Generating Component-based Supervised Learning Programs From Crowdsourced Examples Cambronero, Jose; Rinard, Martin We present CrowdLearn, a new system that processes an existing corpus of crowdsourced machine learning programs to learn how to generate effective pipelines for solving supervised machine learning problems. CrowdLearn uses a probabilistic model of program likelihood, conditioned on the current sequence of pipeline components and on the characteristics of the input data to the next component in the pipeline, to predict candidate pipelines. Our results highlight the effectiveness of this technique in leveraging existing crowdsourced programs to generate pipelines that work well on a range of supervised learning problems.
from Computer Science and Artificial Intelligence Lab (CSAIL) http://ift.tt/2D6PgYG
dimanche 24 décembre 2017
Generating Component-based Supervised Learning Programs From Crowdsourced Examples
mardi 12 décembre 2017
Acceleration Profiles and Processing Methods for Parabolic Flight: Supplemental Material
Acceleration Profiles and Processing Methods for Parabolic Flight: Supplemental Material Carr, Christopher E.; Bryan, Noelle C.; Saboda, Kendall; Bhattaru, Srinivasa Aditya; Ruvkun, Gary; Zuber, Maria T. Supplemental material (dataset, code) for the manuscript: Carr CE, Bryan NC, Saboda K, Bhattaru SA, Ruvkun G, Zuber MT. Acceleration Profiles and Processing Methods for Parabolic Flight. doi: TBD. The dataset includes: 3-axis DC accelerometer (>400 Hz), piezoelectric accelerometer (5 kHz), and low-frequency pressure and temperature (1 Hz) data. In addition, MATLAB analysis code is provided to implement the methodology described in the paper at http://ift.tt/2kpADrN. Dataset contains raw and calibrated data for a parabolic flight as well as a short lab recording used to confirm calibration accuracy (1.0 GB ZIP).
from Department of Earth, Atmospheric, and Planetary Sciences http://ift.tt/2jTbbLw
mardi 5 décembre 2017
A comprehensive approach towards the phylogeny and evolution of cervidae
Heckeberg, Nicola Susanne (2017): A comprehensive approach towards the phylogeny and evolution of cervidae. Dissertation, LMU München: Fakultät für Geowissenschaften
from Elektronische Hochschulschriften der LMU München: http://ift.tt/2ipUt5C
