Why join the course?
Have you ever wondered how mathematics can be used to solve big data problems? This course will show you how. Mathematics is everywhere, and with the rise of big data it becomes a useful tool when extracting information and analyzing large datasets.
Learn how maths underpins big data analysis
We will begin by explaining how maths underpins many of the tools that are used to manage and analyze big data. We will show you how very different applied problems can have common mathematical aims, and therefore can be addressed using similar mathematical tools. We will then proceed to introduce three such tools, based on a linear algebra framework. These tools and the problems that they address are:
- eigenvalues and eigenvectors for ranking
- graph Laplacian for clustering
- singular value decomposition for data compression.
Develop your analysis skills with prototypical case studies
In this course, we have chosen a number of prototypical problems in data analytics to demonstrate the main concepts. These algorithms can be extended to facilitate their use in big data problems. Our hands-on approach will allow you to develop your analytic skills using self-contained datasets, deepen your understanding of the underlying mathematical methods, and explore how these methods can be applied to big data in your area.
Continue learning with the Big Data Analytics program
This course is one of four in the Big Data Analytics program on FutureLearn from the ARC Centre of Excellence for Mathematical and Statistical Frontiers at Queensland University of Technology (QUT). The program enables you to understand how big data is collected and managed, before exploring statistical inference, machine learning, mathematical modeling, and data visualization. When you complete all four courses and buy a Certificate of Achievement for each, you will earn a FutureLearn Award as proof of completing the program of study.
QUT would like to thank the following content contributors:
- Kevin Burrage
- Giuseppe De Martino
- Steve Psaltis
- Ian Turner
What topics will you cover?
- Introduction to key mathematical concepts in big data analytics: eigenvalues and eigenvectors, principal component analysis (PCA), the graph Laplacian, and singular value decomposition (SVD)
- Application of eigenvalues and eigenvectors to investigate prototypical problems of ranking big data
- Application of the graph Laplacian to investigate prototypical problems of clustering big data
- Application of PCA and SVD to investigate prototypical problems of big data compression
What will you achieve?
- Identify big data application areas
- Explore big data frameworks
- Model and analyze data by applying selected techniques
- Demonstrate an integrated approach to big data
- Develop an awareness of how to participate effectively in a team working with big data experts
Who is the course for?
This course is designed for anyone looking to add mathematical methods for data analytics to their skill set. To get the most out of this course, we recommend that you have studied linear algebra at a university/college level. We would encourage you to refresh your knowledge of vector and matrix algebra before engaging with the course material. We will assume basic MATLAB (or other) programming skills for some of the practical exercises. MathWorks will provide you with free access to MATLAB Online for the duration of the course so you can complete the programming exercises. Visit the MATLAB Online website to ensure your system meets the minimum requirements.
- FREE online course
- Duration: 2 weeks
- 2 hours pw
- Certificates available
This school offers programs in:
Last updated January 29, 2018