reordering RNNs

This commit is contained in:
mhjensen
2019-12-16 12:04:11 +01:00
parent 3fb3749494
commit aa177fbcba
12 changed files with 170 additions and 58 deletions
+30 -2
View File
@@ -44,7 +44,13 @@ div { text-align: justify; text-justify: inter-word; }
2,
None,
'___sec0'),
('Set up of an RNN', 2, None, '___sec1')]}
('Set up of an RNN', 2, None, '___sec1'),
('Solving differential equations and eigenvalue problems with '
'RNNs',
2,
None,
'___sec2'),
('Long-Short Time Memory', 2, None, '___sec3')]}
end of tocinfo -->
<body>
@@ -86,7 +92,7 @@ MathJax.Hub.Config({
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
<br>
<p>
<center><h4>Jan 8, 2019</h4></center> <!-- date -->
<center><h4>Dec 16, 2019</h4></center> <!-- date -->
<br>
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -114,6 +120,9 @@ example, they can take sentences, documents, or audio samples as
input, making them extremely useful for natural language processing
systems such as automatic translation and speech-to-text.
<p>
<b>The text here is under development</b>. Planned finished Jan 2020.
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -130,6 +139,25 @@ the output from the previous layer \( t-1 \), that is \( y_{t1} \).
This means also that we need to have weights that link both the inputs \( x_t \) to the outputs \( y_t \) as well as weights that link
the output from the previous time \( y_{t-1} \) and \( y_t \). The figure here shows an example of a simple RNN.
<p>
Add figures and bring up equations.
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="___sec2">Solving differential equations and eigenvalue problems with RNNs </h2>
<p>
Have example with eigenvalues solvers as well.
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="___sec3">Long-Short Time Memory </h2>
<p>
Discussions about dynamic unrolling through time. discuss memory cells, input and output
<!-- ------------------- end of main content --------------- -->