Learn Python with Talk Python's Python courses

What ML Can Teach Us About Life: 7 Lessons

Episode #309, published Fri, Mar 26, 2021, recorded Fri, Mar 19, 2021.

This episode is carbon neutral.
Machine learning and data science are full of best practices and important workflows. Can we extrapolate these to our broader lives? Eugene Yan and I give it a shot on this slightly more philosophical episode of Talk Python To Me.

The seven lessons:

1. Data cleaning: Assess what you consume
2. Low vs. high signal data: Seek to disconfirm and update
3. Explore-Exploit: Balance for greater long-term reward
4. Transfer Learning: Books and papers are cheat codes
5. Iterations: Find reps you can tolerate, and iterate fast
6. Overfitting: Focus on intuition and keep learning
7. Ensembling: Diversity is strength

Links from the show

Eugene Yan: @eugeneyan
What Machine Learning Can Teach Us About Life - 7 Lessons article: eugeneyan.com

Maker's schedule vs. manager's schedule: paulgraham.com
Naval Podcast: overcast.fm
How to Write Better with The Why, What, How Framework https://eugeneyan.com/writing/writing-docs-why-what-how/
Resources mentioned towards the end of the podcast: eugeneyan.com/resources

New media example - Metal song decomposed by classical musicians
Opera singer: youtube.com
Composer music: youtube.com

YouTube Live Stream: youtube.com
PyCon Ticket Giveaway: talkpython.fm/pycon2021

Want to go deeper? Check out our courses

Eugene Yan
Eugene Yan
Eugene Yan works at the intersection of machine learning & product to build pragmatic, customer-facing ML systems. He's currently an Applied Scientist at Amazon. Previously, he led the data science teams at Lazada and uCare.ai. He writes & speaks about data science, data/ML systems, and career growth at eugeneyan.com and tweets at @eugeneyan.
Episode sponsored by
Ads served ethically
Click to show comments


Individuals can support this podcast directly via Patreon. Corporate sponsorship opportunities available here.
X
Become a friend of the show
Stay in the know and get a chance to win our contests.
See our privacy statement about email communications.