Recurrent Neural Network with Adaptive Gating Timescales Mechanisms for Language and Action Learning

Libo Zhao (Corresponding Author), Junpei Zhong

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review


Inspired by the neurons’ differences in membrane time-scales, the multiple timescale recurrent neural network model (MTRNN) adopts the hierarchical architecture with increasing time-scales from bottom to top layers. Based on this idea, the recent adaptive and continuous time recurrent neural networks (ACTRNN) and the gated adaptive continuous time recurrent neural network (GACTRNN) develop the novel learning mechanism on the time-scales. In this paper, we test the performance of GACTRNN using the dataset obtained from a real-world humanoid robot’s object manipulation experiment. By using trainable timescale parameters with the gating mechanism, it can be observed that the GACTRNN can better learn the temporal characteristics of the sequences. Besides, to eliminate the effects of parameters’ overgrowing with a large data-set, we improve the GACTRNN model and propose the MATRNN model. In this model, the sigmoid function is used instead of exponential function. We compare the performances of the CTRNN, GACTRNN and MATRNN models, and find that the GACTRNN and MATRNN models perform better than the CTRNN model with the large-scale dataset. By visualizing the timescales adapting in the training process, we also qualitatively show that the MATRNN model performs better than the GACTRNN model in terms of stability with the dataset.

Original languageEnglish
Title of host publicationNeural Information Processing - 28th International Conference, ICONIP 2021, Proceedings
EditorsTeddy Mantoro, Minho Lee, Media Anugerah Ayu, Kok Wai Wong, Achmad Nizar Hidayanto
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages9
ISBN (Print)9783030923099
Publication statusPublished - 2 Dec 2021
Event28th International Conference on Neural Information Processing, ICONIP 2021 - Virtual, Online
Duration: 8 Dec 202112 Dec 2021

Publication series

NameCommunications in Computer and Information Science
Volume1517 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


Conference28th International Conference on Neural Information Processing, ICONIP 2021
CityVirtual, Online


  • Adaptive timescale
  • Developmental robotics
  • Membrane time constants
  • Recurrent neural network

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics


Dive into the research topics of 'Recurrent Neural Network with Adaptive Gating Timescales Mechanisms for Language and Action Learning'. Together they form a unique fingerprint.

Cite this