Twitter | Pretraživanje | |
Andrew Trask
Machine Learning in a company is 10% Data Science & 90% other challenges It's VERY hard. Everything in this guide is ON POINT, and it's stuff you won't learn in an ML book "Best Practices of ML Engineering" This is a lifesaver project
Reply Retweet Označi sa "sviđa mi se" More
Parisa Rashidi 12. pro
Odgovor korisniku/ci @iamtrask
I would say this is also true in academia if working on applied problems. For example, ML applications in healthcare: a lot more beyond a robust analysis, including privacy issues, human subjects, knowledge of regulations, deployment ecosystem, etc.
Reply Retweet Označi sa "sviđa mi se"
MegaExponential TF 12. pro
Odgovor korisniku/ci @iamtrask
Rule 33 is simply wrong and introduce info-leakage from test to train for non iid data.
Reply Retweet Označi sa "sviđa mi se"
Dieter Castel 12. pro
Odgovor korisniku/ci @iamtrask
Very true. Also my (albeit limited) experience. It's not magic, it's still software and software engineering is hard. Secure software even harder.
Reply Retweet Označi sa "sviđa mi se"
Sidharth Ramesh 12. pro
Odgovor korisniku/ci @iamtrask
Marking it for later
Reply Retweet Označi sa "sviđa mi se"
Imran Khawaja 12. pro
Odgovor korisniku/ci @iamtrask
We are going through this right now and I agree 100. Figuring out what data you have and logging more is one of the first steps as well as how to store it.
Reply Retweet Označi sa "sviđa mi se"
Ayoub Benaissa 12. pro
Odgovor korisniku/ci @iamtrask
Loved rule #1
Reply Retweet Označi sa "sviđa mi se"
Sandeep Sharma 12. pro
Odgovor korisniku/ci @iamtrask
Resonates so much ☝️
Reply Retweet Označi sa "sviđa mi se"
Aman sharma 12. pro
Odgovor korisniku/ci @iamtrask
So true
Reply Retweet Označi sa "sviđa mi se"
Vaibhav Kumar Gupta 13. pro
Odgovor korisniku/ci @iamtrask
So true man ,😂
Reply Retweet Označi sa "sviđa mi se"