This chapter focuses on supervised learning approaches that do take time into account explicitly. Times series approaches are explained as well as recurrent neural networks (including echo state networks). In addition, parameter optimization techniques that can be used to fine-tune more knowledge driven predictive temporal models (dynamical systems models) are discussed.
|Title of host publication||Machine Learning for the Quantified Self|
|Subtitle of host publication||On the Art of Learning from Sensory Data|
|Number of pages||36|
|Publication status||Published - 1 Jan 2018|
|Name||Cognitive Systems Monographs|