Skip to content

Commit 915db6e

Browse files
mhjensenmhjensen
committed
update
1 parent da856b0 commit 915db6e

File tree

8 files changed

+205
-200
lines changed

8 files changed

+205
-200
lines changed

‎doc/pub/week8/html/week8-bs.html‎

Lines changed: 13 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -40,10 +40,10 @@
4040
2,
4141
None,
4242
'plans-for-the-week-march-10-14'),
43-
('Reading recommendations: RNNs',
43+
('Reading recommendations: RNNs and LSTMs',
4444
2,
4545
None,
46-
'reading-recommendations-rnns'),
46+
'reading-recommendations-rnns-and-lstms'),
4747
('Reading recommendations: Autoencoders (AE)',
4848
2,
4949
None,
@@ -195,7 +195,7 @@
195195
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
196196
<ul class="dropdown-menu">
197197
<!-- navigation toc: --> <li><a href="#plans-for-the-week-march-10-14" style="font-size: 80%;">Plans for the week March 10-14</a></li>
198-
<!-- navigation toc: --> <li><a href="#reading-recommendations-rnns" style="font-size: 80%;">Reading recommendations: RNNs</a></li>
198+
<!-- navigation toc: --> <li><a href="#reading-recommendations-rnns-and-lstms" style="font-size: 80%;">Reading recommendations: RNNs and LSTMs</a></li>
199199
<!-- navigation toc: --> <li><a href="#reading-recommendations-autoencoders-ae" style="font-size: 80%;">Reading recommendations: Autoencoders (AE)</a></li>
200200
<!-- navigation toc: --> <li><a href="#gating-mechanism-long-short-term-memory-lstm" style="font-size: 80%;">Gating mechanism: Long Short Term Memory (LSTM)</a></li>
201201
<!-- navigation toc: --> <li><a href="#implementing-a-memory-cell-in-a-neural-network" style="font-size: 80%;">Implementing a memory cell in a neural network</a></li>
@@ -304,15 +304,16 @@ <h2 id="plans-for-the-week-march-10-14" class="anchor">Plans for the week March
304304

305305

306306
<!-- !split -->
307-
<h2 id="reading-recommendations-rnns" class="anchor">Reading recommendations: RNNs </h2>
307+
<h2 id="reading-recommendations-rnns-and-lstms" class="anchor">Reading recommendations: RNNs and LSTMs </h2>
308308

309309
<div class="panel panel-default">
310310
<div class="panel-body">
311311
<!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
312312
<ol>
313-
<li> For RNNs see Goodfellow et al chapter 10.</li>
313+
<li> For RNNs see Goodfellow et al chapter 10, see <a href="https://www.deeplearningbook.org/contents/rnn.html" target="_self"><tt>https://www.deeplearningbook.org/contents/rnn.html</tt></a></li>
314314
<li> Reading suggestions for implementation of RNNs in PyTorch: Rashcka et al's text, chapter 15</li>
315-
<li> Reading suggestions for implementation of RNNs in TensorFlow: <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Textbooks/TensorflowML.pdf" target="_self">Aurelien Geron's chapter 14</a>.</li>
315+
<li> RNN video at URL":https://youtu.be/PCgrgHgy26c?feature=shared"</li>
316+
<li> New xLSTM, see Beck et al <a href="https://arxiv.org/abs/2405.04517" target="_self"><tt>https://arxiv.org/abs/2405.04517</tt></a>. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling.</li>
316317
</ol>
317318
</div>
318319
</div>
@@ -325,13 +326,13 @@ <h2 id="reading-recommendations-autoencoders-ae" class="anchor">Reading recommen
325326
<div class="panel-body">
326327
<!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
327328
<ol>
328-
<li> Goodfellow et al chapter 14.</li>
329+
<li> Goodfellow et al chapter 14, see <a href="https://www.deeplearningbook.org/contents/autoencoders.html" target="_self"><tt>https://www.deeplearningbook.org/contents/autoencoders.html</tt></a></li>
329330
<li> Rashcka et al. Their chapter 17 contains a brief introduction only.</li>
330-
<li> <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_self">Deep Learning Tutorial on AEs from Stanford University</a></li>
331-
<li> <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_self">Building AEs in Keras</a></li>
332-
<li> <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_self">Introduction to AEs in TensorFlow</a></li>
333-
<li> <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_self">Grosse, University of Toronto, Lecture on AEs</a></li>
334-
<li> <a href="https://arxiv.org/abs/2003.05991" target="_self">Bank et al on AEs</a></li>
331+
<li> Deep Learning Tutorial on AEs from Stanford University at <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_self"><tt>http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/</tt></a></li>
332+
<li> Building AEs in Keras at <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_self"><tt>https://blog.keras.io/building-autoencoders-in-keras.html</tt></a></li>
333+
<li> Introduction to AEs in TensorFlow at <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_self"><tt>https://www.tensorflow.org/tutorials/generative/autoencoder</tt></a></li>
334+
<li> Grosse, University of Toronto, Lecture on AEs at <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_self"><tt>http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf</tt></a></li>
335+
<li> Bank et al on AEs at <a href="https://arxiv.org/abs/2003.05991" target="_self"><tt>https://arxiv.org/abs/2003.05991</tt></a></li>
335336
<li> Baldi and Hornik, Neural networks and principal component analysis: Learning from examples without local minima, Neural Networks 2, 53 (1989)</li>
336337
</ol>
337338
</div>

‎doc/pub/week8/html/week8-reveal.html‎

Lines changed: 10 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -208,15 +208,16 @@ <h2 id="plans-for-the-week-march-10-14">Plans for the week March 10-14 </h2>
208208
</section>
209209

210210
<section>
211-
<h2 id="reading-recommendations-rnns">Reading recommendations: RNNs </h2>
211+
<h2 id="reading-recommendations-rnns-and-lstms">Reading recommendations: RNNs and LSTMs </h2>
212212

213213
<div class="alert alert-block alert-block alert-text-normal">
214214
<b></b>
215215
<p>
216216
<ol>
217-
<p><li> For RNNs see Goodfellow et al chapter 10.</li>
217+
<p><li> For RNNs see Goodfellow et al chapter 10, see <a href="https://www.deeplearningbook.org/contents/rnn.html" target="_blank"><tt>https://www.deeplearningbook.org/contents/rnn.html</tt></a></li>
218218
<p><li> Reading suggestions for implementation of RNNs in PyTorch: Rashcka et al's text, chapter 15</li>
219-
<p><li> Reading suggestions for implementation of RNNs in TensorFlow: <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Textbooks/TensorflowML.pdf" target="_blank">Aurelien Geron's chapter 14</a>.</li>
219+
<p><li> RNN video at URL":https://youtu.be/PCgrgHgy26c?feature=shared"</li>
220+
<p><li> New xLSTM, see Beck et al <a href="https://arxiv.org/abs/2405.04517" target="_blank"><tt>https://arxiv.org/abs/2405.04517</tt></a>. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling.</li>
220221
</ol>
221222
</div>
222223
</section>
@@ -228,13 +229,13 @@ <h2 id="reading-recommendations-autoencoders-ae">Reading recommendations: Autoen
228229
<b></b>
229230
<p>
230231
<ol>
231-
<p><li> Goodfellow et al chapter 14.</li>
232+
<p><li> Goodfellow et al chapter 14, see <a href="https://www.deeplearningbook.org/contents/autoencoders.html" target="_blank"><tt>https://www.deeplearningbook.org/contents/autoencoders.html</tt></a></li>
232233
<p><li> Rashcka et al. Their chapter 17 contains a brief introduction only.</li>
233-
<p><li> <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_blank">Deep Learning Tutorial on AEs from Stanford University</a></li>
234-
<p><li> <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_blank">Building AEs in Keras</a></li>
235-
<p><li> <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_blank">Introduction to AEs in TensorFlow</a></li>
236-
<p><li> <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_blank">Grosse, University of Toronto, Lecture on AEs</a></li>
237-
<p><li> <a href="https://arxiv.org/abs/2003.05991" target="_blank">Bank et al on AEs</a></li>
234+
<p><li> Deep Learning Tutorial on AEs from Stanford University at <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_blank"><tt>http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/</tt></a></li>
235+
<p><li> Building AEs in Keras at <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_blank"><tt>https://blog.keras.io/building-autoencoders-in-keras.html</tt></a></li>
236+
<p><li> Introduction to AEs in TensorFlow at <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_blank"><tt>https://www.tensorflow.org/tutorials/generative/autoencoder</tt></a></li>
237+
<p><li> Grosse, University of Toronto, Lecture on AEs at <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_blank"><tt>http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf</tt></a></li>
238+
<p><li> Bank et al on AEs at <a href="https://arxiv.org/abs/2003.05991" target="_blank"><tt>https://arxiv.org/abs/2003.05991</tt></a></li>
238239

239240
<p><li> Baldi and Hornik, Neural networks and principal component analysis: Learning from examples without local minima, Neural Networks 2, 53 (1989)</li>
240241
</ol>

‎doc/pub/week8/html/week8-solarized.html‎

Lines changed: 12 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -67,10 +67,10 @@
6767
2,
6868
None,
6969
'plans-for-the-week-march-10-14'),
70-
('Reading recommendations: RNNs',
70+
('Reading recommendations: RNNs and LSTMs',
7171
2,
7272
None,
73-
'reading-recommendations-rnns'),
73+
'reading-recommendations-rnns-and-lstms'),
7474
('Reading recommendations: Autoencoders (AE)',
7575
2,
7676
None,
@@ -242,15 +242,16 @@ <h2 id="plans-for-the-week-march-10-14">Plans for the week March 10-14 </h2>
242242

243243

244244
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
245-
<h2 id="reading-recommendations-rnns">Reading recommendations: RNNs </h2>
245+
<h2 id="reading-recommendations-rnns-and-lstms">Reading recommendations: RNNs and LSTMs </h2>
246246

247247
<div class="alert alert-block alert-block alert-text-normal">
248248
<b></b>
249249
<p>
250250
<ol>
251-
<li> For RNNs see Goodfellow et al chapter 10.</li>
251+
<li> For RNNs see Goodfellow et al chapter 10, see <a href="https://www.deeplearningbook.org/contents/rnn.html" target="_blank"><tt>https://www.deeplearningbook.org/contents/rnn.html</tt></a></li>
252252
<li> Reading suggestions for implementation of RNNs in PyTorch: Rashcka et al's text, chapter 15</li>
253-
<li> Reading suggestions for implementation of RNNs in TensorFlow: <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Textbooks/TensorflowML.pdf" target="_blank">Aurelien Geron's chapter 14</a>.</li>
253+
<li> RNN video at URL":https://youtu.be/PCgrgHgy26c?feature=shared"</li>
254+
<li> New xLSTM, see Beck et al <a href="https://arxiv.org/abs/2405.04517" target="_blank"><tt>https://arxiv.org/abs/2405.04517</tt></a>. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling.</li>
254255
</ol>
255256
</div>
256257

@@ -262,13 +263,13 @@ <h2 id="reading-recommendations-autoencoders-ae">Reading recommendations: Autoen
262263
<b></b>
263264
<p>
264265
<ol>
265-
<li> Goodfellow et al chapter 14.</li>
266+
<li> Goodfellow et al chapter 14, see <a href="https://www.deeplearningbook.org/contents/autoencoders.html" target="_blank"><tt>https://www.deeplearningbook.org/contents/autoencoders.html</tt></a></li>
266267
<li> Rashcka et al. Their chapter 17 contains a brief introduction only.</li>
267-
<li> <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_blank">Deep Learning Tutorial on AEs from Stanford University</a></li>
268-
<li> <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_blank">Building AEs in Keras</a></li>
269-
<li> <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_blank">Introduction to AEs in TensorFlow</a></li>
270-
<li> <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_blank">Grosse, University of Toronto, Lecture on AEs</a></li>
271-
<li> <a href="https://arxiv.org/abs/2003.05991" target="_blank">Bank et al on AEs</a></li>
268+
<li> Deep Learning Tutorial on AEs from Stanford University at <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_blank"><tt>http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/</tt></a></li>
269+
<li> Building AEs in Keras at <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_blank"><tt>https://blog.keras.io/building-autoencoders-in-keras.html</tt></a></li>
270+
<li> Introduction to AEs in TensorFlow at <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_blank"><tt>https://www.tensorflow.org/tutorials/generative/autoencoder</tt></a></li>
271+
<li> Grosse, University of Toronto, Lecture on AEs at <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_blank"><tt>http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf</tt></a></li>
272+
<li> Bank et al on AEs at <a href="https://arxiv.org/abs/2003.05991" target="_blank"><tt>https://arxiv.org/abs/2003.05991</tt></a></li>
272273
<li> Baldi and Hornik, Neural networks and principal component analysis: Learning from examples without local minima, Neural Networks 2, 53 (1989)</li>
273274
</ol>
274275
</div>

‎doc/pub/week8/html/week8.html‎

Lines changed: 12 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -144,10 +144,10 @@
144144
2,
145145
None,
146146
'plans-for-the-week-march-10-14'),
147-
('Reading recommendations: RNNs',
147+
('Reading recommendations: RNNs and LSTMs',
148148
2,
149149
None,
150-
'reading-recommendations-rnns'),
150+
'reading-recommendations-rnns-and-lstms'),
151151
('Reading recommendations: Autoencoders (AE)',
152152
2,
153153
None,
@@ -319,15 +319,16 @@ <h2 id="plans-for-the-week-march-10-14">Plans for the week March 10-14 </h2>
319319

320320

321321
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
322-
<h2 id="reading-recommendations-rnns">Reading recommendations: RNNs </h2>
322+
<h2 id="reading-recommendations-rnns-and-lstms">Reading recommendations: RNNs and LSTMs </h2>
323323

324324
<div class="alert alert-block alert-block alert-text-normal">
325325
<b></b>
326326
<p>
327327
<ol>
328-
<li> For RNNs see Goodfellow et al chapter 10.</li>
328+
<li> For RNNs see Goodfellow et al chapter 10, see <a href="https://www.deeplearningbook.org/contents/rnn.html" target="_blank"><tt>https://www.deeplearningbook.org/contents/rnn.html</tt></a></li>
329329
<li> Reading suggestions for implementation of RNNs in PyTorch: Rashcka et al's text, chapter 15</li>
330-
<li> Reading suggestions for implementation of RNNs in TensorFlow: <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Textbooks/TensorflowML.pdf" target="_blank">Aurelien Geron's chapter 14</a>.</li>
330+
<li> RNN video at URL":https://youtu.be/PCgrgHgy26c?feature=shared"</li>
331+
<li> New xLSTM, see Beck et al <a href="https://arxiv.org/abs/2405.04517" target="_blank"><tt>https://arxiv.org/abs/2405.04517</tt></a>. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling.</li>
331332
</ol>
332333
</div>
333334

@@ -339,13 +340,13 @@ <h2 id="reading-recommendations-autoencoders-ae">Reading recommendations: Autoen
339340
<b></b>
340341
<p>
341342
<ol>
342-
<li> Goodfellow et al chapter 14.</li>
343+
<li> Goodfellow et al chapter 14, see <a href="https://www.deeplearningbook.org/contents/autoencoders.html" target="_blank"><tt>https://www.deeplearningbook.org/contents/autoencoders.html</tt></a></li>
343344
<li> Rashcka et al. Their chapter 17 contains a brief introduction only.</li>
344-
<li> <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_blank">Deep Learning Tutorial on AEs from Stanford University</a></li>
345-
<li> <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_blank">Building AEs in Keras</a></li>
346-
<li> <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_blank">Introduction to AEs in TensorFlow</a></li>
347-
<li> <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_blank">Grosse, University of Toronto, Lecture on AEs</a></li>
348-
<li> <a href="https://arxiv.org/abs/2003.05991" target="_blank">Bank et al on AEs</a></li>
345+
<li> Deep Learning Tutorial on AEs from Stanford University at <a href="http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/" target="_blank"><tt>http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/</tt></a></li>
346+
<li> Building AEs in Keras at <a href="https://blog.keras.io/building-autoencoders-in-keras.html" target="_blank"><tt>https://blog.keras.io/building-autoencoders-in-keras.html</tt></a></li>
347+
<li> Introduction to AEs in TensorFlow at <a href="https://www.tensorflow.org/tutorials/generative/autoencoder" target="_blank"><tt>https://www.tensorflow.org/tutorials/generative/autoencoder</tt></a></li>
348+
<li> Grosse, University of Toronto, Lecture on AEs at <a href="http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf" target="_blank"><tt>http://www.cs.toronto.edu/~rgrosse/courses/csc321_2017/slides/lec20.pdf</tt></a></li>
349+
<li> Bank et al on AEs at <a href="https://arxiv.org/abs/2003.05991" target="_blank"><tt>https://arxiv.org/abs/2003.05991</tt></a></li>
349350
<li> Baldi and Hornik, Neural networks and principal component analysis: Learning from examples without local minima, Neural Networks 2, 53 (1989)</li>
350351
</ol>
351352
</div>

‎doc/pub/week8/ipynb/ipynb-week8-src.tar.gz‎

0 Bytes
Binary file not shown.

0 commit comments

Comments
 (0)