ANN in heavy meson decays – Machine learning for HEP

Semileptonic decays of heavy mesons with artificial neural networks

paper by Cody M. Grant, Ayesh Gunawardana, and Alexey A Petrov

Project abstract: Experimental checks of the second row unitarity of the Cabibbo-Kobayashi-Maskawa matrix involve extractions of the matrix element $V_{cd}$, which may be obtained from semileptonic decay rates of D to \pi. These decay rates are proportional to hadronic form factors which parameterize how the quark $c \to d$ transition is realized in $D \to \pi$ meson decays. The form factors can not yet be analytically computed over the whole range of available momentum transfer $q^2$, but can be parameterized with a varying degree of model dependency. We propose using artificial neural networks trained from experimental pseudo-data to predict the shape of these form factors with a prescribed uncertainty. We comment on the parameters of several commonly-used model parameterizations of semileptonic form factors. We extract shape parameters and use unitarity to bound the form factor at a given $q^2$, which then allows us to bound the CKM matrix element $|V_{cd}|$.

Graphs and some other relevant files

Our averaged ANN result for the differential decay rate plotted against the experimental measurement. The purple data points are the experimental data. The black and cyan curves are the average value and one standard deviation, respectively, from the output of our averaged ANN.

ANN fits for $\left|V_{cd} F_+ (q^2)\right|$ plotted against the three models described in the text. The black and cyan curves are the average value and one standard deviation, respectively, from the output of our neural network. The dotted red curve is the simple pole model. The dot-dashed green curve is the modified pole model. The dashed magenta curve is the BZ model. The purple data points are calculated from the experimental data.

Other files: ANN structure

Python code for the neural net training (zip file with data): code

Additional questions? Please contact the authors: Cody M. Grant, Ayesh Gunawardana, and Alexey A Petrov