Machine learning is a popular topic in data analysis and modeling. Many different machine learning algorithms have been developed and implemented in a variety of programming languages over the past 20 years. In this article, we first provide an overview of machine learning and clarify its difference from statistical inference. Then, we review Scikit-learn, a machine learning package in the Python programming language that is widely used in data science. The Scikit-learn package includes implementations of a comprehensive list of machine learning methods under unified data and modeling procedure conventions, making it a convenient toolkit for educational and behavior statisticians.

We use the abundance and weak lensing mass measurements of the SDSS maxBCG cluster catalog to simultaneously constrain cosmology and the richness-mass relation of the clusters. Assuming a flat ΛCDM cosmology, we find σ 8 (Ω m /0.25) 0.41 = 0.832 ± 0.033 after marginalization over all systematics. In common with previous studies, our error budget is dominated by systematic uncertainties, the primary two being the absolute mass scale of the weak lensing masses of the maxBCG clusters, and uncertainty in the scatter of the richness-mass relation. Our constraints are fully consistent with the WMAP five-year data, and in a joint analysis we find σ 8 = 0.807 ± 0.020 and Ω m = 0.265 ± 0.016, an improvement of nearly a factor of two relative to WMAP5 alone. Our results are also in excellent agreement with and comparable in precision to the latest cosmological constraints from X-ray cluster abundances. The remarkable consistency among these results demonstrates that cluster abundance constraints are not only tight but also robust, and highlight the power of optically-selected cluster samples to produce precision constraints on cosmological parameters.

We present a novel situational task that integrates collaborative problem solving behavior with testing in a science domain. Participants engage in discourse, which is used to evaluate their collaborative skills. We present initial experiments for automatic classification of such discourse, using a novel classification schema. Considerable accuracy is achieved with just lexical features. A speech-act classifier, trained on out-of-domain data, can also be helpful.

No abstract

The Dark Energy Survey Collaboration is building the Dark Energy Camera (DECam), a 3 square degree, 520 Megapixel CCD camera which will be mounted on the Blanco 4-meter telescope at CTIO. DECam will be used to perform the 5000 sq. deg. Dark Energy Survey with 30% of the telescope time over a 5 year period. During the remainder of the time, and after the survey, DECam will be available as a community instrument. Construction of DECam is well underway. Integration and testing of the major system components has already begun at Fermilab and the collaborating institutions.