mlx/docs/build/doctrees/python/nn/losses.doctree

<EFBFBD><05><>H<00>sphinx.addnodes<65><73>document<6E><74><EFBFBD>)<29><>}<7D>(<28>	rawsource<63><65><00><>children<65>]<5D>(<28>docutils.nodes<65><73>target<65><74><EFBFBD>)<29><>}<7D>(h<05>.. _losses:<3A>h]<5D><>
attributes<EFBFBD>}<7D>(<28>ids<64>]<5D><>classes<65>]<5D><>names<65>]<5D><>dupnames<65>]<5D><>backrefs<66>]<5D><>refid<69><64>losses<65>u<EFBFBD>tagname<6D>h
<EFBFBD>line<6E>K
<01>parent<6E>h<03>	_document<6E>h<03>source<63><65>9/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst<73>ubh	<09>section<6F><6E><EFBFBD>)<29><>}<7D>(hhh]<5D>(h	<09>title<6C><65><EFBFBD>)<29><>}<7D>(h<05>Loss Functions<6E>h]<5D>h	<09>Text<78><74><EFBFBD><EFBFBD>Loss Functions<6E><73><EFBFBD><EFBFBD><EFBFBD>}<7D>(h h+h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhh)h h&h!hh"h#hKubh<00>tabular_col_spec<65><63><EFBFBD>)<29><>}<7D>(hhh]<5D>h}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>spec<65><63>\X{1}{2}\X{1}{2}<7D>uhh;h h&h!hh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hNub<75>sphinx.ext.autosummary<72><79>autosummary_table<6C><65><EFBFBD>)<29><>}<7D>(hX_



binary_cross_entropy(logits, targets[, ...])

Computes the binary cross entropy loss.

cosine_similarity_loss(x1, x2[, axis, eps, ...])

Computes the cosine similarity between the two inputs.

cross_entropy(logits, targets[, weights, ...])

Computes the cross entropy loss.

hinge_loss(inputs, targets[, reduction])

Computes the hinge loss between inputs and targets.

huber_loss(inputs, targets[, delta, reduction])

Computes the Huber loss between inputs and targets.

kl_div_loss(inputs, targets[, axis, reduction])

Computes the Kullback-Leibler divergence loss.

l1_loss(predictions, targets[, reduction])

Computes the L1 loss.

log_cosh_loss(inputs, targets[, reduction])

Computes the log cosh loss between inputs and targets.

mse_loss(predictions, targets[, reduction])

Computes the mean squared error loss.

nll_loss(inputs, targets[, axis, reduction])

Computes the negative log likelihood loss.

smooth_l1_loss(predictions, targets[, beta, ...])

Computes the smooth L1 loss.

triplet_loss(anchors, positives, negatives)

Computes the triplet loss for a set of anchor, positive, and negative samples.<2E>h]<5D>h	<09>table<6C><65><EFBFBD>)<29><>}<7D>(hhh]<5D>h	<09>tgroup<75><70><EFBFBD>)<29><>}<7D>(hhh]<5D>(h	<09>colspec<65><63><EFBFBD>)<29><>}<7D>(hhh]<5D>h}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>colwidth<74>K
uhhZh hWubh[)<29><>}<7D>(hhh]<5D>h}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>colwidth<74>KZuhhZh hWubh	<09>tbody<64><79><EFBFBD>)<29><>}<7D>(hhh]<5D>(h	<09>row<6F><77><EFBFBD>)<29><>}<7D>(hhh]<5D>(h	<09>entry<72><79><EFBFBD>)<29><>}<7D>(hhh]<5D>h	<09>	paragraph<70><68><EFBFBD>)<29><>}<7D>(h<05>c:py:obj:`binary_cross_entropy <mlx.nn.losses.binary_cross_entropy>`\ \(logits\, targets\[\, ...\]\)<29>h]<5D>(h<00>pending_xref<65><66><EFBFBD>)<29><>}<7D>(h<05>C:py:obj:`binary_cross_entropy <mlx.nn.losses.binary_cross_entropy>`<60>h]<5D>h	<09>literal<61><6C><EFBFBD>)<29><>}<7D>(hh<>h]<5D>h0<68>binary_cross_entropy<70><79><EFBFBD><EFBFBD><EFBFBD>}<7D>(h h<>h!hh"NhNubah}<7D>(h]<5D>h]<5D>(<28>xref<65><66>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h h<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F><63>python/nn/losses<65><73>	refdomain<69>h<EFBFBD><68>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E><EFBFBD>	py:module<6C><65>
mlx.nn.losses<65><73>py:class<73>N<EFBFBD>	reftarget<65><74>"mlx.nn.losses.binary_cross_entropy<70>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h h<>ubh0<68>(logits, targets[, ...])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h h<>h!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"h<>hK
h h|ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh hwubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>'Computes the binary cross entropy loss.<2E>h]<5D>h0<68>'Computes the binary cross entropy loss.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h h<>h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h h<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh hwubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>k:py:obj:`cosine_similarity_loss <mlx.nn.losses.cosine_similarity_loss>`\ \(x1\, x2\[\, axis\, eps\, ...\]\)<29>h]<5D>(h<>)<29><>}<7D>(h<05>G:py:obj:`cosine_similarity_loss <mlx.nn.losses.cosine_similarity_loss>`<60>h]<5D>h<EFBFBD>)<29><>}<7D>(hh<>h]<5D>h0<68>cosine_similarity_loss<73><73><EFBFBD><EFBFBD><EFBFBD>}<7D>(h h<>h!hh"NhNubah}<7D>(h]<5D>h]<5D>(h<><68>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h h<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F>h<EFBFBD><68>	refdomain<69>h<EFBFBD><68>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E>h<EFBFBD>h<EFBFBD>h<EFBFBD>Nh<4E><68>$mlx.nn.losses.cosine_similarity_loss<73>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h h<>ubh0<68>(x1, x2[, axis, eps, ...])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h h<>h!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"j
hK
h h<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh h<>ubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>6Computes the cosine similarity between the two inputs.<2E>h]<5D>h0<68>6Computes the cosine similarity between the two inputs.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j
h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh h<>ubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>_:py:obj:`cross_entropy <mlx.nn.losses.cross_entropy>`\ \(logits\, targets\[\, weights\, ...\]\)<29>h]<5D>(h<>)<29><>}<7D>(h<05>5:py:obj:`cross_entropy <mlx.nn.losses.cross_entropy>`<60>h]<5D>h<EFBFBD>)<29><>}<7D>(hjC
h]<5D>h0<68>
cross_entropy<70><79><EFBFBD><EFBFBD><EFBFBD>}<7D>(h jE
h!hh"NhNubah}<7D>(h]<5D>h]<5D>(h<><68>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h jA
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F>h<EFBFBD><68>	refdomain<69>jO
<00>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E>h<EFBFBD>h<EFBFBD>h<EFBFBD>Nh<4E><68>mlx.nn.losses.cross_entropy<70>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j=
ubh0<68>!(logits, targets[, weights, ...])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j=
h!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"ja
hK
h j:
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j7
ubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05> Computes the cross entropy loss.<2E>h]<5D>h0<68> Computes the cross entropy loss.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h ju
h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h jr
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j7
ubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>U:py:obj:`hinge_loss <mlx.nn.losses.hinge_loss>`\ \(inputs\, targets\[\, reduction\]\)<29>h]<5D>(h<>)<29><>}<7D>(h<05>/:py:obj:`hinge_loss <mlx.nn.losses.hinge_loss>`<60>h]<5D>h<EFBFBD>)<29><>}<7D>(hj<>
h]<5D>h0<68>
hinge_loss<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>
h!hh"NhNubah}<7D>(h]<5D>h]<5D>(h<><68>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h j<>
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F>h<EFBFBD><68>	refdomain<69>j<EFBFBD>
<00>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E>h<EFBFBD>h<EFBFBD>h<EFBFBD>Nh<4E><68>mlx.nn.losses.hinge_loss<73>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j<>
ubh0<68>(inputs, targets[, reduction])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>
h!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"j<>
hK
h j<>
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>
ubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>3Computes the hinge loss between inputs and targets.<2E>h]<5D>h0<68>3Computes the hinge loss between inputs and targets.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>
h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j<>
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>
ubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>]:py:obj:`huber_loss <mlx.nn.losses.huber_loss>`\ \(inputs\, targets\[\, delta\, reduction\]\)<29>h]<5D>(h<>)<29><>}<7D>(h<05>/:py:obj:`huber_loss <mlx.nn.losses.huber_loss>`<60>h]<5D>h<EFBFBD>)<29><>}<7D>(hj<>
h]<5D>h0<68>
huber_loss<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>
h!hh"NhNubah}<7D>(h]<5D>h]<5D>(h<><68>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h j<>
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F>h<EFBFBD><68>	refdomain<69>j
<00>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E>h<EFBFBD>h<EFBFBD>h<EFBFBD>Nh<4E><68>mlx.nn.losses.huber_loss<73>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j<>
ubh0<68>%(inputs, targets[, delta, reduction])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>
h!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"jhK
h j<>
ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>
ubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>3Computes the Huber loss between inputs and targets.<2E>h]<5D>h0<68>3Computes the Huber loss between inputs and targets.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j'h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j$ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>
ubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>^:py:obj:`kl_div_loss <mlx.nn.losses.kl_div_loss>`\ \(inputs\, targets\[\, axis\, reduction\]\)<29>h]<5D>(h<>)<29><>}<7D>(h<05>1:py:obj:`kl_div_loss <mlx.nn.losses.kl_div_loss>`<60>h]<5D>h<EFBFBD>)<29><>}<7D>(hjNh]<5D>h0<68>kl_div_loss<73><73><EFBFBD><EFBFBD><EFBFBD>}<7D>(h jPh!hh"NhNubah}<7D>(h]<5D>h]<5D>(h<><68>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h jLubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F>h<EFBFBD><68>	refdomain<69>jZ<00>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E>h<EFBFBD>h<EFBFBD>h<EFBFBD>Nh<4E><68>mlx.nn.losses.kl_div_loss<73>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h jHubh0<68>$(inputs, targets[, axis, reduction])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h jHh!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"jlhK
h jEubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh jBubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>.Computes the Kullback-Leibler divergence loss.<2E>h]<5D>h0<68>.Computes the Kullback-Leibler divergence loss.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j}ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh jBubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>T:py:obj:`l1_loss <mlx.nn.losses.l1_loss>`\ \(predictions\, targets\[\, reduction\]\)<29>h]<5D>(h<>)<29><>}<7D>(h<05>):py:obj:`l1_loss <mlx.nn.losses.l1_loss>`<60>h]<5D>h<EFBFBD>)<29><>}<7D>(hj<>h]<5D>h0<68>l1_loss<73><73><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>h!hh"NhNubah}<7D>(h]<5D>h]<5D>(h<><68>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h j<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F>h<EFBFBD><68>	refdomain<69>j<EFBFBD><00>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E>h<EFBFBD>h<EFBFBD>h<EFBFBD>Nh<4E><68>mlx.nn.losses.l1_loss<73>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j<>ubh0<68>#(predictions, targets[, reduction])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>h!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"j<>hK
h j<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>ubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>Computes the L1 loss.<2E>h]<5D>h0<68>Computes the L1 loss.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>ubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>[:py:obj:`log_cosh_loss <mlx.nn.losses.log_cosh_loss>`\ \(inputs\, targets\[\, reduction\]\)<29>h]<5D>(h<>)<29><>}<7D>(h<05>5:py:obj:`log_cosh_loss <mlx.nn.losses.log_cosh_loss>`<60>h]<5D>h<EFBFBD>)<29><>}<7D>(hjh]<5D>h0<68>
log_cosh_loss<73><73><EFBFBD><EFBFBD><EFBFBD>}<7D>(h jh!hh"NhNubah}<7D>(h]<5D>h]<5D>(h<><68>py<70><79>py-obj<62>eh]<5D>h]<5D>h]<5D>uhh<>h j<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>refdoc<6F>h<EFBFBD><68>	refdomain<69>j<00>reftype<70><65>obj<62><6A>refexplicit<69><74><EFBFBD>refwarn<72><6E>h<EFBFBD>h<EFBFBD>h<EFBFBD>Nh<4E><68>mlx.nn.losses.log_cosh_loss<73>uhh<>h"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j<>ubh0<68>(inputs, targets[, reduction])<29><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j<>h!hh"NhNubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"jhK
h j<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>ubh{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>6Computes the log cosh loss between inputs and targets.<2E>h]<5D>h0<68>6Computes the log cosh loss between inputs and targets.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>(h j2h!hh"NhNubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh"<22>J/Users/awnihannun/repos/mlx/docs/src/python/nn/losses.rst:23:<autosummary><3E>hK
h j/ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhzh j<>ubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhuh hrubhv)<29><>}<7D>(hhh]<5D>(h{)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(h<05>V:py:obj:`mse_loss <mlx.nn.losses.mse_loss
rawentries<EFBFBD>]<5D>uhj<>h j<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>j<EFBFBD>j<>uhj<>h h&h!hh"hHhNubeh}<7D>(h]<5D>(<28>loss-functions<6E>heh]<5D>h]<5D>(<28>loss functions<6E><73>losses<65>eh]<5D>h]<5D>uhh$h hh!hh"h#hK<06>expect_referenced_by_name<6D>}<7D>j	hs<>expect_referenced_by_id<69>}<7D>hhsubeh}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>source<63>h#uhh
<01>current_source<63>N<EFBFBD>current_line<6E>N<EFBFBD>settings<67><73>docutils.frontend<6E><64>Values<65><73><EFBFBD>)<29><>}<7D>(h)N<>	generator<6F>N<EFBFBD>	datestamp<6D>N<EFBFBD>source_link<6E>N<EFBFBD>
source_url<EFBFBD>N<EFBFBD>
toc_backlinks<6B>hz<68>footnote_backlinks<6B>K
<01>
sectnum_xform<72>K
<01>strip_comments<74>N<EFBFBD>strip_elements_with_classes<65>N<EFBFBD>
strip_classes<65>N<EFBFBD>report_level<65>K<02>
halt_level<EFBFBD>K<05>exit_status_level<65>K<05>debug<75>N<EFBFBD>warning_stream<61>N<EFBFBD>	traceback<63><6B><EFBFBD>input_encoding<6E><67>	utf-8-sig<69><67>input_encoding_error_handler<65><72>strict<63><74>output_encoding<6E><67>utf-8<><38>output_encoding_error_handler<65>j2<00>error_encoding<6E><67>utf-8<><38>error_encoding_error_handler<65><72>backslashreplace<63><65>
language_code<64><65>en<65><6E>record_dependencies<65>N<EFBFBD>config<69>N<EFBFBD>	id_prefix<69>h<06>auto_id_prefix<69><78>id<69><64>
dump_settings<67>N<EFBFBD>dump_internals<6C>N<EFBFBD>dump_transforms<6D>N<EFBFBD>dump_pseudo_xml<6D>N<EFBFBD>expose_internals<6C>N<EFBFBD>strict_visitor<6F>N<EFBFBD>_disable_config<69>N<EFBFBD>_source<63>h#<23>_destination<6F>N<EFBFBD>
_config_files<65>]<5D><>file_insertion_enabled<65><64><EFBFBD>raw_enabled<65>K
<01>line_length_limit<69>M'<27>pep_references<65>N<EFBFBD>pep_base_url<72><6C>https://peps.python.org/<2F><>pep_file_url_template<74><65>pep-%04d<34><64>rfc_references<65>N<EFBFBD>rfc_base_url<72><6C>&https://datatracker.ietf.org/doc/html/<2F><>	tab_width<74>K<08>trim_footnote_reference_space<63><65><EFBFBD>syntax_highlight<68><74>long<6E><67>smart_quotes<65><73><EFBFBD>smartquotes_locales<65>]<5D><>character_level_inline_markup<75><70><EFBFBD>doctitle_xform<72><6D><EFBFBD>
docinfo_xform<72>K
<01>sectsubtitle_xform<72><6D><EFBFBD>
image_loading<6E><67>link<6E><6B>embed_stylesheet<65><74><EFBFBD>cloak_email_addresses<65><73><EFBFBD>section_self_link<6E><6B><EFBFBD>env<6E>Nub<75>reporter<65>N<EFBFBD>indirect_targets<74>]<5D><>substitution_defs<66>}<7D><>substitution_names<65>}<7D><>refnames<65>}<7D><>refids<64>}<7D>h]<5D>has<61>nameids<64>}<7D>(j	hjju<>	nametypes<65>}<7D>(j	<00>j<00>uh}<7D>(hh&jh&u<>
footnote_refs<66>}<7D><>
citation_refs<66>}<7D><>
autofootnotes<65>]<5D><>autofootnote_refs<66>]<5D><>symbol_footnotes<65>]<5D><>symbol_footnote_refs<66>]<5D><>	footnotes<65>]<5D><>	citations<6E>]<5D><>autofootnote_start<72>K
<01>symbol_footnote_start<72>K<00>
id_counter<EFBFBD><EFBFBD>collections<6E><73>Counter<65><72><EFBFBD>}<7D><><EFBFBD>R<EFBFBD><52>parse_messages<65>]<5D><>transform_messages<65>]<5D>h	<09>system_message<67><65><EFBFBD>)<29><>}<7D>(hhh]<5D>h<EFBFBD>)<29><>}<7D>(hhh]<5D>h0<68>,Hyperlink target "losses" is not referenced.<2E><><EFBFBD><EFBFBD><EFBFBD>}<7D>h j<>sbah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D>uhhh j<>ubah}<7D>(h]<5D>h]<5D>h]<5D>h]<5D>h]<5D><>level<65>K
<01>type<70><65>INFO<46><4F>source<63>h#<23>line<6E>K
uhj<>uba<62>transformer<65>N<EFBFBD>include_log<6F>]<5D><>
decoration<EFBFBD>Nh!hub.