Data scientists and developers can use the Amazon SageMaker fully managed machine learning service to build and train machine learning (ML) models, and then directly deploy them into a production-ready hosted environment.
Why I Indent My Code 8 Spaces
Roger Peng ** 2018/07/27
Thoughts On Machine Learning Accuracy
This blog shares some brief thoughts on machine learning accuracy and bias.
First Data Project? Go Tandem! (AVISIA at Play)
If you were going skydiving for the first time, you’d definitely want to go tandem and be attached to an experienced instructor to make sure things go right. And for data projects, while the risk isn’t life-and-death, it’s still high for a lot of businesses who are facing increased competition, rising costs and dipping revenues - so why not partner up?
ACL 2018 Highlights： Understanding Representations and Evaluation in More Challenging Settings
Data Notes： Winning Solutions of Kaggle Competitions
Winners, tumors, and avocados: Enjoy these new, intriguing, and overlooked datasets and kernels.
Awesome MCMC animation site by Chi Feng! On Github!
Parsimonious principle vs integration over all uncertainties
tl;dr If you have bad models, bad priors or bad inference choose the simplest possible model. If you have good models, good priors, good inference, use the most elaborate model for predictions. To make interpretation easier you may use a smaller model with similar predictive performance as the most elaborate model.
How to think about an accelerating string of research successes?
While reading this post by Seth Frey on famous scientists who couldn’t let go of bad ideas, I followed a link to this post by David Gorski from 2010 entitled, “Luc Montagnier: The Nobel disease strikes again.” The quick story is that Montagnier endorsed some dubious theories. Here’s Gorski:
Grazing and Calculus Revisited
 |
One of the great things about writing a blog is the occasional interesting email I receive from some of my readers.Recently I was contact by Trung ‘Average’ Phan, a very talented member of Princeton’s Physics department who pointed out a couple of updates/corrections in previous articles I’d written. In the article Grazing and Calculus, which is about how to make the largest possible rectilinear grazing area for a goat using just straight sections of fence, I was comparing the possible field sizes that could be obtained by using the straight sides of a square barn as part of the perimeter of the field. |