Machine learning is quickly becoming a powerful tool for solving complex modeling problems across a broad range of industries. It is enabling engineers and scientists to develop models which learn from data and can be deployed as a part of packaged applications that can run efficiently on embedded systems as well as cloud infrastructure. The benefits of machine learning are being realized in applications everywhere, including predictive maintenance, health monitoring, financial portfolio forecasting, and advanced driver assistance. However, successfully applying machine learning in practice presents several challenges. It is not always clear which data is going to be the most useful for prediction, and tuning machine learning hyperparameters can consume a large amount of time.

In this webinar, you will learn how machine learning tools in MATLAB address these challenges. We will demonstrate:

  • Working with large out-of-memory data using the MATLAB “tall” framework
  • Reducing dimensionality and identifying import features using advanced feature selection techniques
  • Best practices for tuning hyperparameters to optimize the performance of your model
  • How to deploy models for use in production IT systems or embedded devices

About the Presenter

Shyamal Patel is a technical product manager leading products in the area of Statistics, Machine Learning and Deep Learning. He has a PhD in Electrical Engineering from Northeastern University and MS in Electrical Engineering from Rutgers University. Prior to joining MathWorks, he was working on developing algorithms for human health monitoring by applying signal processing and machine learning techniques to data gathered using wearable sensors (e.g. accelerometer, ECG, EMG).

Product Focus

  • Statistics and Machine Learning Toolbox
Session 1:
9:00 a.m. U.S. EST/ 2:00 p.m. GMT/ 3:00 p.m. CET
Session 2:
2:00 p.m. U.S. EST/ 7:00 p.m. GMT/ 8:00 p.m. CET
Session 3:
7:00 p.m. U.S. EST/ November 30, 2016 11:00 a.m. AEDT; 1:00 p.m. NZDT