fixed info theo sections and ordering and aligned deep dive names

slds-lmu · Jan 15, 2024 · ffc0a95 · ffc0a95
1 parent 9b472ea
commit ffc0a95
Show file tree

Hide file tree

Showing 11 changed files with 54 additions and 12 deletions.
diff --git a/content/chapters/02_supervised_regression/02-02-ols.md b/content/chapters/02_supervised_regression/02-02-ols.md
@@ -1,5 +1,5 @@
 ---
-title: "Chapter 02.02: Deep Dive: Proof OLS Regression"
+title: "Chapter 02.02: Proof OLS Regression: Deep Dive"
 weight: 2002
 ---
 In this section, we provide you with a proof for the ordinary least squares (OLS) method.

diff --git a/content/chapters/13_information_theory/13-01-entropy.md b/content/chapters/13_information_theory/13-01-entropy.md
@@ -1,5 +1,5 @@
 ---
-title: "Chapter 13.01: Entropy"
+title: "Chapter 13.01: Entropy I"
 weight: 13001
 ---
 We introduce entropy, which expresses the expected information for discrete random variables, as a central concept in information theory. 

diff --git a/...rs/13_information_theory/13-02-entropy.md → ...s/13_information_theory/13-02-entropy2.md b/...rs/13_information_theory/13-02-entropy.md → ...s/13_information_theory/13-02-entropy2.md
@@ -1,5 +1,5 @@
 ---
-title: "Chapter 13.02: Entropy"
+title: "Chapter 13.02: Entropy II"
 weight: 13002
 ---
 We continue our discussion about entropy and introduce joint entropy, the uniqueness theorem and the maximum entropy principle.

diff --git a/...rmation_theory/13-06-cross-entropy-kld.md → ...rmation_theory/13-05-cross-entropy-kld.md b/...rmation_theory/13-06-cross-entropy-kld.md → ...rmation_theory/13-05-cross-entropy-kld.md
@@ -1,6 +1,6 @@
 ---
-title: "Chapter 13.06: Cross-Entropy, KL and Source Coding"
-weight: 13006
+title: "Chapter 13.05: Cross-Entropy and KL"
+weight: 13005
 ---
 We introduce cross-entropy as a further information-theoretic concept and discuss the connection between entropy, cross-entropy, and Kullback-Leibler divergence.  
 

diff --git a/...hapters/13_information_theory/13-07-ml.md → ...hapters/13_information_theory/13-06-ml.md b/...hapters/13_information_theory/13-07-ml.md → ...hapters/13_information_theory/13-06-ml.md
@@ -1,6 +1,6 @@
 ---
-title: "Chapter 13.07: Information Theory for Machine Learning"
-weight: 13007
+title: "Chapter 13.06: Information Theory for Machine Learning"
+weight: 13006
 ---
 In this section, we discuss how information-theoretic concepts are used in machine learning and demonstrate the equivalence of KL minimization and maximum likelihood maximization, as well as how (cross-)entropy can be used as a loss function. 
 

diff --git a/...3_information_theory/13-08-mutual-info.md → ...3_information_theory/13-07-mutual-info.md b/...3_information_theory/13-08-mutual-info.md → ...3_information_theory/13-07-mutual-info.md
@@ -1,6 +1,6 @@
 ---
-title: "Chapter 13.08: Joint Entropy and Mutual Information"
-weight: 13008
+title: "Chapter 13.07: Joint Entropy and Mutual Information I"
+weight: 13007
 ---
 Information theory also provides means of quantifying relations between two random variables that extend the concept of (linear) correlation. We discuss joint entropy, conditional entropy, and mutual information in this context. 
 

diff --git a/content/chapters/13_information_theory/13-08-mutual-info2.md b/content/chapters/13_information_theory/13-08-mutual-info2.md
@@ -0,0 +1,15 @@
+---
+title: "Chapter 13.08: Joint Entropy and Mutual Information II"
+weight: 13008
+---
+Information theory also provides means of quantifying relations between two random variables that extend the concept of (linear) correlation. We discuss joint entropy, conditional entropy, and mutual information in this context. 
+
+<!--more-->
+
+### Lecture video
+
+{{< video id="" >}}
+
+### Lecture slides
+
+{{< pdfjs file="https://github.com/slds-lmu/lecture_sl/raw/main/slides-pdf/slides-info-mutual-info2.pdf" >}}
diff --git a/..._information_theory/13-05-sourcecoding.md → ..._information_theory/13-09-sourcecoding.md b/..._information_theory/13-05-sourcecoding.md → ..._information_theory/13-09-sourcecoding.md
@@ -1,6 +1,6 @@
 ---
-title: "Chapter 13.05: Entropy and Optimal Code Length"
-weight: 13005
+title: "Chapter 13.09: Entropy and Optimal Code Length I"
+weight: 13009
 ---
 In this section, we introduce source coding and discuss how entropy can be understood as optimal code length. 
 

diff --git a/content/chapters/13_information_theory/13-10-sourcecoding2.md b/content/chapters/13_information_theory/13-10-sourcecoding2.md
@@ -0,0 +1,15 @@
+---
+title: "Chapter 13.10: Entropy and Optimal Code Length II"
+weight: 13010
+---
+In this section, we continue our discussion on source coding and its relation to entropy. 
+
+<!--more-->
+
+### Lecture video
+
+{{< video id="" >}}
+
+### Lecture slides
+
+{{< pdfjs file="https://github.com/slds-lmu/lecture_sl/raw/main/slides-pdf/slides-info-sourcecoding2.pdf" >}}
diff --git a/content/chapters/13_information_theory/13-11-mi-deepdive.md b/content/chapters/13_information_theory/13-11-mi-deepdive.md
@@ -0,0 +1,12 @@
+---
+title: "Chapter 13.11: MI under Reparametrization: Deep Dive"
+weight: 13011
+---
+In this deep dive, we discuss the invariance of MI under certain reparametrizations. 
+
+<!--more-->
+
+
+### Lecture slides
+
+{{< pdfjs file="https://github.com/slds-lmu/lecture_sl/raw/main/slides-pdf/slides-info-mi-deepdive.pdf" >}}
diff --git a/content/chapters/15_regularization/15-09-lasso-deep.md b/content/chapters/15_regularization/15-09-lasso-deep.md
@@ -1,5 +1,5 @@
 ---
-title: "Chapter 15.09: Soft-thresholding and L1 regularization deep-dive"
+title: "Chapter 15.09: Soft-thresholding and L1 regularization: Deep Dive"
 weight: 15009
 ---
 In this section, we prove the previously stated proposition regarding soft-thresholding and L1 regularization.