# tfl.lattice_lib.laplacian_regularizer

Returns Laplacian regularization loss for `Lattice` layer.

Laplacian regularizer penalizes the difference between adjacent vertices in multi-cell lattice (see publication).

Consider a 3 x 2 lattice with weights `w`:

``````w-----w-----w
|        |        |
|        |        |
w-----w-----w
``````

where the number at each node represents the weight index. In this case, the laplacian regularizer is defined as:

``````l1 * (|w - w| + |w - w| +
|w - w| + |w - w|) +
l1 * (|w - w| + |w - w| + |w - w|) +

l2 * ((w - w)^2 + (w - w)^2 +
(w - w)^2 + (w - w)^2) +
l2 * ((w - w)^2 + (w - w)^2 + (w - w)^2)
``````

`weights` `Lattice` weights tensor of shape: `(prod(lattice_sizes), units)`.
`lattice_sizes` List or tuple of integers which represents lattice sizes.
`l1` l1 regularization amount. Either single float or list or tuple of floats to specify different regularization amount per dimension.
`l2` l2 regularization amount. Either single float or list or tuple of floats to specify different regularization amount per dimension.

Laplacian regularization loss.

[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"必要な情報がない" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"複雑すぎる / 手順が多すぎる" },{ "type": "thumb-down", "id": "outOfDate", "label":"最新ではない" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Samples / code issue" },{ "type": "thumb-down", "id": "otherDown", "label":"その他" }]
[{ "type": "thumb-up", "id": "easyToUnderstand", "label":"わかりやすい" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"問題の解決に役立った" },{ "type": "thumb-up", "id": "otherUp", "label":"その他" }]