Camilleri, D. and Prescott, T. orcid.org/0000-0003-4927-5390 (2017) Analysing the limitations of deep learning for developmental robotics. In: Biomimetic and Biohybrid Systems. 6th International Conference, Living Machines 2017, July 26–28, 2017, Stanford, CA, USA. Lecture Notes in Computer Science (10384 ). Springer , pp. 86-94. ISBN 9783319635361
Abstract
Deep learning is a powerful approach to machine learning however its inherent disadvantages leave much to be desired in the pursuit of the perfect learning machine. This paper outlines the multiple disadvantages of deep learning and offers a view into the implications to solving these problems and how this would affect the state of the art not only in developmental learning but also in real world applications.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © Springer International Publishing AG 2017. This is an author produced version of a paper subsequently published in Lecture Notes in Computer Science. Uploaded in accordance with the publisher's self-archiving policy. The final publication is available at Springer via https://doi.org/10.1007/978-3-319-63537-8_8. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) The University of Sheffield > Faculty of Science (Sheffield) > Department of Psychology (Sheffield) |
Funding Information: | Funder Grant number European Commission 720270 (HBP SGA1) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 18 Aug 2017 10:12 |
Last Modified: | 22 Mar 2018 20:24 |
Published Version: | https://doi.org/10.1007/978-3-319-63537-8_8 |
Status: | Published |
Publisher: | Springer |
Series Name: | Lecture Notes in Computer Science |
Refereed: | Yes |
Identification Number: | 10.1007/978-3-319-63537-8_8 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:120261 |