Breaking news: grad students do have friends.
I was pretty lost at TensorFlow summit last year when I met David, Frederik and a few other grad students at lunch and decided immediately that I’d follow them both on Twitter and in real life. Continue reading “[Day 691] What PhD students do on the weekend”
An AI researcher became the face of Yves Saint Laurent
Intel had Flo Rida to launch their latest GPU
Justin Timberlake’s latest video was shot at a Deep Learning conference
Disclaimer: I didn’t verify whether he actually bought the Tesla S or not. This is what he told me.
Today, Dani and I went to watch Baby Driver. It was meh. The director seemed to have problem deciding whether to make an action or a romantic movie, and he ended up doing both. The best part of our cinematic experience was actually the Uber drivers taking us back and forth.
The first driver was an earnest guy in his mid 20s. He drove a nice Toyota Corolla whose window pockets were filled with water and granola bars. “You’re welcome to have some.” “No thank you. I’m good.” When Dani and I saw a checker cab with “You can book us online with curb” painted on the side, I wondered out loud if “curb” was Uber for taxis, and the driver laughed hysterically. I was feeling pretty good about myself until I realized that he laughed hysterically at almost every attempt at jokes we made. Continue reading “[Day 486] This guy bought a Tesla Model S to drive Uber select hoping to potential investors”
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.
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.”
Some 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”
In my anthropology class, there is this lady who comes to every lecture with a peculiar-looking keyboard and transcribes everything everyone says in the room. The average rate for English speakers in the US is 150 wpm, so I estimate her writing speed is well above 150 wpm because she gets everything everyone says right, even manages to insert things like *bell chiming* or *indiscernible sound in the background*. This is really impressive, given that professional typists only have the speed of 75-85 wpm.
So, after lecture today, I decided to come and introduce myself to her. When I told Sarah, the lady’s name, about my fascination with her typing, she was very excited. She told me she loved talking about that, because she thinks it’s magical too. Here is a picture of the setup that she uses:
Continue reading “[Day 169] The magic of phonetic writing”