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

The abstraction tasks are challenging for multi- modal sequences as theyrequire a deeper semantic understanding and a novel text generation for thedata. Although the recurrent neural networks (RNN) can be used to model thecontext of the time-sequences, in most cases the long-term dependencies ofmulti-modal data make the back-propagation through time training of RNN tend tovanish in the time domain. Recently, inspired from Multiple Time-scaleRecurrent Neural Network (MTRNN), an extension of Gated Recurrent Unit (GRU),called Multiple Time-scale Gated Recurrent Unit (MTGRU), has been proposed tolearn the long-term dependencies in natural language processing. Particularlyit is also able to accomplish the abstraction task for paragraphs given thatthe time constants are well defined. In this paper, we compare the MTRNN andMTGRU in terms of its learning performances as well as their abstractionrepresentation on higher level (with a slower neural activation). This was doneby conducting two studies based on a smaller data- set (two-dimension timesequences from non-linear functions) and a relatively large data-set(43-dimension time sequences from iCub manipulation tasks with multi-modaldata). We conclude that gated recurrent mechanisms may be necessary forlearning long-term dependencies in large dimension multi-modal data-sets (e.g.learning of robot manipulation), even when natural language commands was notinvolved. But for smaller learning tasks with simple time-sequences, genericversion of recurrent models, such as MTRNN, were sufficient to accomplish theabstraction task.

Toward Abstraction from Multi-modal Data: Empirical Studies on Multiple Time-scale Recurrent Models