When we practice a movement, human brains creates a motor memory of it. These memories are formed and stored in the brain as representations which allows us to perform familiar tasks faster than new movements. From a developmental robotics and embodied artificial agent perspective it could be also beneficial to exploit the concept of these motor representations in the form of spatial-temporal motion priors for complex, full-body motion synthesis. Encoding such priors in neural networks in a form of inductive biases inherit essential spatio-temporality aspect of human motion. In our current work we examine and compare recent approaches for capturing spatial and temporal dependencies with machine learning algorithms that are used to model human motion.