Figure 2 displays diagrams of deep learning methods and how they can be used to explore new scenarios. Figure 2a) shows a flow diagram of a simplified scheme for a stable diffusion (deep learning) network able to generate new pictures starting from text input. The flow diagram includes the input, data encoder, diffusion, conditioning, denoising and final decoder used to generate the picture. Figure 2b displays a flow diagram for a deep learning method used to create a DL-ROM architecture for a Disk Resonating Gyroscope (DRG). It includes the input (voltage and other device settings), a data encoder, a deep feedforward neural network and finally a decoder used to create the DL-ROM architecture