From dc156729518b3025ce1926341cd04e418a8bc99b Mon Sep 17 00:00:00 2001 From: Morten Hjorth-Jensen Date: Sat, 22 Oct 2022 22:48:50 +0200 Subject: [PATCH] update week43 --- doc/pub/week43/html/week43-bs.html | 109 +---- doc/pub/week43/html/week43-reveal.html | 22 +- doc/pub/week43/html/week43-solarized.html | 25 +- doc/pub/week43/html/week43.html | 25 +- doc/pub/week43/ipynb/ipynb-week43-src.tar.gz | Bin 29 -> 29 bytes doc/pub/week43/ipynb/week43.ipynb | 425 +++++++++---------- doc/src/week43/week43.do.txt | 12 +- 7 files changed, 228 insertions(+), 390 deletions(-) diff --git a/doc/pub/week43/html/week43-bs.html b/doc/pub/week43/html/week43-bs.html index a62aae7aa..c2f5398e8 100644 --- a/doc/pub/week43/html/week43-bs.html +++ b/doc/pub/week43/html/week43-bs.html @@ -8,8 +8,7 @@ doconce format html week43.do.txt --html_style=bootstrap --pygments_html_style=d - -Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis + @@ -38,10 +37,6 @@ doconce format html week43.do.txt --html_style=bootstrap --pygments_html_style=d {'highest level': 2, 'sections': [('Plans for week 43', 2, None, 'plans-for-week-43'), ('Reading Recommendations', 2, None, 'reading-recommendations'), - ('Summary on Deep Learning Methods', - 2, - None, - 'summary-on-deep-learning-methods'), ('CNNs in brief', 2, None, 'cnns-in-brief'), ('Recurrent neural networks: Overarching view', 2, @@ -169,93 +164,10 @@ MathJax.Hub.Config({ - - -

 

 

 

-
-
-

Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis

-
+

ATITLE: Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis

@@ -270,19 +182,17 @@ MathJax.Hub.Config({

-

Aug 23, 2022

+

Oct 22, 2022


- - -
+

Plans for week 43

@@ -314,13 +224,6 @@ MathJax.Hub.Config({
  • Goodfellow et al, chapter 10 on Recurrent NNs, chapters 11 and 12 on various practicalities around deep learning are also recommended.
  • Aurelien Geron, chapter 14 on RNNs.
  • - -

    Summary on Deep Learning Methods

    - -

    We have studied fully connected neural networks (also called artifical nueral networks) and convolutional neural networks (CNNs).

    - -

    The first type of deep learning networks work very well on homogeneous and structured input data while CCNs are normally tailored to recognizing images.

    -

    CNNs in brief

    diff --git a/doc/pub/week43/html/week43-reveal.html b/doc/pub/week43/html/week43-reveal.html index dccbf2f00..02d1bfe16 100644 --- a/doc/pub/week43/html/week43-reveal.html +++ b/doc/pub/week43/html/week43-reveal.html @@ -9,8 +9,7 @@ doconce format html week43-reveal.html week43-reveal reveal --html_slide_theme=b - -Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis + @@ -167,9 +166,7 @@ MathJax.Hub.Config({
    -
    -

    Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis

    -
    +

    ATITLE: Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis

    @@ -184,9 +181,10 @@ MathJax.Hub.Config({

    -

    Aug 23, 2022

    +

    Oct 22, 2022


    +

    @@ -198,8 +196,8 @@ MathJax.Hub.Config({

    Plans for week 43

      -

    • Thursday: Summary of Convolutional Neural Networks from week 42 and Recurrent Neural Networks
    • -

    • Friday: Recurrent Neural Networks and other Deep Learning methods such as Generalized Adversarial Neural Networks. Start discussing Principal component analysis
    • +

    • Thursday: Convolutional Neural Networks, basic elements and
    • +

    • Friday: Recurrent Neural Networks and other Deep, Generalized Adversarial Neural Networ and autoencoders

    @@ -232,14 +230,6 @@ MathJax.Hub.Config({
    -
    -

    Summary on Deep Learning Methods

    - -

    We have studied fully connected neural networks (also called artifical nueral networks) and convolutional neural networks (CNNs).

    - -

    The first type of deep learning networks work very well on homogeneous and structured input data while CCNs are normally tailored to recognizing images.

    -
    -

    CNNs in brief

    diff --git a/doc/pub/week43/html/week43-solarized.html b/doc/pub/week43/html/week43-solarized.html index 883ebf249..c114e8c0b 100644 --- a/doc/pub/week43/html/week43-solarized.html +++ b/doc/pub/week43/html/week43-solarized.html @@ -8,8 +8,7 @@ doconce format html week43.do.txt --pygments_html_style=perldoc --html_style=sol - -Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis + @@ -65,10 +64,6 @@ div.toc p,a { {'highest level': 2, 'sections': [('Plans for week 43', 2, None, 'plans-for-week-43'), ('Reading Recommendations', 2, None, 'reading-recommendations'), - ('Summary on Deep Learning Methods', - 2, - None, - 'summary-on-deep-learning-methods'), ('CNNs in brief', 2, None, 'cnns-in-brief'), ('Recurrent neural networks: Overarching view', 2, @@ -197,9 +192,7 @@ MathJax.Hub.Config({ -
    -

    Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis

    -
    +

    ATITLE: Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis

    @@ -214,16 +207,17 @@ MathJax.Hub.Config({

    -

    Aug 23, 2022

    +

    Oct 22, 2022


    +











    Plans for week 43

      -
    • Thursday: Summary of Convolutional Neural Networks from week 42 and Recurrent Neural Networks
    • -
    • Friday: Recurrent Neural Networks and other Deep Learning methods such as Generalized Adversarial Neural Networks. Start discussing Principal component analysis
    • +
    • Thursday: Convolutional Neural Networks, basic elements and
    • +
    • Friday: Recurrent Neural Networks and other Deep, Generalized Adversarial Neural Networ and autoencoders
    Excellent lectures on CNNs and RNNs @@ -253,13 +247,6 @@ MathJax.Hub.Config({
  • Goodfellow et al, chapter 10 on Recurrent NNs, chapters 11 and 12 on various practicalities around deep learning are also recommended.
  • Aurelien Geron, chapter 14 on RNNs.
  • -









    -

    Summary on Deep Learning Methods

    - -

    We have studied fully connected neural networks (also called artifical nueral networks) and convolutional neural networks (CNNs).

    - -

    The first type of deep learning networks work very well on homogeneous and structured input data while CCNs are normally tailored to recognizing images.

    -









    CNNs in brief

    diff --git a/doc/pub/week43/html/week43.html b/doc/pub/week43/html/week43.html index d3ac5fdbe..dd0940ed0 100644 --- a/doc/pub/week43/html/week43.html +++ b/doc/pub/week43/html/week43.html @@ -8,8 +8,7 @@ doconce format html week43.do.txt --pygments_html_style=default --html_style=blo - -Week 43: Deep Learning: Recurrent Neural Networks and other Deep Learning Methods. Principal Component analysis +