paper-with-me

홈 › Papers

Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice

2019-04-15 · Mayukh Das, Yang Yu, Devendra Singh Dhami, Gautam Kunapuli, Sriraam Natarajan

Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctly capture such domain structure and interactions, but may still be prone to sub-optimal learning from sparse and noisy samples. Inspired by the success of human-advice guided learning in AI, especially in data-scarce domains, we propose Knowledge-augmented Column Networks that leverage human advice/knowledge for better learning with noisy/sparse samples. Our experiments demonstrate that our approach leads to either superior overall performance or faster convergence (i.e., both effective and efficient).

📄 PDF Abstract BibTeX arXiv:1904.06950

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Human-Guided Column Networks: Augmenting Deep Learning with Advice

2019-05-01 · ICLR 2019 5 · Mayukh Das, Yang Yu, Devendra Singh Dhami, Gautam Kunapuli 외

While extremely successful in several applications, especially with low-level representations; sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most…

Deep Learning

Knowledge-augmented Column Networks: Guiding Deep Learning with Advice

2019-05-31 · Mayukh Das, Devendra Singh Dhami, Yang Yu, Gautam Kunapuli 외

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 …

BIG-bench Machine LearningDeep Learning

Grounding Human-to-Vehicle Advice for Self-driving Vehicles

2019-11-16 · CVPR 2019 6 · Jinkyu Kim, Teruhisa Misu, Yi-Ting Chen, Ashish Tawari 외

Recent success suggests that deep neural control networks are likely to be a key component of self-driving vehicles. These networks are trained on large datasets to imitate human actions, but they lack semantic understan…

ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning

2019-02-12 · Harris Chan, Yuhuai Wu, Jamie Kiros, Sanja Fidler 외

Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling t…

Multi-Goal Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

ACTRCE: Augmenting Experience via Teacher’s Advice

2019-05-01 · ICLR 2019 5 · Yuhuai Wu, Harris Chan, Jamie Kiros, Sanja Fidler 외

Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failure experience to a successful one by relabeling …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)