Complex Systems Studies
2.43K subscribers
1.55K photos
125 videos
116 files
4.54K links
What's up in Complexity Science?!
Check out here:

@ComplexSys

#complexity #complex_systems #networks #network_science

📨 Contact us: @carimi
Download Telegram
pymc_learn is focused on bringing probabilistic machine learning to non specialists. Read this draft paper for more details: https://t.co/Xgeacf1VPN #ProbabilisticModeling #MachineLearning @pymc_devs @scikit_learn https://t.co/F2BZT1mu0s
Why Excel Users Should Learn Python : https://t.co/XwF1IbqYy0 #abdsc #BigData #Analytics #DataScientists #Coding

So, check out this "Complete Tutorial To Learn #DataScience With #Python From Scratch": https://t.co/PfQ5gfcke5 #MachineLearning #AI #Algorithms
This algorithm browses Wikipedia to auto-generate textbooks https://t.co/bExALBY6u0

#DeepLearning #MachineLearning #AI #DataScience
A mathematical model from 103 years ago predicted something that was seen for the first time today: a #black_hole.

#MachineLearning could never do that: it needs observations to model anything. This is a major weak-point of ML. Let's fix it.

A stark contrast between Machine Learning vs other forms of mathematical modeling is that ML models often don't model extreme corner cases very well, because #data in those areas is rare. Gathering data in important areas is as important a skill as building fancy neural networks.

Sadly, too often, using extreme inputs to a model is more useful: e.g. by modeling physics of levers on light objects with short levers, we then built very long levers to lift extremely heavy things. Instead, ML is better suited at modeling everyday phenomena with complex models.

https://twitter.com/Reza_Zadeh/status/1053771110410375168?s=19