Node co-activations as a means of error detection : Towards fault-tolerant neural networks
Myllyaho, L., Nurminen, J. K., & Mikkonen, T. (2022). Node co-activations as a means of error detection : Towards fault-tolerant neural networks. Array, 15, Article 100201. https://doi.org/10.1016/j.array.2022.100201
© 2022 the Authors
Context: Machine learning has proved an efficient tool, but the systems need tools to mitigate risks during runtime. One approach is fault tolerance: detecting and handling errors before they cause harm. Objective: This paper investigates whether rare co-activations – pairs of usually segregated nodes activating together – are indicative of problems in neural networks (NN). These could be used to detect concept drift and flagging untrustworthy predictions. Method: We trained four NNs. For each, we studied how often each pair of nodes activates together. In a separate test set, we counted how many rare co-activations occurred with each input, and grouped the inputs based on whether its classification was correct, incorrect, or whether its class was absent during training. Results: Rare co-activations are much more common in inputs from a class that was absent during training. Incorrectly classified inputs averaged a larger number of rare co-activations than correctly classified inputs, but the difference was smaller. Conclusions: As rare co-activations are more common in unprecedented inputs, they show potential for detecting concept drift. There is also some potential in detecting single inputs from untrained classes. The small difference between correctly and incorrectly predicted inputs is less promising and needs further research. ...
ISSN Search the Publication Forum2590-0056
Publication in research information system
MetadataShow full item record
Additional information about fundinghis work was funded by local authorities (“Business Finland”) under grant agreement ITEA-2019-18022-IVVES of ITEA3 programme and grant agreement ITEA-2020-20219-IML4E of ITEA4 programme .
Showing items with similar title or keywords.
Assessment of microalgae species, biomass, and distribution from spectral images using a convolution neural network Salmi, Pauliina; Calderini, Marco; Pääkkönen, Salli; Taipale, Sami; Pölönen, Ilkka (Springer Science and Business Media LLC, 2022)Effective monitoring of microalgae growth is crucial for environmental observation, while the applications of this monitoring could also be expanded to commercial and research-focused microalgae cultivation. Currently, the ...
One and Two Dimensional Convolutional Neural Networks for Seizure Detection Using EEG Signals Wang, Xiaoshuang; Ristaniemi, Tapani; Cong, Fengyu (IEEE, 2020)Deep learning for the automated detection of epileptic seizures has received much attention during recent years. In this work, one dimensional convolutional neural network (1D-CNN) and two dimensional convolutional neural ...
Estimating Tree Health Decline Caused by Ips typographus L. from UAS RGB Images Using a Deep One-Stage Object Detection Neural Network Kanerva, Heini; Honkavaara, Eija; Näsi, Roope; Hakala, Teemu; Junttila, Samuli; Karila, Kirsi; Koivumäki, Niko; Alves Oliveira, Raquel; Pelto-Arvo, Mikko; Pölönen, Ilkka; Tuviala, Johanna; Östersund, Madeleine; Lyytikäinen-Saarenmaa, Päivi (MDPI AG, 2022)Various biotic and abiotic stresses are causing decline in forest health globally. Presently, one of the major biotic stress agents in Europe is the European spruce bark beetle (Ips typographus L.) which is increasingly ...
A method for anomaly detection in hyperspectral images, using deep convolutional autoencoders Penttilä, Jeremias (2017)Menetelmä poikkeavuuksien havaitsemiseen hyperspektrikuvista käyttäen syviä konvolutiivisia autoenkoodereita. Poikkeavuuksien havaitseminen kuvista, erityisesti hyperspektraalisista kuvista, on hankalaa. Kun ongelmaan ...
One Dimensional Convolutional Neural Networks for Seizure Onset Detection Using Long-term Scalp and Intracranial EEG Wang, Xiaoshuang; Wang, Xiulin; Liu, Wenya; Chang, Zheng; Kärkkäinen, Tommi; Cong, Fengyu (Elsevier, 2021)Epileptic seizure detection using scalp electroencephalogram (sEEG) and intracranial electroencephalogram (iEEG) has attracted widespread attention in recent two decades. The accurate and rapid detection of seizures not ...