diff options
author | Evan Shelhamer <shelhamer@imaginarynumber.net> | 2017-02-27 11:54:37 -0800 |
---|---|---|
committer | GitHub <noreply@github.com> | 2017-02-27 11:54:37 -0800 |
commit | 85ab6100a122042c7dfd4adaf06f4c0b2e71148d (patch) | |
tree | 8058758a9bb9ed908c5c52dd498dadadbdf47964 /docs/tutorial | |
parent | 16467ff149c880f752414ee2c241c01040d1a05f (diff) | |
download | caffeonacl-85ab6100a122042c7dfd4adaf06f4c0b2e71148d.tar.gz caffeonacl-85ab6100a122042c7dfd4adaf06f4c0b2e71148d.tar.bz2 caffeonacl-85ab6100a122042c7dfd4adaf06f4c0b2e71148d.zip |
fix broken link to hinge loss
Diffstat (limited to 'docs/tutorial')
-rw-r--r-- | docs/tutorial/layers.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/docs/tutorial/layers.md b/docs/tutorial/layers.md index a903d5ac..2faacc58 100644 --- a/docs/tutorial/layers.md +++ b/docs/tutorial/layers.md @@ -128,7 +128,7 @@ Layers: * [Infogain Loss](layers/infogainloss.html) - a generalization of MultinomialLogisticLossLayer. * [Softmax with Loss](layers/softmaxwithloss.html) - computes the multinomial logistic loss of the softmax of its inputs. It's conceptually identical to a softmax layer followed by a multinomial logistic loss layer, but provides a more numerically stable gradient. * [Sum-of-Squares / Euclidean](layers/euclideanloss.html) - computes the sum of squares of differences of its two inputs, $$\frac 1 {2N} \sum_{i=1}^N \| x^1_i - x^2_i \|_2^2$$. -* [Hinge / Margin](layers/hiddenloss.html) - The hinge loss layer computes a one-vs-all hinge (L1) or squared hinge loss (L2). +* [Hinge / Margin](layers/hingeloss.html) - The hinge loss layer computes a one-vs-all hinge (L1) or squared hinge loss (L2). * [Sigmoid Cross-Entropy Loss](layers/sigmoidcrossentropyloss.html) - computes the cross-entropy (logistic) loss, often used for predicting targets interpreted as probabilities. * [Accuracy / Top-k layer](layers/accuracy.html) - scores the output as an accuracy with respect to target -- it is not actually a loss and has no backward step. * [Contrastive Loss](layers/contrastiveloss.html) |