Interval Neural Networks: Uncertainty Scores
- URL: http://arxiv.org/abs/2003.11566v1
- Date: Wed, 25 Mar 2020 18:03:51 GMT
- Title: Interval Neural Networks: Uncertainty Scores
- Authors: Luis Oala, Cosmas Hei{\ss}, Jan Macdonald, Maximilian M\"arz, Wojciech
Samek and Gitta Kutyniok
- Abstract summary: We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs)
This interval neural network (INN) has interval valued parameters and propagates its input using interval arithmetic.
In numerical experiments on an image reconstruction task, we demonstrate the practical utility of INNs as a proxy for the prediction error.
- Score: 11.74565957328407
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a fast, non-Bayesian method for producing uncertainty scores in
the output of pre-trained deep neural networks (DNNs) using a data-driven
interval propagating network. This interval neural network (INN) has interval
valued parameters and propagates its input using interval arithmetic. The INN
produces sensible lower and upper bounds encompassing the ground truth. We
provide theoretical justification for the validity of these bounds.
Furthermore, its asymmetric uncertainty scores offer additional, directional
information beyond what Gaussian-based, symmetric variance estimation can
provide. We find that noise in the data is adequately captured by the intervals
produced with our method. In numerical experiments on an image reconstruction
task, we demonstrate the practical utility of INNs as a proxy for the
prediction error in comparison to two state-of-the-art uncertainty
quantification methods. In summary, INNs produce fast, theoretically justified
uncertainty scores for DNNs that are easy to interpret, come with added
information and pose as improved error proxies - features that may prove useful
in advancing the usability of DNNs especially in sensitive applications such as
health care.
Related papers
- Scalable Subsampling Inference for Deep Neural Networks [0.0]
A non-asymptotic error bound has been developed to measure the performance of the fully connected DNN estimator.
A non-random subsampling technique--scalable subsampling--is applied to construct a subagged' DNN estimator.
The proposed confidence/prediction intervals appear to work well in finite samples.
arXiv Detail & Related papers (2024-05-14T02:11:38Z) - Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs.
We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD.
We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
arXiv Detail & Related papers (2023-10-02T03:25:32Z) - Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification.
Our results indicate that interpolating with smoother functions leads to better generalization.
arXiv Detail & Related papers (2023-05-30T19:37:44Z) - The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural
Networks [94.63547069706459]
#DNN-Verification problem involves counting the number of input configurations of a DNN that result in a violation of a safety property.
We propose a novel approach that returns the exact count of violations.
We present experimental results on a set of safety-critical benchmarks.
arXiv Detail & Related papers (2023-01-17T18:32:01Z) - Comparative Analysis of Interval Reachability for Robust Implicit and
Feedforward Neural Networks [64.23331120621118]
We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs)
INNs are a class of implicit learning models that use implicit equations as layers.
We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
arXiv Detail & Related papers (2022-04-01T03:31:27Z) - Advantage of Deep Neural Networks for Estimating Functions with
Singularity on Hypersurfaces [23.21591478556582]
We develop a minimax rate analysis to describe the reason that deep neural networks (DNNs) perform better than other standard methods.
This study tries to fill this gap by considering the estimation for a class of non-smooth functions that have singularities on hypersurfaces.
arXiv Detail & Related papers (2020-11-04T12:51:14Z) - PAC Confidence Predictions for Deep Neural Network Classifiers [28.61937254015157]
Key challenge for deploying deep neural networks (DNNs) in safety critical settings is the need to provide rigorous ways to quantify their uncertainty.
We propose an algorithm for constructing predicted classification confidences for DNNs that comes with provable correctness guarantees.
arXiv Detail & Related papers (2020-11-02T04:09:17Z) - Frequentist Uncertainty in Recurrent Neural Networks via Blockwise
Influence Functions [121.10450359856242]
Recurrent neural networks (RNNs) are instrumental in modelling sequential and time-series data.
Existing approaches for uncertainty quantification in RNNs are based predominantly on Bayesian methods.
We develop a frequentist alternative that: (a) does not interfere with model training or compromise its accuracy, (b) applies to any RNN architecture, and (c) provides theoretical coverage guarantees on the estimated uncertainty intervals.
arXiv Detail & Related papers (2020-06-20T22:45:32Z) - GraN: An Efficient Gradient-Norm Based Detector for Adversarial and
Misclassified Examples [77.99182201815763]
Deep neural networks (DNNs) are vulnerable to adversarial examples and other data perturbations.
GraN is a time- and parameter-efficient method that is easily adaptable to any DNN.
GraN achieves state-of-the-art performance on numerous problem set-ups.
arXiv Detail & Related papers (2020-04-20T10:09:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.