XAI: Using Explainable AI to improve Deep Neural Networks. Can this help Tesla's FSD??

If you wish to support us in creating fun, informative content, please consider giving at our Patreon site here:   / drknowitallknows  . Thank you!

Wherein Dr. Know-it-all discusses the work of Dr. Arthur Choi (UCLA) and others concerning the quest to understand how deep convolutional neural networks function. This new field, XAI, or explainable AI, uses decision trees, formal logic, and even tractable boolean circuits (simulated logic gates) to explain why machine learning using deep neural nets functions so well some of the time, but so poorly other times. Watch this episode and find out how there work can improve AI, and make Tesla's Full Self Driving even better!

If you are looking to purchase a new Tesla and would like 1,000 free Supercharger miles, just click this link and use our referral link: https://www.tesla.com/referral/john11286. Thank you!

Music by Zenlee. Check out his amazing music on instagram —@zenlee_music
or Youtube —    / @zenlee_music  

If you enjoy more outdoorsy, adventure type videos--like climbing the Matterhorn or trekking to Mount Everest Base camp--and a few product reviews too, please check out our sister channel, Whole Nuts and Donuts, right here:    / @wholenutsanddonuts5741  

Please ask questions in the comments below, or at: [email protected]. Thank you!

Links to some interesting articles on XAI:
http://reasoning.cs.ucla.edu/fetch.ph...
http://reasoning.cs.ucla.edu/fetch.ph...
http://reasoning.cs.ucla.edu/fetch.ph...
http://innovation.uci.edu/2017/08/hus...