**Título:** Índice de Igualdade e Aprendizado em Redes Neurofuzzy Recorrentes Aplicado a Previsão de Séries Macroeconômicas

**Autores:** Ballini, Rosangela; Gomide, Fernando

**Resumo:** A novel learning algorithm for recurrent fuzzy neural network is introduced in this paper. The core of the learning algorithm uses equality index as the performance measure to be optimized. Equality index is especially important because its properties reflect the fuzzy set-based structure of the neural network and nature of learning. Equality indexes are strongly tied with the properties of the fuzzy set theory and logic-based techniques. The neural network recurrent topology is built with fuzzy neuron units and performs neural processing consistent with fuzzy system methodology. Therefore neural processing and learning are fully embodied within fuzzy set theory. The performance recurrent fuzzy neural network is verified via example of learning sequences. Computational experiments show that the recurrent fuzzy neural model achieves high performance in terms of approximation capability, memory requeriments, and learning speed.

**Palavras-chave:**

**Páginas:** 6

**Código DOI:** 10.21528/CBRN2003-069

**Artigo em PDF:** 6CBRN_069.PDF

**Arquivo BibTex:** 6CBRN_069.bib