{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"67a6f354-a6da-c067-9f07-660b2ba56b39"},"source":"\n\n# Finding τ→ 3μ Using Boost, ANN\n\nThis is a real example from [CERN competition](http://www.home.cern/about/updates/2015/07/flavours-physics-join-lhcb-machine-learning-contest), hosted on [Kaggle](http://www.kaggle.com/c/flavours-of-physics) (ended Oct 2015). It asks to find τ → 3μ. Some of the labeled data are artificially made, but some sucessful learning models from the competition can be used for real detections. See this technical [CERN report](https://indico.cern.ch/event/465572/contributions/1984418/attachments/1203635/1752962/Ustyuzhanin__FoP_Summary.pdf). "},{"cell_type":"markdown","metadata":{"_cell_guid":"f15e35d8-10af-c48b-5434-cd3dfd7337a9"},"source":"I followed the method of the 1st place term, publiched on the [Kaggle blog](http://blog.kaggle.com/2015/11/30/flavour-of-physics-technical-write-up-1st-place-go-polar-bears/). The [tree boost method](https://no2147483647.wordpress.com/2014/09/17/winning-solution-of-kaggle-higgs-competition-what-a-single-model-can-do/) was used by some winning terms in the last contest, which was searching for [Higgs boson](https://www.kaggle.com/c/higgs-boson) (ended Sept 2014). Reference [\"Higgs Boson Discovery with Boosted Trees\"](http://www.jmlr.org/proceedings/papers/v42/chen14.pdf) and [\"The Higgs boson machine learning challenge\"](http://www.jmlr.org/proceedings/papers/v42/cowa14.pdf) \n\nThis 3-year-old video by David Hogg (NYU) (April 2013) reflects how much things have changed in term of the adoption of ANN in the science community.  Thanks to tensorFlow (Google), Torch (NYU, facebook). ANN is a lot easier to use now!"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"21dc6384-c1b4-d322-2094-98c93fa170c9"},"outputs":[],"source":"from IPython.display import YouTubeVideo\ns=YouTubeVideo(\"aA3qdegi8Vw\", start=564,end=642, autoplay=0,\n             theme=\"light\", color=\"white\", rel=0, showinfo=0,  height=523)\ndisplay(s)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"b069b363-65f4-8550-2e66-853777df9b1c"},"outputs":[],"source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"66bc0e01-484b-828a-0bf5-8d5f4c645316"},"outputs":[],"source":""}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.5.2"}},"nbformat":4,"nbformat_minor":0}