English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, memory-augmented neural networks(MANNs) have shown promisingpower to enhance the memory ability of neural networks for sequentialprocessing tasks. However, previous MANNs suffer from complex memory addressingmechanism, making them relatively hard to train and causing computationaloverheads. Moreover, many of them reuse the classical RNN structure such asLSTM for memory processing, causing inefficient exploitations of memoryinformation. In this paper, we introduce a novel MANN, the Auto-addressing andRecurrent Memory Integrating Network (ARMIN) to address these issues. The ARMINonly utilizes hidden state ht for automatic memory addressing, and uses a novelRNN cell for refined integration of memory information. Empirical results on avariety of experiments demonstrate that the ARMIN is more light-weight andefficient compared to existing memory networks. Moreover, we demonstrate thatthe ARMIN can achieve much lower computational overhead than vanilla LSTM whilekeeping similar performances. Codes are available on github.com/zoharli/armin.

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network