Batch-normalized Recurrent Highway Networks

TL;DR

This paper introduces batch normalized recurrent highway networks that improve gradient flow control, leading to faster convergence and better performance in image captioning tasks compared to traditional models.

Contribution

The paper proposes a novel batch normalization technique within recurrent highway networks to enhance gradient control and network convergence.

Findings

Faster convergence of the proposed model.

Improved performance on MSCOCO image captioning.

Outperforms traditional LSTM and RHN models.

Abstract

Gradient control plays an important role in feed-forward networks applied to various computer vision tasks. Previous work has shown that Recurrent Highway Networks minimize the problem of vanishing or exploding gradients. They achieve this by setting the eigenvalues of the temporal Jacobian to 1 across the time steps. In this work, batch normalized recurrent highway networks are proposed to control the gradient flow in an improved way for network convergence. Specifically, the introduced model can be formed by batch normalizing the inputs at each recurrence loop. The proposed model is tested on an image captioning task using MSCOCO dataset. Experimental results indicate that the batch normalized recurrent highway networks converge faster and performs better compared with the traditional LSTM and RHN based models.