Statistical process monitoring of artificial neural networks
Not on the map. Why?
Abstract (arXiv)
The rapid advancement of models based on artificial intelligence demands innovative monitoring techniques which can operate in real time with low computational costs. In machine learning, especially if we consider artificial neural networks (ANNs), the models are often trained in a supervised manner. Consequently, the learned relationship between the input and the output must remain valid during the model's deployment. If this stationarity assumption holds, we can conclude that the ANN provides accurate predictions. Otherwise, the retraining or rebuilding of the model is required. We propose considering the latent feature representation of the data (called "embedding") generated by the ANN to determine the time when the data stream starts being nonstationary. In particular, we monitor embeddings by applying multivariate control charts based on the data depth calculation and normalized ranks. The performance of the introduced method is compared with benchmark approaches for various ANN architectures and different underlying data formats.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 143 references that are in the map. First posted on arXiv 15 Sep 2022.
Builds on
24 of 143 references.
References · 24
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
- 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
- 2015An Introduction to Convolutional Neural Networkscited by 510
- 2020Learning under Concept Drift: A Reviewcited by 470
- 2017Deep Layer Aggregationcited by 436
- 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
- 2018A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decaycited by 223
- 2019Addressing Failure Prediction by Learning Model Confidencecited by 183
- 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
12 more
- 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
- 2015A Primer on Neural Network Models for Natural Language Processingcited by 75
- 2021Understanding Softmax Confidence and Uncertaintycited by 62
- 2018On the Dimensionality of Word Embeddingcited by 46
- 2020A Framework to Learn with Interpretationcited by 23
- 2020Choosing among notions of multivariate depth statisticscited by 14
- 2021Data Twinningcited by 10
- 2020Concept Drift Monitoring and Diagnostics of Supervised Learning Models via Score Vectorscited by 9
- 2016Sparse Sliced Inverse Regression Via Lassocited by 8
- 2016Depth and depth-based classification with R-package ddalphacited by 5
- 2019Toward a Better Monitoring Statistic for Profile Monitoring via Variational Autoencoderscited by 2
- 2021Distributionally robust halfspace depthcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.