6

Google is not the company that filed the application. If you examine the Legal Events, the application for this patent was originally filed by a Canadian startup company affiliated with the University of Toronto: ASSIGNMENT OF ASSIGNORS INTEREST ASSIGNOR:THE GOVERNING COUNCIL OF THE UNIVERSITY OF TORONTO Effective date: 20130311 Owner name: DNNRESEARCH INC.,...


2

Yes, you may (at least for now) because the patent is only at the application phase, which means it is not yet enforceable. However, if the patent is granted, then it is retroactive to the Priority Date, which could potentially make you (your institution) liable for damages. I would not expect the WIPO application to succeed in its current form because ...


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 ...


1

I would suggest that any good book on Model Theory, such as those by Kreisel, Krivine, and W. Hodges, from the 1970s through 1990s, would show that the size of the proof space is in general inversely related to the size of the model space. This does not directly address neural nets. However the positing of alternatives and then pruning them is an old and ...


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