Probabilistic programming languages are built to harness the predictive power of probability distributions. Instead of making them a feature, they use these distributions as primitives with their own set of operands that allow for the creation of stochastic control flows. Since the real world is full of uncertainty, this type of thinking is useful to help build better AI systems. I'll use Uber's newly released Pyro tool to demonstrate how they work.
Code for this video (with coding challenge):
https://github.com/llSourcell/an_intro_to_probabilistic_programming
Shannon's winning code:
https://github.com/DecentricCorp/Coval-Unspecified-Ml-Blockchain
Please Subscribe! And like. And comment. That's what keeps me going.
Want more inspiration & education? Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology
More learning resources:
https://media.nips.cc/Conferences/2015/tutorialslides/wood-nips-probabilistic-programming-tutorial-2015.pdf
http://probabilistic-programming.org/wiki/Home
https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
https://www.oreilly.com/ideas/probabilistic-programming
https://www.oreilly.com/learning/probabilistic-programming-from-scratch
http://pyro.ai/
Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/
And please support me on Patreon:
https://www.patreon.com/user?u=3191693 Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
