Fuzzy logic programs are a useful framework for imperfect knowledge representation and reasoning using the formalism of logic programming. Nevertheless, there is the need for modeling adaptation of fuzzy logic programs, so that machine learning techniques, such as connectionist-based learning, can be applied. Weighted fuzzy logic programs bring fuzzy logic programs and connectionist models closer together by associating a significant weight with each atom in the body of a fuzzy rule: by exploiting the existence of the weights, it is possible to construct a connectionist model that reflects the exact structure of a weighted fuzzy logic program. Based on the connectionist representation, we first define the weight adaptation problem as the task of adapting the weights of the rules of a weighted fuzzy logic program, so that they fit best a set of training data, and then we develop a subgradient descent learning algorithm for the connectionist model that allows us to obtain an approximate solution for the weight adaptation problem.