Adaptation is the neural networks property that a neural network system should provide. Due to the challenge of high complexity and poor generalization of different models of neural network, many researchers were motivated to work in the field of adaptation in neural networks. Adaptation helps neural networks to generalize and adapt the data easily. Adaptive neural network framework is a collection of techniques in which structure of the network is adapted during the training according to a given problem. In this paper, we review the different adaptation technique of the neural network. These adaptation techniques include- structural adaptation, functional adaptation and training parameters or weight adaptation. To achieve architectural and functional adaptation many pruning, constructive and cascading algorithm were proposed in the literature by many researchers. To attain the functional adaptation the slope of the sigmoidal function is adapted during training and to satisfy the adaptive property of neural network weight adaptation is performed by every neural network model that results in better convergence and good generalization