Deep Learning’s Impact on Image Processing, Mathematics, and Humanity

Re:Deep Learning’s Impact on Image Processing, Mathematics, ... by DrNuke on Sunday May 07, 2017 @07:34AM (#14284950)

> But neither the NN nor the researcher will be able to give you a rule like: "F=(G m_1 m_2)/(r^2)" to explain the underlying reasons for the object-trajectory dynamics.

Come on, you can just fit the NN numerical outputs with Excel and come up with tentative explanations for both the underlying elegant rule and the science. The point with NN-based science being you are not left guessing much, instead retrofit the NN numerical output and build a coherent narrative with other accepted results.

[ Parent | on HN ]

Re:Deep Learning’s Impact on Image Processing, Mathematics, ... by kosmet on Sunday May 07, 2017 @08:39AM (#14285149)

Without that equation, you cannot build the rocket that goes to the moon, however.

[ Parent | on HN ]

Re:Deep Learning’s Impact on Image Processing, Mathematics, ... by DrNuke on Sunday May 07, 2017 @08:49AM (#14285195)

Feeding the retrofitted "blurred" equation to mathematicians and let them come up with tentative exact models, while being almost there already?

[ Parent | on HN ]

Re:Deep Learning’s Impact on Image Processing, Mathematics, ... by pshc on Sunday May 07, 2017 @02:04PM (#14286622)

Anything that fits within the error bars is viable if you ask me. Whatever works works.

[ Parent | on HN ]

Re:Deep Learning’s Impact on Image Processing, Mathematics, ... by sgt101 on Sunday May 07, 2017 @03:05PM (#14286978)

A lot of investors agree with you. Often they get very rich, especially if they head for the beach before the fit breaks down.

On the other hand...

[ Parent | on HN ]