningful variables from the dataset.
Upon completion of this course, you will be able to:
- Understand what machine learning is and what is it used for.
- Identify different types of software to conduct machine learning.
- Recognise general concepts and workflows.
- Learn how to select meaningful features from a database.
- Become familiar with data preparation and data issues.
- Acquire skills to train, validate and test machine learning algorithms.
- Understand large groups of machine learning techniques for classification and regression.
- Interpret results and how to select and create meaningful dataset variables.
Our facilitator is an experienced practitioner with a robust mix of academic and practical expertise.
DR ADRIAN MARTINEZ VARGAS
P.Geo, Ph.D. in Geological Sciences, ISMM Moa. Specialist in Geostatistics (CFSG), Paris Mining School. B.Eng. Geology, ISMM Moa
Adrian is both a geologist and a geostatistician. He produces open source software for geostatistics and mineral resources in Python, Fortran, Cython, C and SQL. He has worked as a consultant since 2002 covering many commodities including gold, copper, nickel, chromium, and raw material for cement industry. Adrian has considerable experience using multiple indicator kriging for resource estimation of gold deposits with high nugget and domaining issues; with non-linear geostatistics and with conditional simulations for resource estimation and model validation. Adrian has previously worked as an Assistant Professor in Cuba and Ethiopia, teaching geology and geostatistics.
Who is this course for?
This two-day training course is designed for geologists, geophysicists and professionals working in the mining industry. A strong background in mathematics or previous knowledge of machine learning is not required to undertake this course. If your role is to make sense of your data or to automatize tedious tasks, such as core logging, then this training course is for entirely for you.