In case of no fixed infrastructure (military applications and emergency rescue operations) and we need to build a network with low cost, Wireless sensor networks (WSNs) are useful. We have no fixed routing protocol, or intrusion detection technique available for them because WSNs are dynamic in nature and individual nodes of the network are required for this to be done. Nodes are mobile in most of the applications of WSNs, so they depend on battery power and availability of limited resources which shows that power consumption is an effective research area for performing a set of tasks in WSNs. To deal with such an issue, machine learning (ML) techniques (self-learning algorithms, working without programming or human intervention) can be applied effectively according to the application requirement. In this paper, we have done comparative about several ML-based techniques for WSNs. In addition, we also analyzed ML techniques for clustering and energy harvesting. At the end, we present a summary of ML techniques for both clustering and energy harvesting with some open issues.