Efficient Service Level Agreements (SLA) management and anticipation of Service Level Objectives (SLO) breaches become mandatory to guarantee the fulfilled services in the context of softwarized networks. In this paper, using Artificial Neural Networks, we design, specify and evaluate a framework for cognitive SLA enforcement of networking services involving Virtualized Network Functions (VNFs) and SDN controllers. A proof of concept, a testbed description and an extensive performance evaluation assess the validation of the proposed framework