In addition to the three learning paradigms introduced in the previous three chapters, several learning quasi-paradigms have emerged in the machine learning community. The so-called quasi-paradigm is referring each one of the quasi-paradigms having certain characteristics for a paradigm but not yet forming completely an independent paradigm. In this chapter we select some noteworthy learning quasi-paradigms to introduce, namely, ensemble learning, meta-learning, transfer learning, self-supervised learning, and n-shot learning including one-shot, few-shot, and zero-shot learning.