This paper presents a wavelet-based recurrent fuzzy neural networks (WRFNN) trained with a stochastic search-based adaptation algorithm. A WRFNN represents a recurrent network of neurons employing wavelet functions whose outputs are combined using fuzzy rules. In this paper an earlier WRFNN model proposed by Lin, and Chin (2004), is modified by application of simultaneously perturbed stochastic approximation (SPSA) method for training the network. The model includes TSK-type fuzzy implication to compute output of each layer. The SPSA algorithm was shown to be a stable global optimization technique that is applicable to WRFNN models with demonstrated computational advantages over other optimization algorithms.