Deep neural networks have demonstrated excellent performances in many real-world applications. Unfortunately, they may show Clever Hans-like behaviour (making use of …
K Beckh, S Müller, M Jakobs, V Toborek, H Tan… - arXiv preprint arXiv …, 2021 - arxiv.org
This survey presents an overview of integrating prior knowledge into machine learning systems in order to improve explainability. The complexity of machine learning models has …
The wide adoption of Machine Learning (ML) technologies has created a growing demand for people who can train ML models. Some advocated the term" machine teacher''to refer to …
S Teso, K Kersting - Proceedings of the 2019 AAAI/ACM Conference on …, 2019 - dl.acm.org
Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind predictions and queries is important …
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function …
CG Myers - Academy of Management review, 2018 - journals.aom.org
Vicarious learning—individual learning that occurs through being exposed to and making meaning from another's experience—has long been recognized as a driver of individual …
M Tucker, E Novoseller, C Kann, Y Sui… - … on robotics and …, 2020 - ieeexplore.ieee.org
This paper presents a personalized gait optimization framework for lower-body exoskeletons. Rather than optimizing numerical objectives such as the mechanical cost of …
When a robot performs a task next to a human, physical interaction is inevitable: the human might push, pull, twist, or guide the robot. The state of the art treats these interactions as …
While constraints are ubiquitous in artificial intelligence and constraints are also commonly used in machine learning and data mining, the problem of learning constraints from …