Search Results for author:
Found 10 papers, 3 papers with code
Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection
Therefore, a process that mitigates false detections is crucial for both safety and accuracy.
Informed Spectral Normalized Gaussian Processes for Trajectory Prediction
Previous work has shown that using such informative priors to regularize probabilistic deep learning (DL) models increases their performance and data-efficiency.
Explainable Bayesian Optimization
In industry, Bayesian optimization (BO) is widely applied in the human-AI collaborative parameter tuning of cyber-physical systems.
Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration
We overcome these limitations by: (1) implementing loss attenuation in EfficientDet, and proposing two deterministic methods for the exact and fast propagation of the output distribution, (2) demonstrating on the KITTI and BDD100K datasets that the predicted uncertainty is miscalibrated, and adapting two calibration methods to the localization task, and (3) investigating the correlation between aleatoric uncertainty and task-relevant error sources.
Informed Priors for Knowledge Integration in Trajectory Prediction
We show that our method outperforms both non-informed and informed learning methods, that are often used in the literature.
Efficient Utility Function Learning for Multi-Objective Parameter Optimization with Prior Knowledge
However, result elicitation in real world problems is often based on implicit and explicit expert knowledge, making it difficult to define a utility function, whereas interactive learning or post elicitation requires repeated and expensive expert involvement.
Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey
The availability of representative datasets is an essential prerequisite for many successful artificial intelligence and machine learning models.
Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings
In this work, we present a simple, yet effective, approach to verify that a CNN complies with symbolic predicate logic rules which relate visual concepts.
Preference-Based Monte Carlo Tree Search
To deal with such cases, the experimenter has to supply an additional numeric feedback signal in the form of a heuristic, which intrinsically guides the agent.
