UCL  IRIS
Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at http://www.ucl.ac.uk/finance/research/post_award/post_award_contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
Adaptive neural trees
  • Publication Type:
    Conference
  • Authors:
    Tanno R, Arulkumaran K, Alexander DC, Criminisi A, Nori A
  • Publication date:
    15/06/2019
  • Pagination:
    10761, 10770
  • Published proceedings:
    36th International Conference on Machine Learning, ICML 2019
  • Volume:
    2019-June
  • ISBN-13:
    9781510886988
  • Status:
    Published
  • Name of conference:
    36th International Conference on Machine Learning ( ICML 2019)
  • Conference place:
    Long Beach (CA), USA
  • Conference start date:
    10/06/2019
  • Conference finish date:
    15/06/2019
Abstract
© 36th International Conference on Machine Learning, ICML 2019. All rights reserved. Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures. We unite the two via adaptive neural trees (ANTs) that incorporates representation learning into edges, routing functions and leaf nodes of a decision tree, along with a backpropagation-based training algorithm that adaptively grows the architecture from primitive modules (e.g., convolutional layers). We demonstrate that, whilst achieving competitive performance on classification and regression datasets, ANTs benefit from (i) lightweight inference via conditional computation, (ii) hierarchical separation of features useful to the task e.g. learning meaningful class associations, such as separating natural vs. man-made objects, and (iii) a mechanism to adapt the architecture to the size and complexity of the training dataset.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers
Author
Dept of Computer Science
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by