Четырехслойная вариация модели с 14 миллионами параметров, специально оптимизированная под датасет Penn Treebank. Использование глубоких плотных связей позволяет этому ИИ демонстрировать низкую перплексию при сохранении компактности архитектуры.
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.