diff --git a/doc/pub/week42/html/._week42-bs000.html b/doc/pub/week42/html/._week42-bs000.html index 18e3ee286..bdb5f998a 100644 --- a/doc/pub/week42/html/._week42-bs000.html +++ b/doc/pub/week42/html/._week42-bs000.html @@ -368,7 +368,7 @@ MathJax.Hub.Config({
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

-

Oct 19, 2021

+

Oct 20, 2021


diff --git a/doc/pub/week42/html/._week42-bs003.html b/doc/pub/week42/html/._week42-bs003.html index dca79e393..e8ce13760 100644 --- a/doc/pub/week42/html/._week42-bs003.html +++ b/doc/pub/week42/html/._week42-bs003.html @@ -352,9 +352,24 @@ MathJax.Hub.Config({

Solving ODEs with Deep Learning

+

+
+

The Universal Approximation Theorem states that a neural network can approximate any function at a single hidden layer along with one input and output layer to any given precision. +

+
+ + +

+

+
+

+An Introduction to Neural Network Methods for Differential Equations, by Yadav and Kumar. +

+
+

diff --git a/doc/pub/week42/html/week42-bs.html b/doc/pub/week42/html/week42-bs.html index 18e3ee286..bdb5f998a 100644 --- a/doc/pub/week42/html/week42-bs.html +++ b/doc/pub/week42/html/week42-bs.html @@ -368,7 +368,7 @@ MathJax.Hub.Config({

[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

-

Oct 19, 2021

+

Oct 20, 2021


diff --git a/doc/pub/week42/html/week42-reveal.html b/doc/pub/week42/html/week42-reveal.html index bf9f41261..fdfb2efaf 100644 --- a/doc/pub/week42/html/week42-reveal.html +++ b/doc/pub/week42/html/week42-reveal.html @@ -148,7 +148,7 @@ MathJax.Hub.Config({

[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

 
-

Oct 19, 2021

+

Oct 20, 2021


@@ -200,10 +200,21 @@ we will also study the usage of Solving ODEs with Deep Learning +

+

+

The Universal Approximation Theorem states that a neural network can approximate any function at a single hidden layer along with one input and output layer to any given precision. +

+ +

+

+Book on solving differential equations with ML methods +

+An Introduction to Neural Network Methods for Differential Equations, by Yadav and Kumar. +

diff --git a/doc/pub/week42/html/week42-solarized.html b/doc/pub/week42/html/week42-solarized.html index 60fef723c..3420b64c4 100644 --- a/doc/pub/week42/html/week42-solarized.html +++ b/doc/pub/week42/html/week42-solarized.html @@ -283,7 +283,7 @@ MathJax.Hub.Config({
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

-

Oct 19, 2021

+

Oct 20, 2021












@@ -335,10 +335,23 @@ we will also study the usage of Solving ODEs with Deep Learning +

+

+

The Universal Approximation Theorem states that a neural network can approximate any function at a single hidden layer along with one input and output layer to any given precision. +

+ + +

+

+Book on solving differential equations with ML methods +

+An Introduction to Neural Network Methods for Differential Equations, by Yadav and Kumar. +

+











diff --git a/doc/pub/week42/html/week42.html b/doc/pub/week42/html/week42.html index 626efde76..93500401d 100644 --- a/doc/pub/week42/html/week42.html +++ b/doc/pub/week42/html/week42.html @@ -288,7 +288,7 @@ MathJax.Hub.Config({

[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

-

Oct 19, 2021

+

Oct 20, 2021












@@ -340,10 +340,23 @@ we will also study the usage of Solving ODEs with Deep Learning +

+

+

The Universal Approximation Theorem states that a neural network can approximate any function at a single hidden layer along with one input and output layer to any given precision. +

+ + +

+

+Book on solving differential equations with ML methods +

+An Introduction to Neural Network Methods for Differential Equations, by Yadav and Kumar. +

+











diff --git a/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz b/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz index a6a838731..a5503eb12 100644 Binary files a/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz and b/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz differ diff --git a/doc/pub/week42/ipynb/week42.ipynb b/doc/pub/week42/ipynb/week42.ipynb index 8c046bd8f..7676499c9 100644 --- a/doc/pub/week42/ipynb/week42.ipynb +++ b/doc/pub/week42/ipynb/week42.ipynb @@ -10,7 +10,7 @@ " \n", "**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n", "\n", - "Date: **Oct 19, 2021**\n", + "Date: **Oct 20, 2021**\n", "\n", "Copyright 1999-2021, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n", "\n", @@ -40,6 +40,8 @@ "\n", "\n", "\n", + "\n", + "\n", "## Using Automatic differentiation\n", "\n", "In our discussions of ordinary differential equations \n", @@ -50,7 +52,15 @@ "\n", "The Universal Approximation Theorem states that a neural network can\n", "approximate any function at a single hidden layer along with one input\n", - "and output layer to any given precision. \n", + "and output layer to any given precision.\n", + "\n", + "\n", + "\n", + "**Book on solving differential equations with ML methods.**\n", + "\n", + "[An Introduction to Neural Network Methods for Differential Equations](https://www.springer.com/gp/book/9789401798150), by Yadav and Kumar.\n", + "\n", + "\n", "\n", "\n", "## Ordinary Differential Equations\n", diff --git a/doc/src/week42/week42.do.txt b/doc/src/week42/week42.do.txt index 205210e77..66c31fe7b 100644 --- a/doc/src/week42/week42.do.txt +++ b/doc/src/week42/week42.do.txt @@ -21,6 +21,8 @@ DATE: today * "Video on Convolutional Neural Networks from MIT":"https://www.youtube.com/watch?v=iaSUYvmCekI&ab_channel=AlexanderAmini" !eblock + + !split ===== Using Automatic differentiation ===== @@ -31,9 +33,15 @@ we will also study the usage of "Autograd":"https://www.youtube.com/watch?v=fRf4 !split ===== Solving ODEs with Deep Learning ===== +!bblock The Universal Approximation Theorem states that a neural network can approximate any function at a single hidden layer along with one input and output layer to any given precision. +!eblock + +!bblock Book on solving differential equations with ML methods +"An Introduction to Neural Network Methods for Differential Equations":"https://www.springer.com/gp/book/9789401798150", by Yadav and Kumar. +!eblock !split