TL-008 · for teachers
- Groep 7 to VO
- 15–25 minutes for one animal; the new place adds about 10
- Kerndoel 21D: training an AI system
- After the worksheet Rule or Example (WS-L9-1)
- No account, nothing saved or sent
Open the activity Open the worksheet
What pupils do
What it teaches, and why it is true of real AI
How SORT-1 works
SORT-1 and real image AI
| SORT-1 | Real image AI | |
|---|---|---|
| What it compares | ||
| What it keeps | ||
| Retraining | ||
| How many examples | ||
| When nothing is close | ||
| Explaining an answer |
What we simplified, and why
What it does not teach
In class
Sources
- Cover, T. & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1).
- Ribeiro, M. T., Singh, S. & Guestrin, C. (2016). “Why should I trust you?” Explaining the predictions of any classifier. KDD 2016.
- Beery, S., Van Horn, G. & Perona, P. (2018). Recognition in terra incognita. ECCV 2018.
- Geirhos, R. et al. (2020). Shortcut learning in deep neural networks. Nature Machine Intelligence, 2.
- Nguyen, A., Yosinski, J. & Clune, J. (2015). Deep neural networks are easily fooled. CVPR 2015.
- Hendrycks, D. & Gimpel, K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. ICLR 2017.
- Walan; Dai et al.: on analogies and anthropomorphism with 11–12-year-olds. Summarized in Vonk's design philosophy.