Neural State-Space Models: Empirical Evaluation of Uncertainty Quantification
Effective quantification of uncertainty is an essential and still missing step towards a greater adoption of deep-learning approaches in different applications, including mission-critical ones. In particular, investigations on the predictive uncertainty of deep-learning models describing non-linear dynamical systems are very limited to date. This paper is aimed at filling this gap and presents preliminary results on uncertainty quantification for system identification with neural state-space models. We frame the learning problem in a Bayesian probabilistic setting and obtain posterior distributions for the neural network's weights and outputs through approximate inference techniques. Based on the posterior, we construct credible intervals on the outputs and define a surprise index which can effectively diagnose usage of the model in a potentially dangerous out-of-distribution regime, where predictions cannot be trusted.
Code (1)
Tasks
Deep LearningState Space ModelsUncertainty QuantificationSimilar Papers 제목 키워드 기반
Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models
Model-Based Reinforcement Learning distinguishes between physical dynamics models operating on proprioceptive inputs and latent dynamics models operating on high-dimensional image observations. A prominent latent approac…
Reinforcement LearningEmpirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures
Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model's uncertainty is evaluated …
Deep LearningUncertainty QuantificationUncertainty in Extreme Multi-label Classification
Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small la…
ClassificationDecision MakingExtreme Multi-Label ClassificationMulti-Label Classification+4Label-wise Aleatoric and Epistemic Uncertainty Quantification
We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows uncertainty to be quantified at the individu…
Decision MakingUncertainty QuantificationOld Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learning
One of the key obstacles in traditional deep learning is the reduction in model transparency caused by increasingly intricate model functions, which can lead to problems such as overfitting and excessive confidence in pr…
Quantum Machine Learning