Knowledge-augmented Column Networks: Guiding Deep Learning with Advice
Machine Learning
2019-06-05 v1 Artificial Intelligence
Machine Learning
Abstract
Recently, deep models have had considerable success in several tasks, especially with low-level representations. However, effective learning from sparse noisy samples is a major challenge in most deep models, especially in domains with structured representations. Inspired by the proven success of human guided machine learning, we propose Knowledge-augmented Column Networks, a relational deep learning framework that leverages human advice/knowledge to learn better models in presence of sparsity and systematic noise.
Cite
@article{arxiv.1906.01432,
title = {Knowledge-augmented Column Networks: Guiding Deep Learning with Advice},
author = {Mayukh Das and Devendra Singh Dhami and Yang Yu and Gautam Kunapuli and Sriraam Natarajan},
journal= {arXiv preprint arXiv:1906.01432},
year = {2019}
}
Comments
Presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA. arXiv admin note: substantial text overlap with arXiv:1904.06950