Deep SRN for Robust Object Recognition: A Case Study with NAO Humanoid Robot

In recent years, deep neural networks have shown excellent performance for solving complex object recognition tasks. The increase in performance is achieved by corresponding increase in size and depth of the network, and addition of thousands of active neurons. This, in turn, requires training huge number of free parameters which is computationally intensive. Therefore, in this paper we propose a simultaneous recurrent network (SRN) based auto-encoder for object recognition that significantly reduces the number of trainable parameters by sharing weights in the hidden layers. The simultaneous recurrency results in an unfolding effect of the SRN through time, potentially enabling the design of an arbitrarily deep network. Furthermore, the inherent forward and recurrent connections make the SRN more biologically plausible compared to the generic feed-forward architectures. Experiments using face and character recognition tasks show that our proposed model offers better recognition performance than a generic five layer stacked auto-encoder (SAE). Finally we demonstrate the flexibility of incorporating our proposed recognition framework in a humanoid robotic platform called NAO.