There are many resources available for learning how to leverage Deep Learning to process imagery. However, very few resources exist to demonstrate how to process data from other sensors such as acoustic, seismic, radio, or radar. In this tutorial, we will introduce some basic methods for utilizing a Convolutional Neural Network (CNN) to process Radio Frequency (RF) signals. More specifically, we will look at the classic problem of detecting a weak signal corrupted by noise. We will show you how to leverage the DIGITS application to read in a dataset, train a CNN, adjust hyper-parameters, and then test and evaluate the performance of your model.

Lab created by KickView - Intelligent Processing Applications
Lab Details
Tokens Required: 30 Tokens
Levels: Beginner
Duration: 01 h:30 m
Access Time: 01 h:55 m
Setup Time: 00 h:06 m
Tags: Deep Learning, self-paced, Machine Learning, DIGITS
Language globe Available Languages:

To take a lab in a different language change the default language in your account

En English

Reviews 119

  1. Jean Ming

    Jean Ming Reviewed about 15 hours ago
  2. Jacci Cenci
    This is a good DIGITS Demo with Signal Processing. I would like to know more about Kickview so I will spend more time on their site. Maybe we should invite them to speak at one of our DGX bi-weekly calls or on Ty's Calls I did not have any issues with this demo. One of the screen shots under New CNN Model Creation the base learning rate does not match up. Also, under Neural Network Generalization on New Signals - For this tutorial, we have downloaded the model and prepared it for you. The path to the model is /data/model. I kept looking for a screen shot of how that was pre-prepared.
    Jacci Cenci Reviewed 3 days ago
  3. dima medved
    dima medved Reviewed 5 days ago
  4. S R
    Good lab in detailing how learning rate affects accuracy/overfitting. But does this use case completely fall in the realm of CNNs? Do signals have any time interdependent components that would be better represented by a LSTM?
    S R Reviewed 12 days ago
  5. David Nola

    David Nola Reviewed 16 days ago