Ownership verification for neural networks is important for protecting t...
Imitation learning (IL) algorithms often rely on inverse reinforcement
l...
Neural networks (NNs) playing the role of controllers have demonstrated
...
In geographic data videos, camera movements are frequently used and comb...
This paper introduces semi-automatic data tours to aid the exploration o...
Inertial localisation is an important technique as it enables ego-motion...
Emerging multi-robot systems rely on cooperation between humans and robo...
The Weighted-Mean Subsequence Reduced (W-MSR) algorithm, the state-of-th...
We present a novel methodology for neural network backdoor attacks. Unli...
With the increment of interest in leveraging machine learning technology...
In GNSS-denied environments, aiding a vehicle's inertial navigation syst...
A misspecified reward can degrade sample efficiency and induce undesired...
Reward design is a fundamental problem in reinforcement learning (RL). A...
We present a novel methodology for repairing neural networks that use Re...
Animated transitions help viewers understand changes between related
vis...
We propose POLAR, a polynomial arithmetic framework that
leverages polyn...
This paper proposes a new approach to detecting neural Trojans on Deep N...
Deep reinforcement learning (DRL) agents are often sensitive to visual
c...
Animated visualization is becoming increasingly popular as a compelling ...
We study the problem of policy repair for learning-based control policie...
We propose a principled framework that combines adversarial training and...
Applying neural networks as controllers in dynamical systems has shown g...
An important facet of reinforcement learning (RL) has to do with how the...
Recent work has identified that classification models implemented as neu...
Apprenticeship learning (AL) is a class of "learning from demonstrations...