Saliency methods are frequently used to explain Deep Neural Network-base...
State-of-the-art object detectors are treated as black boxes due to thei...
Trusting the predictions of deep learning models in safety critical sett...
Safety-critical applications like autonomous driving use Deep Neural Net...
Increasingly high-stakes decisions are made using neural networks in ord...
Overfitting and generalization is an important concept in Machine Learni...
Self-supervised learning has proved to be a powerful approach to learn i...
Neural networks are ubiquitous in many tasks, but trusting their predict...
Modeling trajectories generated by robot joints is complex and required ...
Reinforcement Learning (RL) based solutions are being adopted in a varie...
Uncertainty quantification in neural network promises to increase safety...
Robots are becoming everyday devices, increasing their interaction with
...
Uncertainty in machine learning is not generally taught as general knowl...
Accurate detection and segmentation of marine debris is important for ke...
Docking control of an autonomous underwater vehicle (AUV) is a task that...
Machine learning and neural networks are now ubiquitous in sonar percept...
Application of underwater robots are on the rise, most of them are depen...
Neural networks are used for many real world applications, but often the...
Deep Reinforcement Learning (DRL) connects the classic Reinforcement Lea...
Evaluating difficulty and biases in machine learning models has become o...
Around the globe, ticks are the culprit of transmitting a variety of
bac...
Object detectors have improved considerably in the last years by using
a...
In this paper we introduce the Perception for Autonomous Systems (PAZ)
s...
Reinforcement learning (RL) algorithms should learn as much as possible ...
Estimating epistemic uncertainty of models used in low-latency applicati...
Facial emotion recognition is the task to classify human emotions in fac...
Deep learning models are extensively used in various safety critical
app...
Marine and Underwater resources are important part of the economy of man...
Fast estimates of model uncertainty are required for many robust robotic...
Detecting novel objects without class information is not trivial, as it ...
Garbage and waste disposal is one of the biggest challenges currently fa...
We propose a modification to Perlin noise which use computable hash func...
Noncritical soft-faults and model deviations are a challenge for Fault
D...
Current robot platforms are being employed to collaborate with humans in...
In this paper we propose an implement a general convolutional neural net...
Convolutional Neural Networks (CNN) have revolutionized perception for c...
Forward-looking sonar can capture high resolution images of underwater
s...
Deep Neural Networks have impressive classification performance, but thi...
Matching sonar images with high accuracy has been a problem for a long t...