Heavy Flavour Data Mining workshop

Session

Data Science Applications

19 Feb 2016, 09:00

Y16 G15 (University of Zurich, Irchel Campus)

Conveners

Data Science Applications

• Tim Head (Ecole Polytechnique Federale de Lausanne (CH))

Data Science Applications: Data Science Applications

• Marc Olivier Bettler (CERN)

4. Classifier output calibration to probability

Tatiana Likhomanenko (National Research Centre Kurchatov Institute (RU))

19/02/2016, 09:00

2. Classifiers for centrality determination in proton-nucleus and nucleus-nucleus collisions

Igor Altsybeev (St. Petersburg State University (RU))

19/02/2016, 09:40

Centrality, as a geometrical property of the collision, is crucial for the physical interpretation of proton-nucleus and nucleus-nucleus experimental data. However, it cannot be directly accessed in event-by-event data analysis. Contemporary methods of the centrality estimation in A-A and p-A collisions usually rely on a single detector (either on the signal in zero-degree calorimeters or on...

6. Data Fusion Surogate Modeling on Incomplete Factorial Design of Experiments

Prof. Eugene Burnaev (IITP)

19/02/2016, 10:00

This work concerns a construction of surrogate models for a specific aerodynamic data base. This data base is generally available from wind tunnel testing or from CFD aerodynamic simulations and contains aerodynamic coefficients for different flight conditions and configurations (such as Mach number, angle-of-attack, vehicle configuration angle) encountered over different space vehicles...

11. Mathematics of Big Data

Prof. Dmitry Vetrov (Skoltech, Yandex School of Data Analysis, Higher School of Economics)

19/02/2016, 11:00

12. Efficient Elastic Net Regularization for Sparse Linear Models in the Multilabel Setting

Mr Zachary Chase Lipton (University of California, Amazon)

19/02/2016, 11:40

22. Optimized Methods to Apply Neural Networks in HEP

Lev Dudko (M.V. Lomonosov Moscow State University (RU))

19/02/2016, 12:10

Different steps of NN application in HEP are considered. Possible optimization methods for each of the steps are discussed. The proposed methods were applied for the single top quark analysis in CMS and corresponding examples are presented in the talk.

25. Automatic Tuning of Hyperparameters

Mr Alexander Fonarev (Skoltech)

20/02/2016, 09:00

The training process of a machine learning algorithm includes tuning of hyperparameters, such as the regularization coefficient of a linear model or the depth of a decision tree. Unfortunately, it usually is conducted manually, what is very expensive to be done on a regular basis. Moreover, the growing number of hyperparameters in modern complex machine learning methods additionally...

28. Deep Learning for event reconstruction

Amir Farbin (University of Texas at Arlington (US))

20/02/2016, 09:40

27. Fast multimodal clustering: searching for optimal patterns

Dr Dmitry Ignatov (HSE)

20/02/2016, 10:40

In Machine Learning, we usually deal with object-attribute tables. However, underlying objects may have other modalities than attributes only. For instance, an object may have a certain attribute only under specific conditions. The real examples came from gene expression data, where a gene can be active (expressed) in particular situations at a certain moment of time, implying ternary relation...

18. Summary of open space discussions

Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))

20/02/2016, 11:20