I am very pleased to announce that my signal-processing, machine-learning, and modulation-recognition collaborator and friend John Snoap has successfully defended his doctoral dissertation and is now Dr. Snoap!
I started working with John after we met in the Comments section of the CSP Blog way back in 2019. John was building his own set of CSP software tools and ran into a small bump in the road and asked for some advice. Just the kind of reader I hope for–independent-minded, gets to the bottom of things, and embraces signal processing.
As we interacted over email and zoom it became clear that John was thinking of making a contribution in the area of modulation recognition, and was also interested in learning more about machine learning using neural networks. Since I had been recently engaged in hand-to-hand combat with machine learners who were, in my opinion of course, injecting more confusion than elucidation into the field, I figured this might be a friendly way for me to understand machine learning better, and maybe there would be a way or two to marry signal processing with supervised learning. So off we went.
Fast forward four years and we’ve published five papers, with a sixth in review, that I believe are trailblazing. John is that rare person that has mastered two very different technical areas: cyclostationary signal processing and deep learning. Because I believe that neural networks do not actually learn the things that we hope they will, but need not-so-gentle nudges toward learning the truly valuable things, a researcher with one foot firmly in the signal-processing world and the other firmly in the machine-learning world has a very bright future indeed.
The title of John’s dissertation is Deep-Learning-Based Classification of Digitally Modulated Signals, which he wrote as a student in the Department of Electrical and Computer Engineering at Old Dominion University under the direction of his advisor Professor Dimitrie Popescu.
Congratulations Dr. Snoap! And thank you for everything.
Is his dissertation available online anywhere?
Always exciting to see someone blending ML and DSP! Will there be a public release of the dissertation?
Congrats to John. Who knew you could make great friends through a blog?
Thank you, Chad!!!
It has definitely been quite the journey learning everything. I could not have done it without you (or your blog!). I can still remember when I was first trying to understand cyclostationary signal processing. This blog was the one place I could find detailed information about CSP with your examples showing what various results should look like. I remember thinking, “This guy knows what he is talking about because these plots make sense! I’m recreating this because there is a clear path forward and I want to understand how these tools work!”
It actually turned out the first CSP task I was pursuing had already been accomplished/published by a fellow researcher, but by then I already had a (mostly, even though I thought it was fully, heh) working CAF, FSM, and TSM estimator. So, I pushed to take on the machine learning challenge because with everything I did Dimitrie would first make me recreate results and I wanted to recreate the MSSA, hahaha! How’s that for an ulterior motive!? Mine’s still not yet to Chad’s level, but that is fine for now. And finally with a few machine-learning mod-rec data shift breakthroughs the finish line is soon to be crossed!
So thankful you were willing to teach and help me learn this subject, Chad. I learned more about digital signal processing than I thought I was ever going to (and I had previously come close to thinking I was never going to learn what I wanted to about digital communications; even after taking all the courses at ODU, and watching all the MIT Open Courseware videos, and still not finding a path that enabled me to apply theory and really learn it). It’s one thing to have someone teach you theory and you go, “Ok, I can write some code in MATLAB for that. Ok my results sort of look like what that professor was talking about. I think I did it right.” But it is way easier for the brain to learn when you actually have something credible to base your results on and someone who is helping/coaching you overcome the obstacles that are in the way.
Concerning posting the dissertation online, I do plan to eventually do that, and will post a link here when I do, but it may be several months from now. The final portion of the dissertation contains the research/results that we have submitted to a journal and is being reviewed. I plan to wait for it to be accepted before providing the dissertation online. Hopefully not many months from now.
Thank you!
I’m a bit late to the party here but congrats, Dr. Snoap!