Search Results for author:
Found 11 papers, 1 papers with code
Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders
This paper addresses the challenges of detecting anomalies in cellular networks in an interpretable way and proposes a new approach using variational autoencoders (VAEs) that learn interpretable representations of the latent space for each Key Performance Indicator (KPI) in the dataset.
Adversarial Vulnerability of Temporal Feature Networks for Object Detection
In this work, we study whether temporal feature networks for object detection are vulnerable to universal adversarial attacks.
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods.
Temporal Feature Networks for CNN based Object Detection
For reliable environment perception, the use of temporal information is essential in some situations.
Using raytracing to derive the expected performance of STELLA's SES-VIS spectrograph
The visual STELLA echelle spectrograph (SES-VIS) is a new instrument for the STELLA-II telescope at the Iza\~na observatory on Tenerife.
Instrumentation and Methods for Astrophysics
Second generation spectroscopic instrumentation for the STELLA robotic observatory
The current STELLA Echelle spectrograph (SES), which records 390nm to 870nm in one shot at a spectral resolution of 55000, will be replaced by a suite of specialized spectrographs in three spectral bands.
Instrumentation and Methods for Astrophysics
Automated Focal Loss for Image based Object Detection
With automated focal loss we introduce a new loss function which substitutes this hyperparameter by a parameter that is automatically adapted during the training progress and controls the amount of focusing on hard training examples.
Fully Convolutional Neural Networks for Dynamic Object Detection in Grid Maps
Grid maps are widely used in robotics to represent obstacles in the environment and differentiating dynamic objects from static infrastructure is essential for many practical applications.
MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving.
