Consistent Feature Construction with Constrained Genetic Programming for Experimental Physics
Résumé
A good feature representation is a determinant factor to achieve high performance for many machine learning algorithms in terms of classification. This is especially true for techniques that do not build complex internal representations of data (e.g. decision trees, in contrast to deep neural networks). To transform the feature space, feature construction techniques build new high-level features from the original ones. Among these techniques, Genetic Programming is a good candidate to provide interpretable features required for data analysis in high energy physics. Classically, original features or higher-level features based on physics first principles are used as inputs for training. However, physicists would benefit from an automatic and interpretable feature construction for the classification of particle collision events.Our main contribution consists in combining different aspects of Genetic Programming and applying them to feature construction for experimental physics. In particular, to be applicable to physics, dimensional consistency is enforced using grammars.
Results of experiments on three physics datasets show that the constructed features can bring a significant gain to the classification accuracy. To the best of our knowledge, it is the first time a method is proposed for interpretable feature construction with units of measurement, and that experts in high-energy physics validate the overall approach as well as the interpretability of the built features.
Mots clés
machine learning
artificial intelligence
fuzzy logic
online learning
classification
data complex internal representation
decision tree
deep neural network
neural network
feature construction technique
Genetic Programming
data analysis
high-level features
training
interpretable feature construction
particle collision event
dimensional consistency
grammar
classification accuracy
interpretability
grammar-guided genetic programming
high-energy physics
Feature extraction
Gene Regulatory Networks
Collision
Learning Algorithm
Original Features
Interpretation Of Features
Support Vector Machine
Signaling Events
Search Space
Fitness Function
Transition Probabilities
Dimensional Analysis
Numerous Features
Searches For Physics
Context-free Grammar
Subtree
New Physics
Invariant Mass
Balanced Tree
Physical Experiments
Physical Laws
Single Tree
Transition Probability Matrix
Origine | Fichiers produits par l'(les) auteur(s) |
---|