Deep Learning can equip robots with a new level of skill by utilizing insights from neuroscience.
These new developments have impact on various types of robots, from companion robots to driver assistance in semi-autonomous vehicles. Deep Learning can enable unprecedented quality of results in tasks such as object detection, localization, communication and behavior learning.
Training deep neural networks typically requires GPU workstations or high-performance computing servers. It may require huge amounts of data or innovative training schemes. These issues indicate only some of the special challenges when utilizing deep networks in robotics.
Within this context the topics of this thematic special issue include, but are not limited to:
# applications of deep learning
# software and hardware systems
# data acquisition for deep learning
# neural information processing systems
# deep learning training schemes and paradigms
# GPU computing for deep learning
# software engineering for deep learning
# neural networks on low powered devices
# human robot interaction and communication
# cognitive, developmental and evolutionary robotics
Authors are requested to submit their papers to the Topical Issue complying the general scope of the journal. The submitted papers will undergo the standard peer-review process before they can be accepted. Notification of acceptance will be communicated as we progress with the review process.
The deadline for submission is 15 DECEMBER 2018, but individual papers will be reviewed and published online on an ongoing basis.
Contributors to the Topical Issue will benefit from:
+ indexation in SCOPUS
+ NO submission and publication FEES
+ fair and constructive peer review provided by experts in the field
+ no space constraints
+ convenient, web-based paper submission and tracking system - Editorial Manager
+ free language assistance for authors from non-English speaking regions
+ fast online publication upon completing the publishing process (continuous publication model)
+ better visibility due to Open Access
+ long-term preservation of the content (articles archived in Portico)
+ extensive post-publication promotion for selected papers
Stephan K. Chalup, University of Newcastle, Australia
Alan D. Blair, University of New South Wales, Australia
Aydan M. Erkmen, Middle East Technical University, Ankara, Turkey
Alessandro Di Nuovo, Sheffield Hallam University, UK