Teachers! Parents!
It is legal and perfectly welcome to email scientists asking for a PDF of their paper.
Until all papers are free, please RT to make this more widely known. And fyi, scientists don't get the $$ from sales of papers so all it costs us is 1 minute of time!
“Technology come and go, but it has a lot in common. Set priorities right. Invest 80% of your learning time in fundamentals. Leave 20% for frameworks, libraries and tools.”” https://t.co/z3XV2PDrkH
The same applies to ML. Pick fundamentals over the latest Deep RL algo or xGAN.
This rule sounds correct to me. I invite Devil's advocates. Nuances and exceptions help.
Here's the document that contains the claim(s): https://t.co/0eUkqQF7rw
When trying to find a bug, forget what you expected or wanted, and focus on what your program is doing. Holding onto the specs while trying to find the bug just slows you down.
This is my interpretation of claims from Stanford's CS106A.
Deep learning meetup in SF @ USF on Mon, Mar 5:
https://t.co/dL5R5Vt5N6
Come to get unstuck, to teach, to meet people, or just to have some company while working on a deep learning project.
Deep learning meetup in SF @ USF on Mon, Feb 26:
https://t.co/fgLdfUB86C …
Come to get unstuck, to teach, to meet people, or just to have some company while working on a deep learning project.
(Looks like this person detector needs some work.)
We're excited to announce that we're part of @ycombinator's Winter '18 batch!
Side-note: we're currently serving around 10% of the batch. So if you want to work in #DeepLearning at an amazing YC startup, you should definitely apply.
https://t.co/q1ocIymj4M
#5: Deep learning projects meetup in SF @ USF on Mon, Feb 26:
https://t.co/fgLdfUB86C
We organize into small groups so each person can stay active. If you're in between projects, you can still come to learn and help us think.
Onepanel .io will provide food and GPU access.
@fchollet You said in your book, "intuitions you develop through these low-dimensional representations may not always be accurate in practice. This has historically been a source of issues in the world of deep-learning research." What's an example that comes to mind?
#4: Deep learning projects meetup in SF @ USF on Mon, Feb 12:
https://t.co/umMFbHrUAy
https://t.co/CAXM5YQ4qL will be providing sandwiches and GPU access.
Come to get unstuck, to teach, to meet people, or just to have some company while working on a deep learning project
To get myself to stop watching tqdm training loops, I set ncols to 0:
`tqdm(self.trn_dl, desc="Train", ncols=0)`
I feel like I'm being no fun, but they're too addicting.
#3: Deep learning meetup in SF @ USF on Mon, Feb 05:
https://t.co/VD1qOe5XyY
Come to get unstuck, to teach, to meet people, or just to have some company while working on a deep learning concept or project. @DataInstituteSF
I've just launched Practical Deep Learning for Coders 2018! If you think it newsworthy please consider adding your vote on Hacker News :)
https://t.co/JnB7JqXlLx
https://t.co/uTT35WLxq4
Spoiler alert—the 7 things are:
Learn to code
Practice #openscience
Endorse reproducible research
Ditch the lecture
Teach with computing (use #Jupyter)
Writing is hard. Do it often.
Use Twitter professionally.
@Jugger_nought @LorenaABarba I'm guessing "ditch the lecture, and teach with computing" go together. I think lectures can be net beneficial, as long as they're uploaded so people can watch them on a faster speed and pause to think and look things up. Add Jupyter to that and I'm sold.
Deep learning meetup in SF @ USF on Mon, Jan 29: https://t.co/ry3m72HXyi
Come to get unstuck, to teach, to meet people, or just to have some company while working on a deep learning concept or project. @DataInstituteSF