The use of cascade network consisting of RBF nodes and least square error minimization block to Compressed Sensing for recovery of sparse signals is explored in this paper to improve the computation time and convergence. The proposed algorithm Radial basis function cascade network for Sparse signal Recovery (RASR) uses the L0 norm optimization, L2 least square method and feedback network model to improve the signal recovery performance and computational time over the existing ANN based CSIANN and relaxation based SL0 algorithms. The simulation results and experimental evluation of algorithm performance are presented here. © 2014 IEEE.