Deep Extreme Feature Extraction: New MVA Method for Searching Particles in High Energy Physics

Chao Ma, Jinhui Xu, Tiancheng Hou, Bin Lan, Zhenhua Zhang


In this paper, we propose Deep Extreme Feature Extraction (DEFE), a new ensemble MVA method for searching
   channel of Higgs bosons in high energy physics. DEFE can be viewed as a deep ensemble learning scheme that
trains a strongly diverse set of neural feature learners without explicitly encouraging diversity and penalizing
correlations, which is achieved by adopting an implicit neural controller (not involved in feedforward computation)
that directly controls and distributes gradient flows from higher level deep prediction network. Such modelindependent
controller results in that every single local feature learning are used in the feature-to-output mapping
stage, avoiding the blind averaging of features. DEFE makes the ensembles ‘deep’ in the sense which allows deep
post-process of these features that tries to learn to select and abstract the ensemble of neural feature learners. Based
on the construction and approximation of the so-called extreme selection region, the DEFE model is able to be
trained efficiently, and extract discriminative features from multiple angles and dimensions, hence the improvement
of the selection region of searching new particles in HEP can be achieved. With the application of this model, the
selection regions full of signal process can be obtained through the training of a miniature collision events set. In
comparison of the Classic Deep Neural Network, DEFE shows a state-of-the-art performance: the error rate has
decreased by about 37%, the accuracy has broken through 90% for the first time along with the discovery
significance which has reached a standard deviation of 6.0 . Experimental data shows that, DEFE is able to train an
ensemble of discriminative feature learners that boosts the over-performance of final prediction. Furthermore, among
high-level features, there are still some important patterns that are unidentified by DNN and are independent from
low-level features, while DEFE is able to identify these significant patterns more effectively and efficiently.

Full Text:



  • There are currently no refbacks.