This paper presents the design of an artificial neural network (ANN) based intelligent pressure sensor to measure pressure in the range 0-100 psig with high accuracy and temperature compensation. A capacitive pressure sensor detects the applied pressure by means of elastic deflection of diaphragm. A Modified Schering Bridge Signal Conditioning Circuit (MSB-SCC) converts the change in capacitance of the sensor into an equivalent voltage. The effect of change in environmental conditions, especially effect of ambient temperature on the pressure sensor and component drifts, stray effects associated with MSB-SCC introduce nonlinearity and cross-sensitivity errors in the output readout. The ANN trained with Levenberg-Marquardt (LM) algorithm incorporates the intelligence into sensor signal conditioning circuit through a microcontroller unit to reduce the nonlinearity effects and compensate the cross-sensitivity errors.The LM algorithm shows better performance in terms of the linearity error in comparison with Broyden-Fletcher-Goldfarb-Shanno (BFGS) and the Scaled Conjugate Gradient (SCG) algorithms. The proposed method is experimentally verified at various temperatures and it provides voltage readout within ±0.8% of full-scale reading over a range of temperature variations from 10°C to 35°C. © School of Engineering, Taylor’s University.