The paper presents an extension multi-laye r p erceptron model that is capable of representing and reasoning propositional know ledge base. An extended version of propositional calculus is developed, and its some properties is discussed. Formulas of the extended calculus can be expressed in the extension multi-layer perceptron. Naturally, semantic deduction of prop ositional knowledge base can be implement by the extension multi-layer perceptr on, and by learning, an unknown formula set can be found. The paper presents an extension multi-laye rp erceptron model that is capable of representing and reasoning propositional know ledge base. An extended version of propositional calculus is developed, and some of the properties are discussed. Formulas of the extended calculus can be expressed in the extension Naturally, semantic deduction of propositional knowledge base can be implement by the extension multi-layer perceptr on, and by learning, an unknown formula set can be found.