[Day 626] I just gave a lecture to 400 students

Today, I was invited to give a guest lecture for the Stanford class CS224N: Natural Language Processing with Deep Learning. I was pretty excited about the opportunity. First, I’d never given a lecture to such a big audience before – there are 400+ students in the class. Second, it’s Richard Socher‘s class. He’s hands down one of the most chill professors I know. For some reason, he always looks like he’s just got out of bed and we occasionally catch him biking down the stairs to the classroom. Third, I’d always heard that speaking at NVIDIA Auditorium is lit and I want to try it out before graduating. Continue reading “[Day 626] I just gave a lecture to 400 students”

Advertisements
[Day 626] I just gave a lecture to 400 students

[Day 281] TensorFlow Dev Summit Tomorrow!

I’m half excited, half nervous about the TensorFlow Dev Summit tomorrow. I’m excited because it’s the first official TF event, and I will undoubtedly learn a lot. I’m nervous because I’ll be around strangers! S-T-R-A-N-G-E-R-S!!!!

Seriously, what do people do at an event like this? Do you approach to people? Do you maintain eye contact? What if nobody wants to talk to you? What if you accidentally come across as being creepy af? What if you want to take a nap?

TL;DR: If you’re at the event, please come say hi.

 

 

[Day 281] TensorFlow Dev Summit Tomorrow!

[Day 276] Detailed instruction on how to do Style Transfer

If you don’t already know, style transfer is the cool, hip thing that has been taking the recreational AI community by storm. It’s so cool that even Kristen Stewart co-authored a paper about it. To quote one researcher who has done extensive work in style transfer that I’ve got a chance to talk to, “it is an utterly unremarkable paper that wouldn’t have been published otherwise [if Kristen Stewart’s name is not on it]. That’s a publicity stunt.”

kristen stewart style transfer.jpgSome background on why I’m doing this: I’m teaching the course CS 20SI: “TensorFlow for Deep Learning Research” and for the assignment about convolution neural networks, I thought it’d be fun for students to do style transfer as their exercise at home. They, after all, showed a lot of enthusiasm when we did Deep Dream in class.

Continue reading “[Day 276] Detailed instruction on how to do Style Transfer”

[Day 276] Detailed instruction on how to do Style Transfer

[Day 176] Why Stanford has the coterm program

Co-terminal master’s degree is a unique Stanford’s program that allows Stanford undergraduates to stay on for an extra year to earn a master’s degree. You have to apply, but it’s  a pretty easy and sweat-free process. Almost everyone I know who applied  got in. I never knew about the history of the program until today, when I talked to Pat Langley.

Continue reading “[Day 176] Why Stanford has the coterm program”

[Day 176] Why Stanford has the coterm program

[Day 171] Lying with statistics: why Allan Lichtman’s predictions aren’t that good

One of my favorite sayings was the one populated by Mark Twain and frequently (probably wrongly) attributed to the late British Prime Minister Benjamin Disraeli: “There are three kinds of lies: lies, damned lies, and statistics.” I get slightly annoyed when accredited newspapers use statistics to manipulate readers.

This afternoon, I saw this headline on the Washington Post:

learn365project_statistics_lie

Continue reading “[Day 171] Lying with statistics: why Allan Lichtman’s predictions aren’t that good”

[Day 171] Lying with statistics: why Allan Lichtman’s predictions aren’t that good