Return to Answer

In short, local connectivity and parameter sharing (optional).

In terms of image data,
local connectivity says only neurons within a local region should be connected together, which basically assumes that pixels nearby are correlated, and pixels far apart are independent.

Parameter sharing means that the same set of parameters applies to different regions, which assumes that local patterns are shared across the whole image.

But global parameter sharing is not necessary when, for example, the images you have are all frontal faces, in which case you'll know high level patterns (say eyes, noises) would only appear around some certain region of the images.

A paper for reference: http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf

In short, local connectivity and parameter sharing (optional).

In terms of image data,
local connectivity says only neurons within a local region should be connected together, which basically assumes that pixels nearby are correlated, and pixels far apart are independent.

Parameter sharing means that the same set of parameters applies to different regions, which assumes that local patterns are shared across the whole image.

But global parameter sharing is not necessary when, for example, the images you have are all frontal faces, in which case you'll know high level patterns (say eyes, noses) would only appear around some certain region of the images.

A paper for reference: http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf

In short, local connectivity and parameter sharing (optional).

In terms of image data,
local connectivity says only neurons within a local region should be connected together, which basically assumes that pixels nearby are correlated, and pixels far away are independent.

Parameter sharing means that the same set of parameters applies to different regions, which assumes that local patterns are shared across the whole image.

But this is not necessary when, for example, the images you have are all frontal faces, in which case you'll know some patterns only appear in some certain region of the images.

A paper for reference: http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf

In short, local connectivity and parameter sharing (optional).

In terms of image data,
local connectivity says only neurons within a local region should be connected together, which basically assumes that pixels nearby are correlated, and pixels far apart are independent.

Parameter sharing means that the same set of parameters applies to different regions, which assumes that local patterns are shared across the whole image.

But global parameter sharing is not necessary when, for example, the images you have are all frontal faces, in which case you'll know high level patterns (say eyes, noises) would only appear around some certain region of the images.

A paper for reference: http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf

In short, local connectivity and parameter sharing (optional).

In terms of image data,
local connectivity says only neurons within a local region should be connected together, which basically assumes that pixels nearby are correlated, and pixels far away are independent.

Parameter sharing means that the same set of parameters applies to different regions, which assumes that local patterns are shared among the whole image.

But this is not necessary when, for example, the images you have are all frontal faces, in which case you'll know some patterns only appear in some certain region of the images.

A paper for reference: http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf

In short, local connectivity and parameter sharing (optional).

In terms of image data,
local connectivity says only neurons within a local region should be connected together, which basically assumes that pixels nearby are correlated, and pixels far away are independent.

Parameter sharing means that the same set of parameters applies to different regions, which assumes that local patterns are shared across the whole image.

But this is not necessary when, for example, the images you have are all frontal faces, in which case you'll know some patterns only appear in some certain region of the images.

A paper for reference: http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf