5 papers
Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning
Minghe Gao, Juncheng Li, Yuze Lin +15
We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, le…
Temporal-contextual Event Learning for Pedestrian Crossing Intent Prediction
Hongbin Liang, Hezhe Qiao, Wei Huang +3
Ensuring the safety of vulnerable road users through accurate prediction of pedestrian crossing intention (PCI) plays a crucial role in the context of autonomous and assisted drivi…
A game method for improving the interpretability of convolution neural network
Jinwei Zhao, Qizhou Wang, Fuqiang Zhang +7
Real artificial intelligence always has been focused on by many machine learning researchers, especially in the area of deep learning. However deep neural network is hard to be und…
How far from automatically interpreting deep learning
Jinwei Zhao, Qizhou Wang, Yufei Wang +2
In recent years, deep learning researchers have focused on how to find the interpretability behind deep learning models. However, today cognitive competence of human has not comple…
How to improve the interpretability of kernel learning
Jinwei Zhao, Qizhou Wang, Yufei Wang +3
In recent years, machine learning researchers have focused on methods to construct flexible and interpretable prediction models. However, an interpretability evaluation, a relation…