<dd><ahref="#id12"><spanclass="problematic"id="id13">`Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
https://arxiv.org/abs/1406.4729`_</span></a></dd>
<dd><aclass="reference external"href="https://arxiv.org/abs/1406.4729">Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition</a></dd>
<aclass="reference external"href="https://arxiv.org/pdf/1312.6082v4.pdf">Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks</a></dd>
<dd><aclass="reference external"href="http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf">ImageNet Classification with Deep Convolutional Neural Networks</a></dd>
<dd><aclass="reference external"href="http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf">Learning to Rank using Gradient Descent</a></dd>
</dl>
<divclass="math">
\[ \begin{align}\begin{aligned}C_{i,j} & = -\tilde{P_{ij}} * o_{i,j} + log(1 + e^{o_{i,j}})\\o_{i,j} & = o_i - o_j\\\tilde{P_{i,j}} & = \{0, 0.5, 1\} \ or \ \{0, 1\}\end{aligned}\end{align} \]</div>
...
...
@@ -4152,9 +4146,8 @@ classication task. e.g. sequence labeling problems where the
alignment between the inputs and the target labels is unknown.</p>
<dlclass="docutils">
<dt>Reference:</dt>
<dd><ahref="#id24"><spanclass="problematic"id="id25">`Connectionist Temporal Classification: Labelling Unsegmented Sequence Data
<dd><aclass="reference external"href="https://www.cs.toronto.edu/~amnih/papers/ncelm.pdf">A fast and simple algorithm for training neural probabilistic language
<dd><aclass="reference external"href="http://arxiv.org/pdf/1502.01852v1.pdf">Delving Deep into Rectifiers: Surpassing Human-Level Performance on
ImageNet Classification</a></dd>
</dl>
<divclass="math">
\[\begin{split}z_i &\quad if \quad z_i > 0 \\
...
...
@@ -4588,11 +4579,10 @@ details.</li>
<dd><p>The gated unit layer implements a simple gating mechanism over the input.
The input <spanclass="math">\(X\)</span> is first projected into a new space <spanclass="math">\(X'\)</span>, and
it is also used to produce a gate weight <spanclass="math">\(\sigma\)</span>. Element-wise
product between <ahref="#id10"><spanclass="problematic"id="id11">:match:`X’`</span></a> and <spanclass="math">\(\sigma\)</span> is finally returned.</p>
product between <ahref="#id11"><spanclass="problematic"id="id12">:match:`X’`</span></a> and <spanclass="math">\(\sigma\)</span> is finally returned.</p>
<dlclass="docutils">
<dt>Reference:</dt>
<dd><ahref="#id34"><spanclass="problematic"id="id35">`Language Modeling with Gated Convolutional Networks
<dd><ahref="#id12"><spanclass="problematic"id="id13">`Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
https://arxiv.org/abs/1406.4729`_</span></a></dd>
<dd><aclass="reference external"href="https://arxiv.org/abs/1406.4729">Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition</a></dd>
<aclass="reference external"href="https://arxiv.org/pdf/1312.6082v4.pdf">Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks</a></dd>
<dd><aclass="reference external"href="http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf">ImageNet Classification with Deep Convolutional Neural Networks</a></dd>
<dd><aclass="reference external"href="http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf">Learning to Rank using Gradient Descent</a></dd>
</dl>
<divclass="math">
\[ \begin{align}\begin{aligned}C_{i,j} & = -\tilde{P_{ij}} * o_{i,j} + log(1 + e^{o_{i,j}})\\o_{i,j} & = o_i - o_j\\\tilde{P_{i,j}} & = \{0, 0.5, 1\} \ or \ \{0, 1\}\end{aligned}\end{align} \]</div>
...
...
@@ -4153,9 +4147,8 @@ classication task. e.g. sequence labeling problems where the
alignment between the inputs and the target labels is unknown.</p>
<dlclass="docutils">
<dt>Reference:</dt>
<dd><ahref="#id24"><spanclass="problematic"id="id25">`Connectionist Temporal Classification: Labelling Unsegmented Sequence Data
<dd><aclass="reference external"href="https://www.cs.toronto.edu/~amnih/papers/ncelm.pdf">A fast and simple algorithm for training neural probabilistic language
<dd><aclass="reference external"href="http://arxiv.org/pdf/1502.01852v1.pdf">Delving Deep into Rectifiers: Surpassing Human-Level Performance on
ImageNet Classification</a></dd>
</dl>
<divclass="math">
\[\begin{split}z_i &\quad if \quad z_i > 0 \\
...
...
@@ -4589,11 +4580,10 @@ details.</li>
<dd><p>The gated unit layer implements a simple gating mechanism over the input.
The input <spanclass="math">\(X\)</span> is first projected into a new space <spanclass="math">\(X'\)</span>, and
it is also used to produce a gate weight <spanclass="math">\(\sigma\)</span>. Element-wise
product between <ahref="#id10"><spanclass="problematic"id="id11">:match:`X’`</span></a> and <spanclass="math">\(\sigma\)</span> is finally returned.</p>
product between <ahref="#id11"><spanclass="problematic"id="id12">:match:`X’`</span></a> and <spanclass="math">\(\sigma\)</span> is finally returned.</p>
<dlclass="docutils">
<dt>Reference:</dt>
<dd><ahref="#id34"><spanclass="problematic"id="id35">`Language Modeling with Gated Convolutional Networks
