Skip to main content
added 2 characters in body
Source Link
arivero
  • 141
  • 3

One idea evading the use of explicit "mod 2" in the input could be to codify the number as a sequence of pixels, then the problem amounts to recognize ofif the segment can be split ininto two equal segments. This is a machine vision problem and that could be learned by conventional networks.

On the other extreme, if the number is stored as a float, the question reduces (or generalizes) to recognize when a float number is approximately an integer.

One idea evading the use of explicit "mod 2" in the input could be to codify the number as a sequence of pixels, then the problem amounts to recognize of the segment can be split in two equal segments. This is a machine vision problem and that could be learned by conventional networks.

On the other extreme, if the number is stored as a float, the question reduces (or generalizes) to recognize when a float number is approximately an integer.

One idea evading the use of explicit "mod 2" in the input could be to codify the number as a sequence of pixels, then the problem amounts to recognize if the segment can be split into two equal segments. This is a machine vision problem and that could be learned by conventional networks.

On the other extreme, if the number is stored as a float, the question reduces (or generalizes) to recognize when a float number is approximately an integer.

Source Link
arivero
  • 141
  • 3

One idea evading the use of explicit "mod 2" in the input could be to codify the number as a sequence of pixels, then the problem amounts to recognize of the segment can be split in two equal segments. This is a machine vision problem and that could be learned by conventional networks.

On the other extreme, if the number is stored as a float, the question reduces (or generalizes) to recognize when a float number is approximately an integer.