Overfitting and generalization is an important concept in Machine Learning as only models that generalize are interesting for general applications.
Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best.
Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets.
Modeling trajectories generated by robot joints is complex and required for high level activities like trajectory generation, clustering, and classification.
Out of distribution detection for RL is generally not well covered in the literature, and there is a lack of benchmarks for this task.
Uncertainty quantification in neural network promises to increase safety of AI systems, but it is not clear how performance might vary with the training set size.
With a Convolutional Neural Network Long Short Term Memory (CNN LSTM) on facial images an accuracy of 92% was reached on the test set.
Uncertainty in machine learning is not generally taught as general knowledge in Machine Learning course curricula.
Docking control of an autonomous underwater vehicle (AUV) is a task that is integral to achieving persistent long term autonomy.
Machine learning and neural networks are now ubiquitous in sonar perception, but it lags behind the computer vision field due to the lack of data and pre-trained models specifically for sonar images.
Application of underwater robots are on the rise, most of them are dependent on sonar for underwater vision, but the lack of strong perception capabilities limits them in this task.
It is being proven to what extent the algorithms can be used in the area of Reinforcement learning.
Around the globe, ticks are the culprit of transmitting a variety of bacterial, viral and parasitic diseases.
Evaluating difficulty and biases in machine learning models has become of extreme importance as current models are now being applied in real-world situations.
In this work, we propose the use of Black-box optimization methods to tune the prior/default box scales in Faster R-CNN and SSD, using Bayesian Optimization, SMAC, and CMA-ES.
Through our experiments, we show a significant reduction in the GFLOPS required to model uncertainty, compared to Monte Carlo DropConnect, with marginal trade-off in performance.
In this paper we introduce the Perception for Autonomous Systems (PAZ) software library.
There are multiple algorithms that solve the task in a physics engine based environment but there is no work done so far to understand if the RL algorithms can generalize across physics engines.
In this paper we show that Bayesian Neural Networks, as approximated using MC-Dropout, MC-DropConnect, or an Ensemble, are able to model the aleatoric uncertainty in facial emotion recognition, and produce output probabilities that are closer to what a human expects.
Deep learning models are extensively used in various safety critical applications.
no code implementations • 29 Oct 2019 • Matias Valdenegro-Toro, Mariela De Lucas Alvarez, Mariia Dmitrieva, Bilal Wehbe, Georgios Salavasidis, Shahab Heshmati-Alamdari, Juan F. Fuentes-Pérez, Veronika Yordanova, Klemen Istenič, Thomas Guerneve
Marine and Underwater resources are important part of the economy of many countries.
SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation.
Detecting novel objects without class information is not trivial, as it is difficult to generalize from a small training set.
Proper waste disposal and recycling is a must in any sustainable community, and in many coastal areas there is significant water pollution in the form of floating or submerged garbage.
Noncritical soft-faults and model deviations are a challenge for Fault Detection and Diagnosis (FDD) of resident Autonomous Underwater Vehicles (AUVs).
Estimating predictive uncertainty is crucial for many computer vision tasks, from image classification to autonomous driving systems.
Current robot platforms are being employed to collaborate with humans in a wide range of domestic and industrial tasks.
In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs.
In this work we develop a Convolutional Neural Network that can reliably score objectness of image windows in forward-looking sonar images and by thresholding objectness, we generate detection proposals.
In this work, we evaluate three common decisions that need to be made by a CNN designer, namely the performance of transfer learning, the effect of object/image size and the relation between training set size.
Deep Neural Networks have impressive classification performance, but this comes at the expense of significant computational resources at inference time.
Matching sonar images with high accuracy has been a problem for a long time, as sonar images are inherently hard to model due to reflections, noise and viewpoint dependence.