IJCAI 2020poster0 citations

Commonsense Reasoning to Guide Deep Learning for Scene Understanding (Extended Abstract)

Mohan Sridharan, Tiago Mota

Abstract

Our architecture uses non-monotonic logical reasoning with incomplete commonsense domain knowledge, and incremental inductive learning, to guide the construction of deep network models from a small number of training examples. Experimental results in the context of a robot reasoning about the partial occlusion of objects and the stability of object configurations in simulated images indicate an improvement in reliability and a reduction in computational effort in comparison with an architecture based just on deep networks.

Knowledge Representation and Reasoning: Non-monotonic Reasoning, Common-Sense ReasoningMachine Learning: Deep LearningMachine Learning: Online LearningRobotics: Robotics and Vision
BibTeX
@inproceedings{ijcai2020p661,
  title     = {Commonsense Reasoning to Guide Deep Learning for Scene Understanding (Extended Abstract)},
  author    = {Sridharan, Mohan and Mota, Tiago},
  booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on
               Artificial Intelligence, {IJCAI-20}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Christian Bessiere},
  pages     = {4760--4764},
  year      = {2020},
  month     = {7},
  note      = {Sister Conferences Best Papers},
  doi       = {10.24963/ijcai.2020/661},
  url       = {https://doi.org/10.24963/ijcai.2020/661},
}