Call Search
     

New to Ham Radio?
My Profile

Community
Articles
Forums
News
Reviews
Friends Remembered
Strays
Survey Question

Operating
Contesting
DX Cluster Spots
Propagation

Resources
Calendar
Classifieds
Ham Exams
Ham Links
List Archives
News Articles
Product Reviews
QSL Managers

Site Info
eHam Help (FAQ)
Support the site
The eHam Team
Advertising Info
Vision Statement
About eHam.net

donate to eham
   Home   Help Search  
Pages: [1]   Go Down
  Print  
Author Topic: Denoising Auto-encoder for Morse code using Tensorflow Machine Learning  (Read 392 times)
AG1LE
Member

Posts: 151


WWW

Ignore
« on: November 25, 2017, 07:22:12 PM »

Gents
Another Machine Learning experiment during the long weekend.
Can you read the Morse character in this image?


Well,  with a trained denoising auto-encoder you can easily decode this character. I was quite impressed to see the performance of this neural network after only 30 minutes training session on my laptop.  More details in my blog post:
http://ag1le.blogspot.com/2017/11/morse-denoising-auto-encoder.html

By the way: Tensorflow based Jupyter Notebook source code posted in Github https://github.com/ag1le/LSTM_morse/blob/master/MNIST-MORSE-DE_NOISING_DECODER-ENCODER.ipynb in case you are interested in replicating this experiment.  

73 de AG1LE
« Last Edit: November 25, 2017, 07:29:49 PM by AG1LE » Logged
KD8IIC
Member

Posts: 673




Ignore
« Reply #1 on: November 25, 2017, 09:27:56 PM »

  Looks like an awful lot of information to produce and then decode a single character
  which could, in the case of Morse, could simply be a single audible "dit" or "dah".
  Might be of some value if I were a robot and not human.
  Next....
Logged
Pages: [1]   Go Up
  Print  
 
Jump to:  

Powered by MySQL Powered by PHP Powered by SMF 1.1.11 | SMF © 2006-2009, Simple Machines LLC Valid XHTML 1.0! Valid CSS!