Software Engineering

Podcast: Neurosymbolic AI with Mohan Mahadevan

Alex Strick van Linschoten
Jan 27, 2022
1 Min Read

Last updated: February 16, 2022.

Our guest this week was Mohan Mahadevan, a senior VP at Onfido, a machine-learning powered identity verification platform. He has previously worked at Amazon heading up a computer vision team working on robotics applications as well as for many years at KLA, a leading semiconductor hardware company. He holds a doctorate in theoretical physics from Colorado State University.

Mohan had mentioned that he thought it might be interesting to discuss neurosymbolic AI, and the implications of a shift towards that as a core paradigm for production AI systems. In particular, we discuss the practical consequences of such a shift, both in terms of team composition as well as infrastructure requirements.

In this clip, Mohan explains some of the benefits of traditional end-to-end neural networks as compared to neurosymbolic approaches:

I didn’t know much about this approach and the tradeoffs before doing some reading ahead of this conversation, and I think it offers a useful overview of some of the tradeoffs to be considered when implementing a neurosymbolic solution to a problem. Check out out the full episode below or however you prefer to listen to podcasts!

Subscribe to Pipeline Conversations with your favorite podcast player here.

Start your new ML Project today with ZenML Cloud

Join 1,000s of members already deploying models with ZenML.