N
Nuri Cingillioglu
Researcher at Imperial College London
Publications - 8
Citations - 27
Nuri Cingillioglu is an academic researcher from Imperial College London. The author has contributed to research in topics: Logical reasoning & Artificial neural network. The author has an hindex of 3, co-authored 7 publications receiving 21 citations.
Papers
More filters
Posted Content
DeepLogic: Towards End-to-End Differentiable Logical Reasoning
TL;DR: In this article, symbolic logic programs at a character level are learned to be represented in a high-dimensional vector space using RNN-based iterative neural networks to perform reasoning.
Posted Content
DeepLogic: End-to-End Logical Reasoning.
TL;DR: This article defines 12 classes of logic programs that exemplify increased level of complexity of the inference process (multi-hop and default reasoning) and shows that the proposed Neural Inference Network (NIN) passes 10 out of the 12 tasks.
Proceedings Article
DeepLogic: Towards End-to-End Differentiable Logical Reasoning.
TL;DR: In this article, symbolic logic programs at a character level are learned to be represented in a high-dimensional vector space using RNN-based iterative neural networks to perform reasoning.
Proceedings Article
Learning Invariants through Soft Unification
TL;DR: Unification Networks as mentioned in this paper ) is an end-to-end differentiable neural network approach capable of lifting examples into invariants and using those invariants to solve a given task.
Posted Content
HySTER: A Hybrid Spatio-Temporal Event Reasoner.
TL;DR: HySTER as mentioned in this paper is a hybrid spatio-temporal event reasoner that leverages the strength of deep learning methods to extract information from video frames with the reasoning capabilities and explainability of symbolic artificial intelligence in an answer set programming framework.