From 6f019736cfdc2f510bae152d84edd534ab010801 Mon Sep 17 00:00:00 2001 From: Morten Hjorth-Jensen Date: Thu, 21 Dec 2023 20:04:03 +0100 Subject: [PATCH] update --- doc/pub/week1/html/week1-bs.html | 33 ++++--- doc/pub/week1/html/week1-reveal.html | 34 ++++--- doc/pub/week1/html/week1-solarized.html | 31 +++--- doc/pub/week1/html/week1.html | 31 +++--- doc/pub/week1/ipynb/ipynb-week1-src.tar.gz | Bin 191 -> 190 bytes doc/pub/week1/ipynb/week1.ipynb | 106 +++++++++++---------- doc/pub/week1/pdf/week1.pdf | Bin 227173 -> 227298 bytes doc/src/week1/week1.do.txt | 21 ++-- 8 files changed, 149 insertions(+), 107 deletions(-) diff --git a/doc/pub/week1/html/week1-bs.html b/doc/pub/week1/html/week1-bs.html index bf11fe47..60b11b46 100644 --- a/doc/pub/week1/html/week1-bs.html +++ b/doc/pub/week1/html/week1-bs.html @@ -8,8 +8,8 @@ - -January 23-27: Advanced machine learning and data analysis for the physical sciences + +January 15-19: Advanced machine learning and data analysis for the physical sciences @@ -94,7 +94,7 @@ - January 23-27: Advanced machine learning and data analysis for the physical sciences + January 15-19: Advanced machine learning and data analysis for the physical sciences
-
  • Final oral examination to be agreed upon
    • +
  • No exam, only two projects whoch count 1/2 of the final grade each
  • All info at the GitHub address https://github.com/CompPhysics/AdvancedMachineLearning

    • Deep learning methods covered

      -
    1. Feed forward neural networks (NNs)
      2. -
    2. Convolutional neural networks (CNNs)
      3. -
    3. Recurrent neural networks (RNNs)
      4. -
    4. Autoencoders (AEs) and variational autoencoders (VAEe)
      5. -
    5. Generative Adversarial Networks (GANs)
      6. +
    6. Deep learning, classics +
        +
      1. Feed forward neural networks and its mathematics (NNs)
        2. +
      2. Convolutional neural networks (CNNs)
        3. +
      3. Recurrent neural networks (RNNs)
        4. +
      4. Autoencoders and principal component analysis
        5. +
      5. Physics informed neural networks
        6. +
      +
    7. Deeep learning, generative methods +
        +
      1. Boltzmann machines and energy based methods
        2. +
      2. Autoencodervariational autoencoders (VAEe)
        3. +
      3. Generative Adversarial Networks (GANs)
        4. +

    The lecture notes contain a more in depth discussion of these methods, in particular on neural networks, CNNs and RNNs.

    diff --git a/doc/pub/week1/html/week1-reveal.html b/doc/pub/week1/html/week1-reveal.html index aded3b99..fcc961fd 100644 --- a/doc/pub/week1/html/week1-reveal.html +++ b/doc/pub/week1/html/week1-reveal.html @@ -9,8 +9,8 @@ - -January 23-27: Advanced machine learning and data analysis for the physical sciences + +January 15-19: Advanced machine learning and data analysis for the physical sciences @@ -168,7 +168,7 @@
    -

    January 23-27: Advanced machine learning and data analysis for the physical sciences

    +

    January 15-19: Advanced machine learning and data analysis for the physical sciences

    @@ -184,7 +184,7 @@

    January 23-27: Advanced machine learning and dat
    -

    Jan 25, 2023

    +

    Dec 21, 2023


    @@ -207,9 +207,6 @@

    Overview of week first week

  • Eventual start with theory discussions on deep learning methods
    • - - -Video of lecture
    @@ -228,7 +225,7 @@

    Practicalities and possible projec

  • and many other research paths and topics

    • -

  • Final oral examination to be agreed upon
    • +

  • No exam, only two projects whoch count 1/2 of the final grade each

  • All info at the GitHub address https://github.com/CompPhysics/AdvancedMachineLearning

    • @@ -237,11 +234,22 @@

    Practicalities and possible projec

    Deep learning methods covered

      -

    1. Feed forward neural networks (NNs)
      2. -

    2. Convolutional neural networks (CNNs)
      3. -

    3. Recurrent neural networks (RNNs)
      4. -

    4. Autoencoders (AEs) and variational autoencoders (VAEe)
      5. -

    5. Generative Adversarial Networks (GANs)
      6. +

    6. Deep learning, classics +
        +

      1. Feed forward neural networks and its mathematics (NNs)
        2. +

      2. Convolutional neural networks (CNNs)
        3. +

      3. Recurrent neural networks (RNNs)
        4. +

      4. Autoencoders and principal component analysis
        5. +

      5. Physics informed neural networks
        6. +
      +

      +

    7. Deeep learning, generative methods +
        +

      1. Boltzmann machines and energy based methods
        2. +

      2. Autoencodervariational autoencoders (VAEe)
        3. +

      3. Generative Adversarial Networks (GANs)
        4. +
      +

    The lecture notes contain a more in depth discussion of these methods, in particular on neural networks, CNNs and RNNs.

    diff --git a/doc/pub/week1/html/week1-solarized.html b/doc/pub/week1/html/week1-solarized.html index a850bd8f..66a197e5 100644 --- a/doc/pub/week1/html/week1-solarized.html +++ b/doc/pub/week1/html/week1-solarized.html @@ -8,8 +8,8 @@ - -January 23-27: Advanced machine learning and data analysis for the physical sciences + +January 15-19: Advanced machine learning and data analysis for the physical sciences @@ -115,7 +115,7 @@
    -

    January 23-27: Advanced machine learning and data analysis for the physical sciences

    +

    January 15-19: Advanced machine learning and data analysis for the physical sciences

    @@ -131,7 +131,7 @@

    January 23-27: Advanced machine learning and data analysis for the physical
    -

    Jan 25, 2023

    +

    Dec 21, 2023


    @@ -150,8 +150,6 @@

    Overview of week first week

    -Video of lecture -









    Practicalities and possible projects

    @@ -167,18 +165,27 @@

    Practicalities and possible projec
  • Bayesian Machine Learning and Gaussian processes
  • and many other research paths and topics
    • -
  • Final oral examination to be agreed upon
    • +
  • No exam, only two projects whoch count 1/2 of the final grade each
  • All info at the GitHub address https://github.com/CompPhysics/AdvancedMachineLearning










    • Deep learning methods covered

      -
    1. Feed forward neural networks (NNs)
      2. -
    2. Convolutional neural networks (CNNs)
      3. -
    3. Recurrent neural networks (RNNs)
      4. -
    4. Autoencoders (AEs) and variational autoencoders (VAEe)
      5. -
    5. Generative Adversarial Networks (GANs)
      6. +
    6. Deep learning, classics +
        +
      1. Feed forward neural networks and its mathematics (NNs)
        2. +
      2. Convolutional neural networks (CNNs)
        3. +
      3. Recurrent neural networks (RNNs)
        4. +
      4. Autoencoders and principal component analysis
        5. +
      5. Physics informed neural networks
        6. +
      +
    7. Deeep learning, generative methods +
        +
      1. Boltzmann machines and energy based methods
        2. +
      2. Autoencodervariational autoencoders (VAEe)
        3. +
      3. Generative Adversarial Networks (GANs)
        4. +

    The lecture notes contain a more in depth discussion of these methods, in particular on neural networks, CNNs and RNNs.

    diff --git a/doc/pub/week1/html/week1.html b/doc/pub/week1/html/week1.html index 76e08ee8..67c548c5 100644 --- a/doc/pub/week1/html/week1.html +++ b/doc/pub/week1/html/week1.html @@ -8,8 +8,8 @@ - -January 23-27: Advanced machine learning and data analysis for the physical sciences + +January 15-19: Advanced machine learning and data analysis for the physical sciences