recentpopularlog in

pierredv : explanation   6

Introduction to Local Interpretable Model-Agnostic Explanations (LIME) - O'Reilly Media
A technique to explain the predictions of any machine learning classifier.
By Marco Tulio RibeiroSameer SinghCarlos Guestrin
August 12, 2016

"In "Why Should I Trust You?" Explaining the Predictions of Any Classifier, a joint work by Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin (to appear in ACM's Conference on Knowledge Discovery and Data Mining -- KDD2016), we explore precisely the question of trust and explanations."

"Because we want to be model-agnostic, what we can do to learn the behavior of the underlying model is to perturb the input and see how the predictions change."

"We used LIME to explain a myriad of classifiers (such as random forests, support vector machines (SVM), and neural networks) in the text and image domains."
ML  AI  neural-nets  explanation  prediction 
september 2018 by pierredv
Quantum purity: How the big picture banishes weirdness - New Scientist 11 April 2015
Based on work started by Lucien Hardy. “When I look at quantum theory, I see something that’s akin to the ad hoc nature of Kepler’s laws of planetary motion and of Lorentz transformations,” says Hardy. “What we need is some deeper set of principles.” Could it be that all the messy uncertainty of the quantum world simply stems from lack of information: making a measurement of a mixed state without having access to the larger pure state of which it is part? “The idea is not to get rid of the weirdness, but to explain it as a logical consequence of basic principles,” Chiribella says. "Fivefold way" per D’Ariano, Chiribella, Perinotti: five fundamental principles that must apply to any physical system to make a sensible measurement of it 1 Causality 2 Distinguishability 3 Composition 4 Compression 5 Tomography
NewScientist  explanation  quantum-mechanics  physics  *  information-theory 
august 2015 by pierredv
18 Complicated Scientific Ideas Explained In Plain English - Business Insider
The comic inspired Theo Anderson, a geneticist who supports accessible science education, to build a text editor that would force the user to write with only the 1000 most frequent words. He then invited scientists to describe what they do using the editor
explanation  writing  science 
february 2013 by pierredv
Trees Come 'From Out Of The Air,' Said Nobel Laureate Richard Feynman. Really? : Krulwich Wonders... : NPR
Ask one of the greatest scientists of the 20th century a simple question, and his answer makes me go, "What? What did he just say?"

The question was: Where do trees come from?
science  video  explanation  Feynman  ** 
october 2012 by pierredv
The secret of science's success - opinion - David Deutsch - 26 April 2011 - New Scientist
Laying out the argument that science is more than empiricism. Sustained progress requires alternating guesswork and criticism. But one also needs "testable explanations" (not testable predictions), that are derived from "hard-to-vary theories" essay based on Deutsch's new book, The Beginning of Infinity
books  science  explanation  philosophy  NewScientist  ** 
june 2011 by pierredv

Copy this bookmark:

to read