[ABE-L] Main trends at this year’s NIPS: the merging of Bayesian statistics with deep learning.

[Hedibert Lopes]

Bom dia,

Aparentemente, e naturalmente, a maior comunidade de Machine Learning do mundo finalmente percebeu que “Bayesian statistical learning” é o caminho a se seguir.  

O trecho (abaixo) que está relacionado a minha insistência em dizer que “aprendizagem estatística” (Bayesian statistical learning) eleva “machine learning” (aprendizado de máquina) ao status de modelagem e tratamento apropriado de incertezas, algo pouco familiar, até recentemente, aos “machine learners”

Vale citar o livro que gosto muito do Kevin P. Murphy “Machine Learning: A Probabilistic Perspective”.   Conheço menos o livro do David Barber “Bayesian Reasoning and Machine Learning”.

Abs,
Hedibert

“Mr Smiroldo does put his finger on one of the main trends at this year’s NIPS: the merging of Bayesian statistics with deep learning. Instead of algorithms presenting deterministic “yes” or “no” results to queries, new systems are able to offer up more probabilistic inferences about the world. This is particularly useful for Mercedes-Benz, which needs driverless cars that can handle tricky situations. Instead of an algorithm simply determining if an object in the road is a pedestrian or a plastic bag, a system using Bayesian learning offers a more nuanced view that will allow AI systems to handle uncertainty better.”



The Economist | Algorithm is gonna get you 
http://www.economist.com/news/science-and-technology/21732081-machine-learnings-big-event-all-buzz-ais-big-shindig?frsc=dg%7Ce

-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <https://lists.ime.usp.br/archives/abe/attachments/20171208/8d2dd57b/attachment.html>