From 9b1d005b9b114a66e122ee134910c8726afcdab4 Mon Sep 17 00:00:00 2001 From: Morten Hjorth-Jensen Date: Mon, 23 Sep 2024 06:15:55 +0200 Subject: [PATCH] update --- doc/pub/week39/html/week39-bs.html | 26 +- doc/pub/week39/html/week39-reveal.html | 30 - doc/pub/week39/html/week39-solarized.html | 31 - doc/pub/week39/html/week39.html | 31 - doc/pub/week39/ipynb/ipynb-week39-src.tar.gz | Bin 192 -> 192 bytes doc/pub/week39/ipynb/week39.ipynb | 613 +++++++++---------- doc/src/week39/week39.do.txt | 10 - 7 files changed, 305 insertions(+), 436 deletions(-) diff --git a/doc/pub/week39/html/week39-bs.html b/doc/pub/week39/html/week39-bs.html index 9981773ad..e57267e6f 100644 --- a/doc/pub/week39/html/week39-bs.html +++ b/doc/pub/week39/html/week39-bs.html @@ -242,7 +242,6 @@ doconce format html week39.do.txt --html_style=bootstrap --pygments_html_style=d 2, None, 'the-syntax-a-dot-b-when-finding-the-dot-product'), - ('Recommended to avoid', 2, None, 'recommended-to-avoid'), ('Using Autograd with OLS', 2, None, 'using-autograd-with-ols'), ('Same code but now with momentum gradient descent', 2, @@ -359,7 +358,7 @@ MathJax.Hub.Config({
  • Program example for gradient descent with Ridge Regression
  • Using gradient descent methods, limitations
  • Improving gradient descent with momentum
    • -
  • Same code but now with momentum gradient descent
    • +
  • Same code but now with momentum gradient descent
  • Overview video on Stochastic Gradient Descent
  • Batches and mini-batches
  • Stochastic Gradient Descent (SGD)
    • @@ -391,17 +390,16 @@ MathJax.Hub.Config({
  • Using recursion
  • Unsupported functions
  • The syntax a.dot(b) when finding the dot product
    • -
  • Recommended to avoid
    • -
  • Using Autograd with OLS
    • -
  • Same code but now with momentum gradient descent
    • -
  • But none of these can compete with Newton's method
    • -
  • Including Stochastic Gradient Descent with Autograd
    • -
  • Same code but now with momentum gradient descent
    • -
  • Similar (second order function now) problem but now with AdaGrad
    • -
  • RMSprop for adaptive learning rate with Stochastic Gradient Descent
    • -
  • And finally "ADAM":"https://arxiv.org/pdf/1412.6980.pdf"
    • -
  • And Logistic Regression
    • -
  • Introducing "JAX":"https://jax.readthedocs.io/en/latest/"
    • +
  • Using Autograd with OLS
    • +
  • Same code but now with momentum gradient descent
    • +
  • But none of these can compete with Newton's method
    • +
  • Including Stochastic Gradient Descent with Autograd
    • +
  • Same code but now with momentum gradient descent
    • +
  • Similar (second order function now) problem but now with AdaGrad
    • +
  • RMSprop for adaptive learning rate with Stochastic Gradient Descent
    • +
  • And finally "ADAM":"https://arxiv.org/pdf/1412.6980.pdf"
    • +
  • And Logistic Regression
    • +
  • Introducing "JAX":"https://jax.readthedocs.io/en/latest/"
    • @@ -456,7 +454,7 @@ MathJax.Hub.Config({
  • 9
  • 10
  • ...
    • -
  • 90
    • +
  • 89
  • »
    • diff --git a/doc/pub/week39/html/week39-reveal.html b/doc/pub/week39/html/week39-reveal.html index bc484770c..88b9db0f9 100644 --- a/doc/pub/week39/html/week39-reveal.html +++ b/doc/pub/week39/html/week39-reveal.html @@ -3106,36 +3106,6 @@ x = np.array([3.0,Recommended to avoid -

    The documentation recommends to avoid inplace operations such as

    - - -
    -
    -
    -
    -
    - 
    a += b
-a -= b
-a*= b
-a /=b
-
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    - -

    Using Autograd with OLS

    diff --git a/doc/pub/week39/html/week39-solarized.html b/doc/pub/week39/html/week39-solarized.html index 121eb1b65..d553b3e72 100644 --- a/doc/pub/week39/html/week39-solarized.html +++ b/doc/pub/week39/html/week39-solarized.html @@ -269,7 +269,6 @@ div.toc p,a { 2, None, 'the-syntax-a-dot-b-when-finding-the-dot-product'), - ('Recommended to avoid', 2, None, 'recommended-to-avoid'), ('Using Autograd with OLS', 2, None, 'using-autograd-with-ols'), ('Same code but now with momentum gradient descent', 2, @@ -3044,36 +3043,6 @@ x = np.array([3.0,Recommended to avoid -

    The documentation recommends to avoid inplace operations such as

    - - -
    -
    -
    -
    -
    - 
    a += b
-a -= b
-a*= b
-a /=b
-
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    - -









    Using Autograd with OLS

    diff --git a/doc/pub/week39/html/week39.html b/doc/pub/week39/html/week39.html index a829601d8..43852bafc 100644 --- a/doc/pub/week39/html/week39.html +++ b/doc/pub/week39/html/week39.html @@ -346,7 +346,6 @@ div.toc p,a { 2, None, 'the-syntax-a-dot-b-when-finding-the-dot-product'), - ('Recommended to avoid', 2, None, 'recommended-to-avoid'), ('Using Autograd with OLS', 2, None, 'using-autograd-with-ols'), ('Same code but now with momentum gradient descent', 2, @@ -3121,36 +3120,6 @@ x = np.a -









    - -

    The documentation recommends to avoid inplace operations such as

    - - -
    -
    -
    -
    -
    - 
    a += b
-a -= b
-a*= b
-a /=b
-
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    - -









    Using Autograd with OLS

    diff --git a/doc/pub/week39/ipynb/ipynb-week39-src.tar.gz b/doc/pub/week39/ipynb/ipynb-week39-src.tar.gz index 97d2e6938ed236b4926d7c6b36ad6d00fa3c3919..39737c46da2ff02055fc04a4e3776328d8684419 100644 GIT binary patch literal 192 zcmV;x06+g9iwFR2>+og(1MSbv3c@f92XN1Oiafz+U0d-exPu2l#24sTbak$sZHMmd z-3RDN@iIi{@A4-kgk+zt*4s4pcR!m9Aw)0+eJ%talFY|?Kq&{x#DY=5ITt`^!kL%> zneL>Q#(8PGQ>x;O+M#|o*Nq*IANGu|z%&2Ep->JsyVe&*gEk&BV@kLomdP?!b*nST u4Z6Ms7O#!62vWBo^IUmlw7f*MH76@87e~K-CJ2Hc_}T;WUD^Qv2mk;qrdOZ< literal 192 zcmV;x06+g9iwFSY>hNX&1MSaC3c@fD24L4c#hjod=22V&J@X!=C9Cc;=rtmde3)-}%yL(8kNmm