Self-Driving Deep Learning with Lex Fridman

Self-driving cars are here. Fully autonomous systems like Waymo are being piloted in less complex circumstances. Human-in-the-loop systems like Tesla Autopilot navigate drivers when it is safe to do so, and lets the human take control in ambiguous circumstances.

Computers are great at memorization, but not yet great at reasoning. We cannot enumerate to a computer every single circumstance that a car might find itself in. The computer needs to perceive its surroundings, plan how to take action, execute control over the situation, and respond to changing circumstances inside and outside of the car.

Lex Fridman has worked on autonomous vehicles with companies like Google and Tesla. He recently taught a class on deep learning for semi-autonomous vehicles at MIT, which is freely available online. There was so much ground to cover in this conversation. Most of the conversation was higher level. How do you even approach the problem? What is the hardware and software architecture of a car?

I enjoyed talking to Lex, and if you want to hear more from him check out his podcast Take It Uneasy, which is about jiu jitsu, judo, wrestling, and learning.


Transcript provided by We Edit Podcasts. Software Engineering Daily listeners can go to to get 20% off the first two months of audio editing and transcription services. Thanks to We Edit Podcasts for partnering with SE Daily. Please click here to view this show’s transcript.


Have you been thinking you’d be happier at a new job? If you’re dreaming about a new job and have been waiting for the right time to make a move, go to Hired makes finding work enjoyable. Hired uses an algorithmic job-matching tool in combination with a talent advocate who will walk you through the process of finding a better job. Check out to get a special offer for Software Engineering Daily listeners–a $600 signing bonus from Hired when you find that great job that gives you the respect and salary that you deserve as a talented engineer. 

Bugsnag is an automatic error-monitoring platform that helps developers understand the impact of application errors and fix the ones that matter in a time-efficient and enjoyable way. Bugsnag’s open source error reporting libraries automatically capture errors and provide in-depth diagnostic reports across all major programming languages and frameworks. Diagnostic reports consolidate the information you need to reproduce errors in one place, including the stacktrace. Errors are grouped by root cause and mapped to users so you can easily identify which errors are the most widespread and affect the greatest amount of users. Integrate with Slack and PagerDuty to get notified in real-time of new errors and spikes in your error rate. Then, integrate with your issue tracker or use Bugsnag’s workflow to help you move errors through your debugging process and get them fixed for your users.  Airbnb, Lyft, and Shopify all use Bugsnag for error-monitoring. Get up and running in three minutes. Try all features free for 14 days at

Toptal is the best place to find reasonably priced, extremely talented software engineers to build your projects from scratch or scale your workforce. Get a free pair of Apple Airpods when you use to work with an engineer for at least 20 hours.

VividCortex is the best way to improve your database performance, efficiency, and uptime. It’s a cloud-hosted monitoring platform that eliminates your most critical visibility gap, providing insights at 1-second granularity into production database workload and query performance. It measures the execution and resource consumption of every statement and transaction, so you can proactively fix future database issues before they impact customers. To learn more, visit and find out why companies like Github, DigitalOcean, and Yelp all use VividCortex to see deeper into their database performance. Learn more at, and get started today!