This tutorial adopts the Structural Similarity Index Measure (SSIM) [2] as the system metric for evaluating the performance impact of any algorithmic impairments introduced by the AI Engine implementation of the SAR BP algorithms. The SSIM metric is used to measure the similarity between two images and is often adopted as a method of predicting the perceived quality of digital images and videos in various industries. The SSIM provides a perception-based metric that captures changes in image structure that including both luminance and contrast making effects. This differs from mean squared error (MSE) or peak signal-to-noise (PSNR) that typically ignore these structural changes. The SSIM metric for two pictures will evaluate to unity when the pictures are identical (i.e., there is no degradation in the test image), and will decrease towards zero as the test image becomes corrupted. The tutorial adopts a target SSIM=0.99 as the maximum degradation to be allowed for the AI Engine implementation of the SAR BP algorithm (as is also used in [3]).