2

These guys proposed droupout in 1992. The differences are that Clay and Séquin dropped only units not inputs, and that they did not normalize the learned weights after completing training. "Fault Tolerance Training Improves Generalization and Robustness" Reed D. Clay and Carlo H. Séquin [Proceedings 1992] IJCNN International Joint Conference on Neural ...


Only top voted, non community-wiki answers of a minimum length are eligible