Deep Sequential Neural Networks

Neural Networks sequentially build high-level features through their successive layers. We propose a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process. The resulting model is structured according to a DAG like architecture, so that a path from the root to a leaf node defines a sequence of transformations. The model is thus able to process data with different characteristics through specific sequences of local transformations, increasing the expression power of this model w.r.t a classical deep neural network. The learning algorithm is inspired from policy gradient techniques coming from the reinforcement learning domain and is used here instead of the classical back-propagation based gradient descent techniques.

Authors

• Ludovic Denoyer
• Patrick Gallinari

Keywords

• reinforcement learning
• deep learning
• policy gradient