Dynamic Adaptive Network Intelligence

Richard Searle; Megan Bingham-Walker

Dynamic Adaptive Network Intelligence

Computation and Language 2015-11-23 v1 Machine Learning

Authors: Richard Searle , Megan Bingham-Walker

Abstract

Accurate representational learning of both the explicit and implicit relationships within data is critical to the ability of machines to perform more complex and abstract reasoning tasks. We describe the efficient weakly supervised learning of such inferences by our Dynamic Adaptive Network Intelligence (DANI) model. We report state-of-the-art results for DANI over question answering tasks in the bAbI dataset that have proved difficult for contemporary approaches to learning representation (Weston et al., 2015).

Keywords

deep neural networks neural network deep neural network

Cite

@article{arxiv.1511.06379,
  title  = {Dynamic Adaptive Network Intelligence},
  author = {Richard Searle and Megan Bingham-Walker},
  journal= {arXiv preprint arXiv:1511.06379},
  year   = {2015}
}

Comments

8 pages, 2 figures, 3 tables, ICLR 2016 conference paper submission

Related papers

View all related →