Re:Are deep neural networks dramatically overfitted? (2019)
by reader_mode on Monday April 05, 2021 @08:18AM
(#26698024)
> We don't generally equip models with robotic interfaces to train in 3d before benchmarking them on ImageNet.
Don't they train models using 3D rendering and simulations ? We have relatively realistic simulations for various scenarios - having a learned model that could make inferences based on those complex simulations sounds like a win.
Re:Are deep neural networks dramatically overfitted? (2019)
by logicchains on Monday April 05, 2021 @07:37AM
(#26697722)
>Like trying to learn from images instead of the 3d world. Humans learn to distinguish between objects in a 3-dimensional space using sight and interaction. This learning generalizably transfers to recognition in 2 dimensions.
If we use human "comprehension" as a reference point, then the relevant point of comparison should be the understanding a human can develop given the same inputs.
Re:Are deep neural networks dramatically overfitted? (2019)
by wongarsu on Monday April 05, 2021 @10:19AM
(#26699288)
Sure, but how do you measure that? How do we figure out how much understanding a human can develop from only ever seeing 2d pictures, without any movement or interaction with a 3d world?
Most ML problems are things humans are quite good at and have a lot of context to draw from.
Re:Are deep neural networks dramatically overfitted? (2019)
by fractionalhare on Monday April 05, 2021 @07:40AM
(#26697742)
Sure. But again, practically speaking, that isn't the reality of how we learn. The commenter wasn't refuting Kolmogorov complexity. They're just saying it's an extremely limited way of viewing the problem. Useful sure, but insufficient.
They're making a practical distinction that you generally don't have access to the actual thing in an empirical format for which compression will achieve true learning. Instead you have access to training data which represents, let's say, a projection of the actual thing in a smaller space with fewer dimensions.
Like trying to learn from images instead of the 3d world. Humans learn to distinguish between objects in a 3-dimensional space using sight and interaction. This learning generalizably transfers to recognition in 2 dimensions. We don't generally equip models with robotic interfaces to train in 3d before benchmarking them on ImageNet.