So, we've learnt how to build pipelines that model strong lenses and customize them to our science case.

However, we ran into a pretty huge barrier when trying to fit complex sources. It required an unwieldy number
of non-linear parameters, and even when we included them, the results were rubbish. The non-linear parameter space
was just too complex, and even a well crafted pipeline couldn't fix the problem :(

In this chapter, we'll learn about `Pixelization`'., `Mapper`'. and inversions. These tools allow us to reconstruct the
source-galaxy's without an analytic `LightProfile`, but instead a pixel-grid. In doing so, we make no assumption about
the source's morphology, breaking the simplifying assumptions inherent to analytic `LightProfile`'. (e.g. symmetry).
Remarkably, pixels `Grid` use just a couple of non-linear parameters, meaning the 30+ non-linear parameters we required
to fit complex-sources before are going to be reduced to just 3 or 4!

In particular, you'll learn how we:

1) Pixelize our source-plane into a set of source-plane pixels that define mappings to image pixels.
2) Invert this source-plane `Pixelization`.o fit the strongly lensed source and thus reconstruct its light.
3) Apply a smoothness prior on our source reconstruction, called 'regularization', to ensure our solution is physical.
4) Apply this prior in a Bayesian framework to objectively quantify our source reconstruction's log likelihood.
5) Define a border in the source-plane to prevent pixels tracing outside the source reconstruction.
6) Can use alternative `Pixelization`'. that use irVoronoi pixels adapted to the lens's mass model.
7) Use these features in PyAutoLelns pipelines.

Sound good? I agree, so lets get on with it.