Feedforward Sequential Memory Neural Networks without Recurrent Feedback Article Swipe

MAKE IMPACT

Shiliang Zhang , Hui Jiang , Si Wei , Li-Rong Dai · YOU? · · 2015 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1510.02693

We introduce a new structure for memory neural networks, called feedforward sequential memory networks (FSMN), which can learn long-term dependency without using recurrent feedback. The proposed FSMN is a standard feedforward neural networks equipped with learnable sequential memory blocks in the hidden layers. In this work, we have applied FSMN to several language modeling (LM) tasks. Experimental results have shown that the memory blocks in FSMN can learn effective representations of long history. Experiments have shown that FSMN based language models can significantly outperform not only feedforward neural network (FNN) based LMs but also the popular recurrent neural network (RNN) LMs.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/1510.02693

PDF

https://arxiv.org/pdf/1510.02693

OA Status

green

Cited By

20

References

17

Related Works

10

OpenAlex ID

https://openalex.org/W1920942766

Raw OpenAlex JSON