# Improving Language Modeling using Densely Connected Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1707.06130 · HTML: https://mlsanity.com/paper/1707.06130/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2017.

## Built on by (most cited first, 1 of 1)

- [Residual Matrix Transformers: Scaling the Size of the Residual Stream](https://mlsanity.com/paper/2506.22696/) (2025)

## Abstract (arXiv)

In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity scores with six times fewer parameters compared to a standard stacked 2-layer LSTM model trained with dropout (Zaremba et al. 2014). In contrast with the current usage of skip connections, we show that densely connecting only a few stacked layers with skip connections already yields significant perplexity reductions.