From 04dff80908188c2488d4ea2ceb8333aeae5d86c6 Mon Sep 17 00:00:00 2001 From: mhjensen Date: Wed, 25 Nov 2020 10:38:50 +0100 Subject: [PATCH] test --- doc/pub/week48/html/._week48-bs000.html | 2 +- doc/pub/week48/html/._week48-bs001.html | 2 +- doc/pub/week48/html/._week48-bs031.html | 2 +- doc/pub/week48/html/._week48-bs032.html | 2 +- doc/pub/week48/html/._week48-bs033.html | 4 +- doc/pub/week48/html/._week48-bs034.html | 2 +- doc/pub/week48/html/._week48-bs038.html | 2 +- doc/pub/week48/html/._week48-bs039.html | 15 ++--- doc/pub/week48/html/._week48-bs040.html | 2 + doc/pub/week48/html/._week48-bs044.html | 3 + doc/pub/week48/html/._week48-bs046.html | 9 ++- doc/pub/week48/html/._week48-bs047.html | 3 +- doc/pub/week48/html/._week48-bs053.html | 9 ++- doc/pub/week48/html/._week48-bs054.html | 5 +- doc/pub/week48/html/week48-bs.html | 2 +- doc/pub/week48/html/week48-reveal.html | 65 ++++++++++++------- doc/pub/week48/html/week48-solarized.html | 62 +++++++++++------- doc/pub/week48/html/week48.html | 62 +++++++++++------- doc/pub/week48/ipynb/ipynb-week48-src.tar.gz | Bin 822634 -> 822634 bytes doc/pub/week48/ipynb/week48.ipynb | 59 ++++++++++------- 20 files changed, 190 insertions(+), 122 deletions(-) diff --git a/doc/pub/week48/html/._week48-bs000.html b/doc/pub/week48/html/._week48-bs000.html index f0fbdd390..341424093 100644 --- a/doc/pub/week48/html/._week48-bs000.html +++ b/doc/pub/week48/html/._week48-bs000.html @@ -260,7 +260,7 @@ MathJax.Hub.Config({
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

-

Nov 23, 2020

+

Nov 25, 2020


diff --git a/doc/pub/week48/html/._week48-bs001.html b/doc/pub/week48/html/._week48-bs001.html index dbe803cc2..f543da998 100644 --- a/doc/pub/week48/html/._week48-bs001.html +++ b/doc/pub/week48/html/._week48-bs001.html @@ -244,7 +244,7 @@ MathJax.Hub.Config({

Overview of week 48

diff --git a/doc/pub/week48/html/._week48-bs031.html b/doc/pub/week48/html/._week48-bs031.html index 122ca9cf3..048ac99f9 100644 --- a/doc/pub/week48/html/._week48-bs031.html +++ b/doc/pub/week48/html/._week48-bs031.html @@ -263,7 +263,7 @@ Some of the most common tasks are:
  • Classification: Outputs are divided into two or more classes. The goal is to produce a model that assigns inputs into one of these classes. An example is to identify digits based on pictures of hand-written ones. Classification is typically supervised learning.
  • Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.
  • Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.
    • -
  • Other unsupervised learning algortihms like Boltzmann machines
    • +
  • Other unsupervised learning algortihms like Boltzmann machines
    • diff --git a/doc/pub/week48/html/._week48-bs032.html b/doc/pub/week48/html/._week48-bs032.html index 53bdf16c7..fa11355c1 100644 --- a/doc/pub/week48/html/._week48-bs032.html +++ b/doc/pub/week48/html/._week48-bs032.html @@ -251,7 +251,7 @@ One of the major reasons is that they can be stacked layer-wise to build deep ne The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.

    -Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models. +Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.

    diff --git a/doc/pub/week48/html/._week48-bs033.html b/doc/pub/week48/html/._week48-bs033.html index 6b9f56342..3209bf89f 100644 --- a/doc/pub/week48/html/._week48-bs033.html +++ b/doc/pub/week48/html/._week48-bs033.html @@ -252,8 +252,8 @@ Why use a generative model rather than the more well known discriminative deep n

    1. A model for images could learn to draw new examples of cats and dogs, given a training dataset of images of cats and dogs.
      2. -
    2. Generate a sample of an ordered or disordered Ising model phase, having been given samples of such phases.
      3. -
    3. Model the trial function for Monte Carlo calculations
      4. +
    4. Generate a sample of an ordered or disordered phase, having been given samples of such phases.
      5. +
    5. Model the trial function for Monte Carlo calculations.
    diff --git a/doc/pub/week48/html/._week48-bs034.html b/doc/pub/week48/html/._week48-bs034.html index 781f8de5c..c8486fe74 100644 --- a/doc/pub/week48/html/._week48-bs034.html +++ b/doc/pub/week48/html/._week48-bs034.html @@ -249,7 +249,7 @@ MathJax.Hub.Config({
  • DNNs often have several hidden layers. A restricted Boltzmann machine has only one hidden layer, however several RBMs can be stacked to make up Deep Belief Networks, of which they constitute the building blocks.
    • -History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google. +History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google.

    diff --git a/doc/pub/week48/html/._week48-bs038.html b/doc/pub/week48/html/._week48-bs038.html index f3671d72d..753385a79 100644 --- a/doc/pub/week48/html/._week48-bs038.html +++ b/doc/pub/week48/html/._week48-bs038.html @@ -247,7 +247,7 @@ MathJax.Hub.Config({ The network layers:

      -
    1. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be the pixels of an image, the spin values of the Ising model, or coefficients representing speech.
      2. +
    2. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be given by the pixels of an image or coefficients representing speech, or the coordinates of a quantum mechanical state function.
    3. The function \( \mathbf{h} \) represents the hidden, or latent, layer. A vector of \( N \) elements (nodes). Also called "feature detectors".
    diff --git a/doc/pub/week48/html/._week48-bs039.html b/doc/pub/week48/html/._week48-bs039.html index 020724d8c..c2c0afe79 100644 --- a/doc/pub/week48/html/._week48-bs039.html +++ b/doc/pub/week48/html/._week48-bs039.html @@ -244,17 +244,14 @@ MathJax.Hub.Config({

    Goals

    -The goal of the hidden layer is to increase the model's expressive power. We encode complex interactions between visible variables by introducing additional, hidden variables that interact with visible degrees of freedom in a simple manner, yet still reproduce the complex correlations between visible degrees in the data once marginalized over (integrated out). +The goal of the hidden layer is to increase the model's expressive +power. We encode complex interactions between visible variables by +introducing additional, hidden variables that interact with visible +degrees of freedom in a simple manner, yet still reproduce the complex +correlations between visible degrees in the data once marginalized +over (integrated out).

    -Examples of this trick being employed in for example physics: - -

      -
    1. The Hubbard-Stratonovich transformation
      2. -
    2. The introduction of ghost fields in gauge theory
      3. -
    3. Shadow wave functions in Quantum Monte Carlo simulations
      4. -
    - The network parameters, to be optimized/learned:
      diff --git a/doc/pub/week48/html/._week48-bs040.html b/doc/pub/week48/html/._week48-bs040.html index e0c21ff59..bbb61cd38 100644 --- a/doc/pub/week48/html/._week48-bs040.html +++ b/doc/pub/week48/html/._week48-bs040.html @@ -242,6 +242,8 @@ MathJax.Hub.Config({

      Joint distribution

      + +

      The restricted Boltzmann machine is described by a Bolztmann distribution $$ \begin{align} diff --git a/doc/pub/week48/html/._week48-bs044.html b/doc/pub/week48/html/._week48-bs044.html index 63995740b..4a92abe90 100644 --- a/doc/pub/week48/html/._week48-bs044.html +++ b/doc/pub/week48/html/._week48-bs044.html @@ -273,6 +273,9 @@ learn the identity function under some constraints.

      Video on autoencoders +

      +See also A. Geron's textbook, chapter 15. +

      diff --git a/doc/pub/week48/html/._week48-bs046.html b/doc/pub/week48/html/._week48-bs046.html index 6f28fb8c2..1c2d69256 100644 --- a/doc/pub/week48/html/._week48-bs046.html +++ b/doc/pub/week48/html/._week48-bs046.html @@ -244,7 +244,13 @@ MathJax.Hub.Config({

      Reinforcement Learning

      -Reinforcement learning is a sub-area of machine learning. It studies +Reinforcement Learning (RL) is one of the most exciting fields of +Machine Learning today, and also one of the oldest. It has been around +since the 1950s, producing many interesting applications over the +years. + +

      +It studies how agents take actions based on trial and error, so as to maximize some notion of cumulative reward in a dynamic system or environment. Due to its generality, the problem has also been studied @@ -266,6 +272,7 @@ learning. Lecture on Reinforcement Learning.

      +See also A. Geron's textbook, chapter 16.

      @@ -1139,7 +1139,7 @@ One of the major reasons is that they can be stacked layer-wise to build deep ne The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.

      -Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models. +Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models. @@ -1155,8 +1155,8 @@ Why use a generative model rather than the more well known discriminative deep n

      1. A model for images could learn to draw new examples of cats and dogs, given a training dataset of images of cats and dogs.
        2. -

      2. Generate a sample of an ordered or disordered Ising model phase, having been given samples of such phases.
        3. -

      3. Model the trial function for Monte Carlo calculations
        4. +

      4. Generate a sample of an ordered or disordered phase, having been given samples of such phases.
        5. +

      5. Model the trial function for Monte Carlo calculations.

      @@ -1173,7 +1173,7 @@ Why use a generative model rather than the more well known discriminative deep n

    -History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google. +History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google. @@ -1253,7 +1253,7 @@ Here we take away all lateral connections between nodes in the visible layer as The network layers:

      -

    1. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be the pixels of an image, the spin values of the Ising model, or coefficients representing speech.
      2. +

    2. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be given by the pixels of an image or coefficients representing speech, or the coordinates of a quantum mechanical state function.

    3. The function \( \mathbf{h} \) represents the hidden, or latent, layer. A vector of \( N \) elements (nodes). Also called "feature detectors".
    @@ -1263,18 +1263,14 @@ Here we take away all lateral connections between nodes in the visible layer as

    Goals

    -The goal of the hidden layer is to increase the model's expressive power. We encode complex interactions between visible variables by introducing additional, hidden variables that interact with visible degrees of freedom in a simple manner, yet still reproduce the complex correlations between visible degrees in the data once marginalized over (integrated out). +The goal of the hidden layer is to increase the model's expressive +power. We encode complex interactions between visible variables by +introducing additional, hidden variables that interact with visible +degrees of freedom in a simple manner, yet still reproduce the complex +correlations between visible degrees in the data once marginalized +over (integrated out).

    -Examples of this trick being employed in for example physics: - -

      -

    1. The Hubbard-Stratonovich transformation
      2. -

    2. The introduction of ghost fields in gauge theory
      3. -

    3. Shadow wave functions in Quantum Monte Carlo simulations
      4. -
    -

    - The network parameters, to be optimized/learned:

      @@ -1287,6 +1283,8 @@ Examples of this trick being employed in for example physics:

      Joint distribution

      + +

      The restricted Boltzmann machine is described by a Bolztmann distribution

       
      $$ @@ -1430,6 +1428,9 @@ learn the identity function under some constraints.

      Video on autoencoders + +

      +See also A. Geron's textbook, chapter 15.

      @@ -1459,7 +1460,13 @@ See also the Reinforcement Learning

      -Reinforcement learning is a sub-area of machine learning. It studies +Reinforcement Learning (RL) is one of the most exciting fields of +Machine Learning today, and also one of the oldest. It has been around +since the 1950s, producing many interesting applications over the +years. + +

      +It studies how agents take actions based on trial and error, so as to maximize some notion of cumulative reward in a dynamic system or environment. Due to its generality, the problem has also been studied @@ -1479,6 +1486,9 @@ learning.

      Lecture on Reinforcement Learning. + +

      +See also A. Geron's textbook, chapter 16. @@ -1493,8 +1503,7 @@ rationality of doing so lies in that usually the source and target tasks have inter-correlations, and therefore either the features, samples, or models in the source task might provide useful information for us to better solve the target task. Transfer learning is a hot -research topic in recent years, with many problems still waiting to be -solved in this space. +research topic in recent years, with many problems still waiting to be studied.

      Lecture on transfer learning. @@ -1597,14 +1606,17 @@ stage in terms of explaining why those effective models work and how they work.

      -What is missing: the gap between correlation and causation Most +What is missing: the gap between correlation and causation. Standard Machine Learning is based on what e have called a frequentist approach. + +

      +Most machine learning techniques, especially the statistical ones, depend -highly on data correlation to make predictions and analyses. In +highly on correlations in data sets to make predictions and analyses. In contrast, rational humans tend to reply on clear and trustworthy causality relations obtained via logical reasoning on real and clear facts. It is one of the core goals of explainable machine learning to transition from solving problems by data correlation to solving -problems by logical reasoning. +problems by logical reasoning. Bayesian Machine Learning is one of the exciting research directions in this field. @@ -1632,7 +1644,10 @@ algorithms (on classic computers) to analyze and improve quantum computing systems.

      -Lecture on Quantum ML. +Lecture on Quantum ML. + +

      +Read interview with Maria Schuld on her work on Quantum Machine Learning. See also her recent textbook. diff --git a/doc/pub/week48/html/week48-solarized.html b/doc/pub/week48/html/week48-solarized.html index 98b603a21..10b838e36 100644 --- a/doc/pub/week48/html/week48-solarized.html +++ b/doc/pub/week48/html/week48-solarized.html @@ -190,7 +190,7 @@ MathJax.Hub.Config({

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

      -

      Nov 23, 2020

      +

      Nov 25, 2020












      @@ -198,7 +198,7 @@ MathJax.Hub.Config({

      Overview of week 48

      @@ -1100,7 +1100,7 @@ Some of the most common tasks are:
    1. Classification: Outputs are divided into two or more classes. The goal is to produce a model that assigns inputs into one of these classes. An example is to identify digits based on pictures of hand-written ones. Classification is typically supervised learning.
    2. Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.
    3. Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.
      4. -
    4. Other unsupervised learning algortihms like Boltzmann machines
      5. +
    5. Other unsupervised learning algortihms like Boltzmann machines
      6. @@ -1118,7 +1118,7 @@ One of the major reasons is that they can be stacked layer-wise to build deep ne The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.

      -Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models. +Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.











      @@ -1134,8 +1134,8 @@ Why use a generative model rather than the more well known discriminative deep n

      1. A model for images could learn to draw new examples of cats and dogs, given a training dataset of images of cats and dogs.
        2. -
      2. Generate a sample of an ordered or disordered Ising model phase, having been given samples of such phases.
        3. -
      3. Model the trial function for Monte Carlo calculations
        4. +
      4. Generate a sample of an ordered or disordered phase, having been given samples of such phases.
        5. +
      5. Model the trial function for Monte Carlo calculations.
      @@ -1150,7 +1150,7 @@ Why use a generative model rather than the more well known discriminative deep n
    6. DNNs often have several hidden layers. A restricted Boltzmann machine has only one hidden layer, however several RBMs can be stacked to make up Deep Belief Networks, of which they constitute the building blocks.
    -History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google. +History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google.











    @@ -1234,7 +1234,7 @@ Here we take away all lateral connections between nodes in the visible layer as The network layers:

      -
    1. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be the pixels of an image, the spin values of the Ising model, or coefficients representing speech.
      2. +
    2. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be given by the pixels of an image or coefficients representing speech, or the coordinates of a quantum mechanical state function.
    3. The function \( \mathbf{h} \) represents the hidden, or latent, layer. A vector of \( N \) elements (nodes). Also called "feature detectors".
    @@ -1243,17 +1243,14 @@ Here we take away all lateral connections between nodes in the visible layer as

    Goals

    -The goal of the hidden layer is to increase the model's expressive power. We encode complex interactions between visible variables by introducing additional, hidden variables that interact with visible degrees of freedom in a simple manner, yet still reproduce the complex correlations between visible degrees in the data once marginalized over (integrated out). +The goal of the hidden layer is to increase the model's expressive +power. We encode complex interactions between visible variables by +introducing additional, hidden variables that interact with visible +degrees of freedom in a simple manner, yet still reproduce the complex +correlations between visible degrees in the data once marginalized +over (integrated out).

    -Examples of this trick being employed in for example physics: - -

      -
    1. The Hubbard-Stratonovich transformation
      2. -
    2. The introduction of ghost fields in gauge theory
      3. -
    3. Shadow wave functions in Quantum Monte Carlo simulations
      4. -
    - The network parameters, to be optimized/learned:
      @@ -1265,6 +1262,8 @@ Examples of this trick being employed in for example physics:









      Joint distribution

      + +

      The restricted Boltzmann machine is described by a Bolztmann distribution $$ \begin{align} @@ -1402,6 +1401,9 @@ learn the identity function under some constraints.

      Video on autoencoders +

      +See also A. Geron's textbook, chapter 15. +











      @@ -1430,7 +1432,13 @@ See also the Reinforcement Learning

      -Reinforcement learning is a sub-area of machine learning. It studies +Reinforcement Learning (RL) is one of the most exciting fields of +Machine Learning today, and also one of the oldest. It has been around +since the 1950s, producing many interesting applications over the +years. + +

      +It studies how agents take actions based on trial and error, so as to maximize some notion of cumulative reward in a dynamic system or environment. Due to its generality, the problem has also been studied @@ -1452,6 +1460,7 @@ learning. Lecture on Reinforcement Learning.

      +See also A. Geron's textbook, chapter 16.









      Transfer learning

      @@ -1464,8 +1473,7 @@ rationality of doing so lies in that usually the source and target tasks have inter-correlations, and therefore either the features, samples, or models in the source task might provide useful information for us to better solve the target task. Transfer learning is a hot -research topic in recent years, with many problems still waiting to be -solved in this space. +research topic in recent years, with many problems still waiting to be studied.

      Lecture on transfer learning. @@ -1568,14 +1576,17 @@ stage in terms of explaining why those effective models work and how they work.

      -What is missing: the gap between correlation and causation Most +What is missing: the gap between correlation and causation. Standard Machine Learning is based on what e have called a frequentist approach. + +

      +Most machine learning techniques, especially the statistical ones, depend -highly on data correlation to make predictions and analyses. In +highly on correlations in data sets to make predictions and analyses. In contrast, rational humans tend to reply on clear and trustworthy causality relations obtained via logical reasoning on real and clear facts. It is one of the core goals of explainable machine learning to transition from solving problems by data correlation to solving -problems by logical reasoning. +problems by logical reasoning. Bayesian Machine Learning is one of the exciting research directions in this field.











      @@ -1603,7 +1614,10 @@ algorithms (on classic computers) to analyze and improve quantum computing systems.

      -Lecture on Quantum ML. +Lecture on Quantum ML. + +

      +Read interview with Maria Schuld on her work on Quantum Machine Learning. See also her recent textbook.











      diff --git a/doc/pub/week48/html/week48.html b/doc/pub/week48/html/week48.html index d1ffb4778..2b6701145 100644 --- a/doc/pub/week48/html/week48.html +++ b/doc/pub/week48/html/week48.html @@ -195,7 +195,7 @@ MathJax.Hub.Config({

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

      -

      Nov 23, 2020

      +

      Nov 25, 2020












      @@ -203,7 +203,7 @@ MathJax.Hub.Config({

      Overview of week 48

      @@ -1105,7 +1105,7 @@ Some of the most common tasks are:
    1. Classification: Outputs are divided into two or more classes. The goal is to produce a model that assigns inputs into one of these classes. An example is to identify digits based on pictures of hand-written ones. Classification is typically supervised learning.
    2. Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.
    3. Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.
      4. -
    4. Other unsupervised learning algortihms like Boltzmann machines
      5. +
    5. Other unsupervised learning algortihms like Boltzmann machines
      6. @@ -1123,7 +1123,7 @@ One of the major reasons is that they can be stacked layer-wise to build deep ne The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.

      -Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models. +Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.











      @@ -1139,8 +1139,8 @@ Why use a generative model rather than the more well known discriminative deep n

      1. A model for images could learn to draw new examples of cats and dogs, given a training dataset of images of cats and dogs.
        2. -
      2. Generate a sample of an ordered or disordered Ising model phase, having been given samples of such phases.
        3. -
      3. Model the trial function for Monte Carlo calculations
        4. +
      4. Generate a sample of an ordered or disordered phase, having been given samples of such phases.
        5. +
      5. Model the trial function for Monte Carlo calculations.
      @@ -1155,7 +1155,7 @@ Why use a generative model rather than the more well known discriminative deep n
    6. DNNs often have several hidden layers. A restricted Boltzmann machine has only one hidden layer, however several RBMs can be stacked to make up Deep Belief Networks, of which they constitute the building blocks.
    -History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google. +History: The RBM was developed by amongst others Geoffrey Hinton, called by some the "Godfather of Deep Learning", working with the University of Toronto and Google.











    @@ -1239,7 +1239,7 @@ Here we take away all lateral connections between nodes in the visible layer as The network layers:

      -
    1. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be the pixels of an image, the spin values of the Ising model, or coefficients representing speech.
      2. +
    2. A function \( \mathbf{x} \) that represents the visible layer, a vector of \( M \) elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be given by the pixels of an image or coefficients representing speech, or the coordinates of a quantum mechanical state function.
    3. The function \( \mathbf{h} \) represents the hidden, or latent, layer. A vector of \( N \) elements (nodes). Also called "feature detectors".
    @@ -1248,17 +1248,14 @@ Here we take away all lateral connections between nodes in the visible layer as

    Goals

    -The goal of the hidden layer is to increase the model's expressive power. We encode complex interactions between visible variables by introducing additional, hidden variables that interact with visible degrees of freedom in a simple manner, yet still reproduce the complex correlations between visible degrees in the data once marginalized over (integrated out). +The goal of the hidden layer is to increase the model's expressive +power. We encode complex interactions between visible variables by +introducing additional, hidden variables that interact with visible +degrees of freedom in a simple manner, yet still reproduce the complex +correlations between visible degrees in the data once marginalized +over (integrated out).

    -Examples of this trick being employed in for example physics: - -

      -
    1. The Hubbard-Stratonovich transformation
      2. -
    2. The introduction of ghost fields in gauge theory
      3. -
    3. Shadow wave functions in Quantum Monte Carlo simulations
      4. -
    - The network parameters, to be optimized/learned:
      @@ -1270,6 +1267,8 @@ Examples of this trick being employed in for example physics:









      Joint distribution

      + +

      The restricted Boltzmann machine is described by a Bolztmann distribution $$ \begin{align} @@ -1407,6 +1406,9 @@ learn the identity function under some constraints.

      Video on autoencoders +

      +See also A. Geron's textbook, chapter 15. +











      @@ -1435,7 +1437,13 @@ See also the Reinforcement Learning

      -Reinforcement learning is a sub-area of machine learning. It studies +Reinforcement Learning (RL) is one of the most exciting fields of +Machine Learning today, and also one of the oldest. It has been around +since the 1950s, producing many interesting applications over the +years. + +

      +It studies how agents take actions based on trial and error, so as to maximize some notion of cumulative reward in a dynamic system or environment. Due to its generality, the problem has also been studied @@ -1457,6 +1465,7 @@ learning. Lecture on Reinforcement Learning.

      +See also A. Geron's textbook, chapter 16.









      Transfer learning

      @@ -1469,8 +1478,7 @@ rationality of doing so lies in that usually the source and target tasks have inter-correlations, and therefore either the features, samples, or models in the source task might provide useful information for us to better solve the target task. Transfer learning is a hot -research topic in recent years, with many problems still waiting to be -solved in this space. +research topic in recent years, with many problems still waiting to be studied.

      Lecture on transfer learning. @@ -1573,14 +1581,17 @@ stage in terms of explaining why those effective models work and how they work.

      -What is missing: the gap between correlation and causation Most +What is missing: the gap between correlation and causation. Standard Machine Learning is based on what e have called a frequentist approach. + +

      +Most machine learning techniques, especially the statistical ones, depend -highly on data correlation to make predictions and analyses. In +highly on correlations in data sets to make predictions and analyses. In contrast, rational humans tend to reply on clear and trustworthy causality relations obtained via logical reasoning on real and clear facts. It is one of the core goals of explainable machine learning to transition from solving problems by data correlation to solving -problems by logical reasoning. +problems by logical reasoning. Bayesian Machine Learning is one of the exciting research directions in this field.











      @@ -1608,7 +1619,10 @@ algorithms (on classic computers) to analyze and improve quantum computing systems.

      -Lecture on Quantum ML. +Lecture on Quantum ML. + +

      +Read interview with Maria Schuld on her work on Quantum Machine Learning. See also her recent textbook.











      diff --git a/doc/pub/week48/ipynb/ipynb-week48-src.tar.gz b/doc/pub/week48/ipynb/ipynb-week48-src.tar.gz index 0a5b7cf54c14bc439dba2a8b922b642e9cfceae7..f82be520dec74f6e55a3a040c882776739ae76f4 100644 GIT binary patch delta 54 zcmaDg%jnfCBX;?24hAW;eU0p`?2N7KOs(w9t?VqV?5wTqY_04-L5@~-&Q^A=R(9^K I>^#Z60HodxssI20 delta 54 zcmaDg%jnfCBX;?24hFfL-Hq(6?2N7KOs(w9t?VqV?5wTqY_04-L5@~-&Q^A=R(9^K I>^#Z60I-V<@c;k- diff --git a/doc/pub/week48/ipynb/week48.ipynb b/doc/pub/week48/ipynb/week48.ipynb index 63833dde3..8f3b41c5e 100644 --- a/doc/pub/week48/ipynb/week48.ipynb +++ b/doc/pub/week48/ipynb/week48.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: **Nov 23, 2020**\n", + "Date: **Nov 25, 2020**\n", "\n", "Copyright 1999-2020, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n", "\n", @@ -18,7 +18,7 @@ "\n", "## Overview of week 48\n", "\n", - "* **Thursday**: Support Vector Machines, Kernels, Classification and Regression\n", + "* **Thursday**: Support Vector Machines: Kernels, Classification and Regression\n", "\n", "* **Friday**: Summary of course with perspectives for future studies\n", "\n", @@ -1064,7 +1064,7 @@ "\n", " * Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.\n", "\n", - " * Other unsupervised learning algortihms like Boltzmann machines\n", + " * Other unsupervised learning algortihms like **Boltzmann machines**\n", "\n", "\n", "\n", @@ -1076,7 +1076,7 @@ "\n", "The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images. \n", "\n", - "Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models. \n", + "Furthermore, they have been used to solve complicated [quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models](https://journals.aps.org/rmp/abstract/10.1103/RevModPhys.91.045002). \n", "\n", "\n", "## Boltzmann Machines\n", @@ -1089,9 +1089,9 @@ "\n", "a. A model for images could learn to draw new examples of cats and dogs, given a training dataset of images of cats and dogs.\n", "\n", - "b. Generate a sample of an ordered or disordered Ising model phase, having been given samples of such phases.\n", + "b. Generate a sample of an ordered or disordered phase, having been given samples of such phases.\n", "\n", - "c. Model the trial function for Monte Carlo calculations\n", + "c. Model the trial function for [Monte Carlo calculations](https://journals.aps.org/rmp/abstract/10.1103/RevModPhys.91.045002).\n", "\n", "\n", "## Some similarities and differences from DNNs\n", @@ -1102,7 +1102,7 @@ "\n", "3. DNNs often have several hidden layers. A restricted Boltzmann machine has only one hidden layer, however several RBMs can be stacked to make up Deep Belief Networks, of which they constitute the building blocks.\n", "\n", - "History: The RBM was developed by amongst others Geoffrey Hinton, called by some the \"Godfather of Deep Learning\", working with the University of Toronto and Google.\n", + "History: The RBM was developed by amongst others [Geoffrey Hinton](https://en.wikipedia.org/wiki/Geoffrey_Hinton), called by some the \"Godfather of Deep Learning\", working with the University of Toronto and Google.\n", "\n", "\n", "## Boltzmann machines (BM)\n", @@ -1159,20 +1159,18 @@ "## The network\n", "\n", "**The network layers**:\n", - "1. A function $\\mathbf{x}$ that represents the visible layer, a vector of $M$ elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be the pixels of an image, the spin values of the Ising model, or coefficients representing speech.\n", + "1. A function $\\mathbf{x}$ that represents the visible layer, a vector of $M$ elements (nodes). This layer represents both what the RBM might be given as training input, and what we want it to be able to reconstruct. This might for example be given by the pixels of an image or coefficients representing speech, or the coordinates of a quantum mechanical state function.\n", "\n", "2. The function $\\mathbf{h}$ represents the hidden, or latent, layer. A vector of $N$ elements (nodes). Also called \"feature detectors\".\n", "\n", "## Goals\n", "\n", - "The goal of the hidden layer is to increase the model's expressive power. We encode complex interactions between visible variables by introducing additional, hidden variables that interact with visible degrees of freedom in a simple manner, yet still reproduce the complex correlations between visible degrees in the data once marginalized over (integrated out).\n", - "\n", - "Examples of this trick being employed in for example physics: \n", - "1. The Hubbard-Stratonovich transformation\n", - "\n", - "2. The introduction of ghost fields in gauge theory\n", - "\n", - "3. Shadow wave functions in Quantum Monte Carlo simulations\n", + "The goal of the hidden layer is to increase the model's expressive\n", + "power. We encode complex interactions between visible variables by\n", + "introducing additional, hidden variables that interact with visible\n", + "degrees of freedom in a simple manner, yet still reproduce the complex\n", + "correlations between visible degrees in the data once marginalized\n", + "over (integrated out).\n", "\n", "**The network parameters, to be optimized/learned**:\n", "1. $\\mathbf{a}$ represents the visible bias, a vector of same length as $\\mathbf{x}$.\n", @@ -1182,6 +1180,7 @@ "3. $W$ represents the interaction weights, a matrix of size $M\\times N$.\n", "\n", "## Joint distribution\n", + "\n", "The restricted Boltzmann machine is described by a Bolztmann distribution" ] }, @@ -1360,7 +1359,7 @@ "\n", "[Video on autoencoders](https://www.coursera.org/lecture/building-deep-learning-models-with-tensorflow/autoencoders-1U4L3)\n", "\n", - "\n", + "See also A. Geron's textbook, chapter 15.\n", "\n", "## Bayesian Machine Learning\n", "\n", @@ -1379,7 +1378,12 @@ "\n", "## Reinforcement Learning\n", "\n", - "Reinforcement learning is a sub-area of machine learning. It studies\n", + "Reinforcement Learning (RL) is one of the most exciting fields of\n", + "Machine Learning today, and also one of the oldest. It has been around\n", + "since the 1950s, producing many interesting applications over the\n", + "years.\n", + "\n", + "It studies\n", "how agents take actions based on trial and error, so as to maximize\n", "some notion of cumulative reward in a dynamic system or\n", "environment. Due to its generality, the problem has also been studied\n", @@ -1398,6 +1402,7 @@ "\n", "[Lecture on Reinforcement Learning](https://www.youtube.com/watch?v=FgzM3zpZ55o&ab_channel=stanfordonline).\n", "\n", + "See also A. Geron's textbook, chapter 16.\n", "## Transfer learning\n", "\n", "The goal of transfer learning is to transfer the model or knowledge\n", @@ -1407,8 +1412,7 @@ "tasks have inter-correlations, and therefore either the features,\n", "samples, or models in the source task might provide useful information\n", "for us to better solve the target task. Transfer learning is a hot\n", - "research topic in recent years, with many problems still waiting to be\n", - "solved in this space.\n", + "research topic in recent years, with many problems still waiting to be studied.\n", "\n", "[Lecture on transfer learning](https://www.ias.edu/video/machinelearning/2020/0331-SamoryKpotufe).\n", "\n", @@ -1485,14 +1489,16 @@ "stage in terms of explaining why those effective models work and how\n", "they work.\n", "\n", - "What is missing: the gap between correlation and causation Most\n", + "**What is missing: the gap between correlation and causation**. Standard Machine Learning is based on what e have called a frequentist approach. \n", + "\n", + "Most\n", "machine learning techniques, especially the statistical ones, depend\n", - "highly on data correlation to make predictions and analyses. In\n", + "highly on correlations in data sets to make predictions and analyses. In\n", "contrast, rational humans tend to reply on clear and trustworthy\n", "causality relations obtained via logical reasoning on real and clear\n", "facts. It is one of the core goals of explainable machine learning to\n", "transition from solving problems by data correlation to solving\n", - "problems by logical reasoning.\n", + "problems by logical reasoning. Bayesian Machine Learning is one of the exciting research directions in this field.\n", "\n", "## Quantum machine learning\n", "\n", @@ -1513,7 +1519,10 @@ "algorithms (on classic computers) to analyze and improve quantum\n", "computing systems.\n", "\n", - "[Lecture on Quantum ML](https://www.youtube.com/watch?v=Lbndu5EIWvI&ab_channel=%E6%85%B6%E6%87%89%E7%BE%A9%E5%A1%BEKeioUniversity).\n", + "[Lecture on Quantum ML](https://www.youtube.com/watch?v=Xh9pUu3-WxM&ab_channel=InstituteforPure%26AppliedMathematics%28IPAM%29).\n", + "\n", + "[Read interview with Maria Schuld on her work on Quantum Machine Learning](https://physics.aps.org/articles/v13/179?utm_campaign=weekly&utm_medium=email&utm_source=emailalert). See also [her recent textbook](https://www.springer.com/gp/book/9783319964232). \n", + "\n", "\n", "## Quantum machine learning algorithms based on linear algebra\n", "\n", @@ -1569,6 +1578,8 @@ "\n", "And much more.\n", "\n", + "\n", + "\n", "## The last words?\n", "\n", "Early computer scientist Alan Kay said, **The best way to predict the\n",