In this paper, we have applied artificial neural network (ANN) for modeling and simulation of carbon nanotube metal-oxide-semiconductor field-effect transistors (CNT-MOSFETs). The simulation is based on ANN model which reduces the computational time while keeping the accuracy of physics-based model like non-equilibrium Green's function (NEGF) formalism. Finally, the proposed ANN model is imported into HSPICE software as a subcircuit. Results show that the ANN model is suitable to be incorporated into Spice-like tools for nanoscale circuits simulation. (C) 2009 Elsevier Ltd. All rights reserved.