No abstract

The number of neurons in hidden layers of Feedforward Neural Networks is very relative to their learning ability and generalization ability. The Iterative Pruning(IP) algorithm spends much time computing adjusting factors of the remaining weights. So the Improved Iterative Pruning(IIP) algorithm is put forward, which adopts dividing blocks strategy and uses the Generalized Inverse Matrix(GIM) algorithm to replace the Conjugate Gradient Precondition Normal Equation(CGPCNE) algorithm for updating the remaining weights. The IIP algorithm is applied in the hidden layers of Feedforward Neural Networks to simplify their structures in a great extent and preserve a good level of accuracy and generalization ability without retraining after pruning. The simulation results demonstrate the effectiveness and the feasibility of the algorithm.

No abstract

No abstract