Bolding the gate names

posts/2015-08-Understanding-LSTMs/index.html

@@ -169,12 +169,12 @@ <h2 id="the-core-idea-behind-lstms">The Core Idea Behind LSTMs</h2>
 <p>The sigmoid layer outputs numbers between zero and one, describing how much of each component should be let through. A value of zero means “let nothing through,” while a value of one means “let everything through!”</p>
 <p>An LSTM has three of these gates, to protect and control the cell state.</p>
 <h2 id="step-by-step-lstm-walk-through">Step-by-Step LSTM Walk Through</h2>
-<p>The first step in our LSTM is to decide what information we’re going to throw away from the cell state. This decision is made by a sigmoid layer called the “forget gate layer.” It looks at <span class="math">\(h_{t-1}\)</span> and <span class="math">\(x_t\)</span>, and outputs a number between <span class="math">\(0\)</span> and <span class="math">\(1\)</span> for each number in the cell state <span class="math">\(C_{t-1}\)</span>. A <span class="math">\(1\)</span> represents “completely keep this” while a <span class="math">\(0\)</span> represents “completely get rid of this.”</p>
+<p>The first step in our LSTM is to decide what information we’re going to throw away from the cell state. This decision is made by a sigmoid layer called the “<b>forget gate</b> layer.” It looks at <span class="math">\(h_{t-1}\)</span> and <span class="math">\(x_t\)</span>, and outputs a number between <span class="math">\(0\)</span> and <span class="math">\(1\)</span> for each number in the cell state <span class="math">\(C_{t-1}\)</span>. A <span class="math">\(1\)</span> represents “completely keep this” while a <span class="math">\(0\)</span> represents “completely get rid of this.”</p>
 <p>Let’s go back to our example of a language model trying to predict the next word based on all the previous ones. In such a problem, the cell state might include the gender of the present subject, so that the correct pronouns can be used. When we see a new subject, we want to forget the gender of the old subject.</p>
 <div style="width:90%; margin-left:auto; margin-right:auto; margin-bottom:8px; margin-top:8px;">
 <img src="img/LSTM3-focus-f.png" alt>
 </div>
-<p>The next step is to decide what new information we’re going to store in the cell state. This has two parts. First, a sigmoid layer called the “input gate layer” decides which values we’ll update. Next, a tanh layer creates a vector of new candidate values, <span class="math">\(\tilde{C}_t\)</span>, that could be added to the state. In the next step, we’ll combine these two to create an update to the state.</p>
+<p>The next step is to decide what new information we’re going to store in the cell state. This has two parts. First, a sigmoid layer called the “<b>input gate</b> layer” decides which values we’ll update. Next, a tanh layer creates a vector of new candidate values, <span class="math">\(\tilde{C}_t\)</span>, that could be added to the state. In the next step, we’ll combine these two to create an update to the state.</p>
 <p>In the example of our language model, we’d want to add the gender of the new subject to the cell state, to replace the old one we’re forgetting.</p>
 <div style="width:90%; margin-left:auto; margin-right:auto; margin-bottom:8px; margin-top:8px;">
 <img src="img/LSTM3-focus-i.png" alt>