Open djanloo opened 2 years ago
Dataset scoring using a pre-trained model appears to work properly.
Next step is using a MCMC to generate samples of increasing difficulty sampling with different probabilities for each level.
Each color has the same number of records.
Changed strategy from the one proposed in the article since a scoring function does not ensure each cluster to have enough records.
Data displays the estimates of a student trained with a prof. The student was trained for 25 epochs on the lvl 5 subset of the dataset.
Colors display the difficulty levels of the whole dataset seen by the prof network but predicted by the student.
Training over hard data makes easy data difficult (?) @luciapapalini
Keras is not able to increase the dataset length through epochs: https://github.com/tensorflow/tensorflow/issues/41571
A possible solution is writing a training loop from scratch.
@djanloo oh damn it ahah.. Is it really necessary for the curriculum?
https://arxiv.org/pdf/1904.03626.pdf