recentpopularlog in

nccollignon : ml   22

OpenCV People Counter - PyImageSearch
In this tutorial you will learn how to build a “people counter” with OpenCV and Python. Using OpenCV, we’ll count the number of people who are heading “in” or “out” of a department store in real-time.
object-tracking  python  ML 
5 days ago by nccollignon
The Shallowness of Google Translate - The Atlantic
The program uses state-of-the-art AI techniques, but simple tests show that it's a long way from real understanding.

"To me, however, such quantification of the unquantifiable reeks of pseudoscience, or, if you prefer, of nerds trying to mathematize things whose intangible, subtle, artistic nature eludes them."
language  ML  linguistics 
6 weeks ago by nccollignon
Artificial Intelligence Shows Why Atheism Is Unpopular - The Atlantic
The goal of the project is to give politicians an empirical tool that will help them assess competing policy options so they can choose the most effective one. It’s a noble idea: If leaders can use artificial intelligence to predict which policy will produce the best outcome, maybe we’ll end up with a healthier and happier world. But it’s also a dangerous idea: What’s “best” is in the eye of the beholder, after all.

“The MODRN model gives you a recipe for accelerating secularization—and it gives you a recipe for blocking it. You can use it to make everything revert to supernaturalism by messing with some of those key conditions—say, by triggering some ecological disaster. Then everything goes plunging back into pre-secularism. That keeps me up at night.”

"He cautioned that we should be skeptical about the word prediction in relation to this type of model. Opinion might be better."
religion  culture  ML  society 
7 weeks ago by nccollignon
inter-skill inter disciplinary Data Science
How to give a Data Science bootcamp to a mixed cohort of undergraduate and graduate students from a wide range of disciplines
ML  teaching  data-science  interpretable-ML  fairness 
june 2018 by nccollignon
The Lottery Ticket Hypothesis
According to the hypothesis, good performance results from lucky initialization of a subnetwork or subcomponent of the original network. Since fat networks have exponentially more component subnetworks, starting from a fatter network increases the effective number of lottery tickets, thereby increasing the chances of containing a winning ticket.
ML  deep-learning  learning 
may 2018 by nccollignon
Open NSynth Super
Open NSynth Super is an experimental physical interface for the NSynth algorithm
music  ML  DIY 
april 2018 by nccollignon

Copy this bookmark:

to read