Fig. 6: Sketch of Calo4pQVAE.
From: Conditioned quantum-assisted deep generative surrogate for particle-calorimeter interactions
a The input data is composed of the energy per voxel, x and the incident energy, e. During training, the data flows through the encoder and gets encoded into a latent space, z, it then goes through the decoder and generates a reconstruction of the voxels per energy, while the incident energy is the label of the event and conditions the encoder and decoder. The decoder outputs the activation vector, χ and the hits vector ξ. The model is trained via the optimization of the mean squared error between the input shower and the reconstructed shower, the binary cross entropy (hit loss) between the hits vector and the input shower and the Kulbach–Liebler divergence which is composed by the entropy of the encoded sample and the restricted Boltzmann machine log-likelihood. b For inference, we sample from the RBM or the QA conditioned to an incident energy, afterwards the sample goes through the decoder to generate a shower.
