Name
Abstract | ||
|---|---|---|
Regions of high-dimensional input spaces that are underrepresented in training datasets reduce machine-learnt classifier performance, and may lead to corner cases and unwanted bias for classifiers used in decision making systems. When these regions belong to otherwise well-represented classes, their presence and negative impact are very hard to identify. We propose an approach for the detection an... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/AITEST52744.2021.00012 | 2021 IEEE International Conference on Artificial Intelligence Testing (AITest) |
Keywords | DocType | ISBN |
Training,Deep learning,Measurement,Computational modeling,Conferences,Neural networks,Decision making | Conference | 978-1-6654-3481-2 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Colin Paterson | 1 | 112 | 10.76 |
| Radu Calinescu | 2 | 905 | 63.01 |
| Chiara Picardi | 3 | 4 | 1.79 |