datascience   17795

« earlier    

The Scikit-Learn Tutorial Series — Mastering and with :…
DataScience  MachineLearning  Python  from twitter_favs
7 hours ago by rukku
WFIRST Exoplanet Data Challenges
WFIRST Exoplanet Data Challenge #1
Welcome to the WFIRST Exoplanets Data Challenge #1! The WFIRST mission is currently in Phase A, during which time the science and instrument performance requirements will be defined for exoplanet imaging and spectroscopy. In order to provide the project with the best possible inputs before the end of Phase A in 2017, we are seeking participation from teams with spectral retrieval expertise through the WFIRST exoplanets data challenge.

The Challenge will run from August 2016 to March 2017. The 2016 Challenge consists of a blind spectral retrieval exercise using simulated, extracted spectra for several known RV and/or hypothetical discovery exoplanets. The spectra will NOT need to be extracted from simulated IFS data. Instead, we will explore the impact of signal-to-noise ratio and spectral resolution on the detection/measurement of atmospheric abundances and other planet properties. Even with that relatively simple goal, we expect the Challenge to be non-trivial!

Sample spectra from Data Challenge #1. Shown are simulated spectra for three of the four exoplanets at the highest signal-to-noise and resolving power (top row) and at the lowest signal-to-noise and resolving power (bottom row)..

Incentive to Participate: While defining the first space-borne exoplanet imaging mission is hopefully its own compelling reason for doing this, to make this a little more fun the WFIRST Data Challenge Science Investigation Team is offering travel expenses and registration costs for one person on each team that fully completes the Challenge (all four planets, all SNR and R values, all requested retrieval outputs) to attend the 2017 WFIRST Science Meeting, or another exoplanets meeting of his/her choice (up to $2000).

Participation in the Challenge is contingent upon acceptance of terms which will be included in the invitation email.
If you wish to participate, please register and you will be sent an invitation.

If you have questions, please forward them to Margaret Turnbull and David Ciardi through the "Contact" link above.

We look forward to working with you this Fall!
17 hours ago by HM0880
process using Deep Learning to analyze MNIST digit recognition
DataScience  from twitter_favs
yesterday by neuralmarket

« earlier    

related tags

abdsc  ai  algorithms  analytics  article  artificial-intelligence  artificialintelligence  bash  bayesian  berkeley  bestpractices  bi  bigdata  bitcoin  blockchain  blogpost  blogs  books  cars  cheatsheet  cio  clojure  cloud  cloudcomputing  collaboration  commandline  comprehension  cx  data  dataviz  deep-learning  deeplearning  dev  directory  docker  ebook  education  fake  fintech  ggplot2  hadoop  interactive  iot  job  journalism  jupyter  kaggle  learn  learning  machine-learning  machinelearning  methodo  mind  ml  neuralnetworks  news  norvig  opensource  optimization  orms  os  panel  philosophy  portal  productivity  programming  psychology  python  r  random  reference  research  researchdata  rstats  scala  science  scraping  selfimprovement  shell  sightings  significance  sklearn  softwaretesting  sql  statistics  tables  tech  tensorlang  theme  tips  toolkit  travel  tutorial  tutorials  ubuntu  uxdesign  vancouver  visualanalytics  visualization  wisdom  workflow  yelp  zeppelin 

Copy this bookmark: