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

Developmental psychology and neuroimaging research identified a close linkbetween numbers and fingers, which can boost the initial number knowledge inchildren. Recent evidence shows that a simulation of the children's embodiedstrategies can improve the machine intelligence too. This article explores theapplication of embodied strategies to convolutional neural network models inthe context of developmental neuro-robotics, where the training information islikely to be gradually acquired while operating rather than being abundant andfully available as the classical machine learning scenarios. The experimentalanalyses show that the proprioceptive information from the robot fingers canimprove network accuracy in the recognition of handwritten Arabic digits whentraining examples and epochs are few. This result is comparable to brainimaging and longitudinal studies with young children. In conclusion, thesefindings also support the relevance of the embodiment in the case of artificialagents' training and show a possible way for the humanization of the learningprocess, where the robotic body can express the internal processes ofartificial intelligence making it more understandable for humans.

A Developmental Neuro-Robotics Approach for Boosting the Recognition of Handwritten Digits