We introduce a hybrid recognition/reconstruction architecture that is suitable for recognition of images degraded by various forms of blur. This architecture includes an ensemble of feed-forward networks each of which is constrained to reconstruct the inputs in addition to performing classification. The strength of the constraints is controlled by a regularization parameter. Networks are trained on original as well as Gaussian-blurred images, so as to achieve higher robustness to different blur operators. Face recognition is used to demonstrate the proposed method and results are compared to those of classical unconstrained feed-forward architectures. In addition, the effect of state-of-the-art restoration methods is demonstrated and it is shown that image restoration with the proposed hybrid architecture leads to the best and most robust results under various forms of blur.