Optical Coherence Tomography (OCT) is a light-based, 3D imaging technique used in ophthalmology for eye disease detection. Every so often, the OCT device requires re-calibration, where setup parameters are re-evaluated to create updated correction vectors. These are critical for OCT imaging as they enable the removal of signal nonlinearities that lead to image resolution degradation. Here, we demonstrate that a nonlinear raw OCT signal can be efficiently corrected, i.e., linearised, using a neural network, without a priori knowledge of OCT device parameters. We test several training strategies for their successful performance - signal pre-processing and training dataset size variation - on both the computer-generated and experimental data.