Kaggle's 5 remote-first tips for new WFH'ers. Thanks @MeganRisdal and @vimota for writing this up! https://t.co/cmbeIXkH2H
— Ben Hamner (@benhamner) March 27, 2020
Kaggle's 5 remote-first tips for new WFH'ers. Thanks @MeganRisdal and @vimota for writing this up! https://t.co/cmbeIXkH2H
— Ben Hamner (@benhamner) March 27, 2020
"Machine Learning code generally doesn’t throw errors, it just underperforms" https://t.co/zIF0JhYb4j pic.twitter.com/zJIxPFxtJe
— Peter Skomoroch (@peteskomoroch) March 24, 2020
Very useful for conveying feelings through your tracebacks. pic.twitter.com/eKBHtvkaPP
— Jake VanderPlas (@jakevdp) March 17, 2020
This is a super extensive article by @Tim_Dettmers on how to choose a grad school.
— Sebastian Ruder (@seb_ruder) March 10, 2020
Its goal: to "help you make a balanced choice that not only leads to academic success but long-term satisfaction and a full and rich life." 👏https://t.co/lxUmlNA9tu
Really interesting results! The correct answer came in 3rd place, probably because it contains not one but two gotchas. https://t.co/yUKldF07I5
— Jake VanderPlas (@jakevdp) March 5, 2020
sweet little function for parallelizing processing of DataFrames 🙂
— Radek Osmulski (@radekosmulski) February 28, 2020
All credit goes to: https://t.co/FstcS9nbmq
Very RAM heavy but useful in some scenarios pic.twitter.com/DlEwKZUZgc
Ever wondered what @PyTorch nn.Module and nn.Parameter do really? And how hooks actually work? Here's a working implementation from scratch of their key functionality, in one tweet!
— Jeremy Howard (@jeremyphoward) February 27, 2020
From our upcoming book and course:
- https://t.co/bLd3sEXTpV
- https://t.co/guKT7y9VfM pic.twitter.com/wYh1jyb1Bm
Calculate memory used by a #pandas dataframe:
— Daily Python Tip (@python_tip) February 24, 2020
df.memory_usage(deep=True).sum()
"Trace precedents" in @msexcel is a great way to visualize the receptive field of a convnet. We'll be using this trick in our upcoming book and next course in San Francisco. The green cell is activation, blue square receptive field https://t.co/guKT7y9VfMhttps://t.co/bLd3sEXTpV pic.twitter.com/iZpXspd3Vg
— Jeremy Howard (@jeremyphoward) February 24, 2020
Got tired of Googling this, so here's how to open a Jupyter notebook from within a virtual environment: https://t.co/1y2Jdu8TrN
— Vicki Boykis (@vboykis) February 18, 2020
#NumPy has many function ignoring NaN values (the list is 👇👇👇)
— Daily Python Tip (@python_tip) February 17, 2020
>>> import numpy as np
>>>
>>> np.nanvar([1,2,3])
0.6666666666666666
>>> np.nanvar([1,2,3,np.NaN])
0.6666666666666666
>>> np.var([1,2,3,np.NaN])
nan pic.twitter.com/aMxHLGMZQ7
If you're not sure where to start on the ARC competition, here's my advice.
— François Chollet (@fchollet) February 13, 2020
It's a very difficult challenge, but I strongly believe (with some evidence) that someone smart & motivated can develop in a few weeks an approach that solves ~5-10% of the tasks in the hidden test set. pic.twitter.com/1hvZrXugnt