Many perception tasks can be cast as ‘inverse problems’ where the input signal is the outcome of a causal process and perception is to invert that process. For example in visual object perception, the image is caused by an object and perception is to infer which object gave rise to that image. Following an analysis-by-synthesis approach, modelling the forward and causal direction of the data generation process is a natural way to capture the underlying scene structure, which typically leads to broader generalisation and better sample efficiency. Such a forward model can be applied to solve the inverse problem (inferring the scene structure from an input image) using Bayes rule, for example. This workflow stands in contrast to common approaches in deep learning, where typically one first defines a task, and then optimises a deep model end-to-end to solve it. In this workshop we propose to revisit ideas from the generative approach and advocate for learning-based analysis-by-synthesis methods for perception and inference. In addition, we pose the question of how ideas from these research areas can be combined with and complement modern deep learning practices.