Deep Sequential Neural Network

TL;DR

This paper introduces a novel neural network architecture where each layer selects from multiple candidate mappings via a sequential decision process, enabling more flexible data processing and increased expressive power compared to traditional multilayer networks.

Contribution

It proposes a new DAG-structured neural network model with local transformations and a reinforcement learning-based training algorithm, differing from classical backpropagation methods.

Findings

Demonstrates improved performance on various datasets.

Shows increased model flexibility and expressiveness.

Validates the effectiveness of reinforcement learning for training.

Abstract

Neural Networks sequentially build high-level features through their successive layers. We propose here 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. Instead of considering global transformations, like in classical multilayer networks, this model allows us for learning a set of local transformations. It is thus able to process data with different characteristics through specific sequences of such local transformations, increasing the expression power of this model w.r.t a classical multilayered 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. Experiments on different datasets show the relevance of this approach.