Increasing survival rates in severe illnesses and traumatic injuries can lead to an increase in the number of disabled people with central nervous system (CNS) damages. Motor training after CNS damage is an important part of neurorehabilitation. It can partially reverse the loss of cortical representation after lesion thanks to neuroplasticity. Patients may regain some motor functions in the months following damage due both to spontaneous recovery and physical therapy interventions targeted at further improvement of function. The neural correlates of motor training after CNS damage have been investigated in animals with motor cortex lesions and in humans using fMRI, TMS, etc. However it is hard to fully explain all mechanisms of neuroplasticity. One of ways to increase knowledge and clinical experience is developing of computational models. To refine a lot of hypotheses existing in the area of CNS neuroplasticity there are useful computational models of lesions and following recovery due to neurorehabilitation. The models based on artificial neural networks are novel solution, but in some cases can provide effectivity and biological plausibility. This article aims at investigating the extent to which the available opportunities are being exploited, including models as a first step in the development of adaptive and cost-effective rehabilitation methods tailored to individuals with CNS deficits.