Deterministic and probabilistic deep learning models for inverse design of broadband acoustic cloak

Concealing an object from incoming waves (light and/or sound) remained science fiction for a long time due to the absence of wave-shielding materials in nature. Yet, invention artificial and new physical principles optical sound wave manipulation translated this abstract concept into reality by making acoustically invisible. Here, we present notion machine learning-driven acoustic cloak demonstrate example such with multilayered core-shell configuration. Importantly, develop deterministic probabilistic deep learning models based on autoencoder-like neural network structure retrieve structural material properties cloaking shell surrounding that suppresses scattering broad spectral range, as if it was not there. The model enhances generalization ability design procedure uncovers sensitivity parameters response practical implementation. This proposal opens up avenues expedite intelligent devices tailored offers feasible solution inverse problems.