Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Koch, Anita De Mello"'
Autor:
Hill, William, Liu, Ireton, Koch, Anita De Mello, Harvey, Damion, Kumar, Nishanth, Konidaris, George, James, Steven
We propose a new benchmark for planning tasks based on the Minecraft game. Our benchmark contains 45 tasks overall, but also provides support for creating both propositional and numeric instances of new Minecraft tasks automatically. We benchmark num
Externí odkaz:
http://arxiv.org/abs/2312.12891
Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization group is a compelling example of a problem which has very few paramete
Externí odkaz:
http://arxiv.org/abs/2012.03531
Publikováno v:
Phys. Rev. E 102, 013307 (2020)
A theory explaining how deep learning works is yet to be developed. Previous work suggests that deep learning performs a coarse graining, similar in spirit to the renormalization group (RG). This idea has been explored in the setting of a local (near
Externí odkaz:
http://arxiv.org/abs/2002.02664