Cascading photonic reservoirs with deep neural networks increases computational performance

Deep neural networks (DNNs) have been successfully applied to solving complex problems, such as pattern recognition when analyzing big data. To achieve a good computational performance, these networks are often designed such that they contain many trainable parameters. However, this often makes DNNs very energy-intensive and time-consuming to train. In this work, we propose to use a photonic reservoir to preprocess the input data instead of directly injecting it into the DNN. A photonic reservoir consists of a network of many randomly connected nodes which do not need to be trained. It forms an additional layer to the deep neural network and can transform the input data into a state in a higher dimensional state-space. This allows us to reduce the size of the DNN, and in turn, the amount of training required for the DNN, due to less backpropagation being performed for a smaller DNN.