Signal Processing for Deep Learning and Machine Learning


Machine learning and Deep Learning are powerful tools for solving complex modeling problems across a broad range of industries. The benefits of these techniques are being realized in applications everywhere, including predictive maintenance, health monitoring, financial portfolio forecasting, and advanced driver assistance systems.

However, developing predictive models using Deep Networks for signals obtained from sensors is not a trivial task. Moreover, there is an increasing need for developing smart sensor signal processing algorithms which can be either deployed on edge nodes / embedded devices or on the cloud depending on the application.

In this session we will showcase latest techniques in MATLAB including Invariant Wavelet Scattering Framework and how this technique can be used as an automatic feature extractor for building models that can classify signals. We will explore an example of classification system that is built using automatic feature extraction using invariant scattering networks with the goal of recognizing the genre of a music sample.  We will also explore how capabilities in addon tools like Statistics and Machine Learning Toolbox and Deep Learning Toolbox can aid in building the predictive models.


Using real-data we will explore the following topics:

  • Signal Pre- processing techniques
  • Easily manage signal datasets using datastores
  • Automatic feature extraction techniques for classifying signals
  • Leverage high-performance computing resources, such as multicore computers, GPUs, computer to scale up the performance

Please allow approximately 45 minutes to attend the presentation and Q&A session. We will be recording this webinar, so if you can't make it for the live broadcast, register and we will send you a link to watch it on-demand. 

About the Presenter

Kirthi K. Devleker is a Product Manager at MathWorks focusing on Signal Processing and Wavelets Toolbox. Kirthi specializes in helping MATLAB users see the value of advanced Signal Processing and Machine Learning techniques applied to sensor data across multiple industry verticals such as medical, aero-defense and other industries. He has been with MathWorks for 8 years, and has a Masters in Electrical Engineering from San Jose State University.

Product Focus

This live webinar has ended. You can now view the on-demand webinar.

See on-demand webinars