Abstract: Example deep learning systems and related methods for posterior sampling in inverse problems are described herein. An example method for training a deep learning model includes receiving a training dataset including a plurality of input/output pairs; and training a conditional generative adversarial network (cGAN) using the training dataset, where the training includes a regularization process configured to enforce consistency with a posterior mean and a posterior covariance or trace-covariance.

Abstract: An electrical signal jitter and wander measurement system (30) operates in real time and digitally controls bandwidths over which the measurements are performed. A digital phase-lock loop ("PLL") (34) includes a phase detector (44), low pass filters (48, 56), an analog-to-digital converter ("ADC") (54), a digital signal processor ("DSP") (32), a direct digital synthesizer ("DDS") (38), and a tracking oscillator (39). The phase detector receives an input signal that is compared with a signal derived from the DDS. The phase detector signal contains wander and jitter data that are filtered and digitized by the ADC. The DSP receives the data and performs a proportional integral control function to lock the PLL by digitally controlling the DDS frequency. The DDS generates a clock signal at a precise rate determined by the phase accumulation registers. The tracking oscillator locks to multiples of the DDS frequency to increase the resolution of the phase measurement.