Abstract | ||
---|---|---|
For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runtime neuron activation pattern monitoring - after the standard training process, one creates a monitor by feeding the training data to the network again in order to store the neuron activation patterns in abstract form. In operation, a classification decision over an input is further supplemented by examining if a pattern similar (measured by Hamming distance) to the generated pattern is contained in the monitor. If the monitor does not contain any pattern similar to the generated pattern, it raises a warning that the decision is not based on the training data. Our experiments show that, by adjusting the similarity-threshold for activation patterns, the monitors can report a significant portion of misclassfications to be not supported by training with a small false-positive rate, when evaluated on a test set. |
Year | DOI | Venue |
---|---|---|
2018 | 10.23919/DATE.2019.8714971 | 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE) |
Keywords | Field | DocType |
runtime monitoring,neural network,dependability,autonomous driving | Training set,Hamming distance,Artificial intelligence,Artificial neural network,Mathematics,Machine learning,Test set | Journal |
Volume | ISSN | ISBN |
abs/1809.06573 | 1530-1591 | 978-1-7281-0331-0 |
Citations | PageRank | References |
3 | 0.38 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chih-Hong Cheng | 1 | 134 | 17.63 |
Georg Nührenberg | 2 | 38 | 2.56 |
Hirotoshi Yasuoka | 3 | 34 | 2.38 |