Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

new links for regu #306

Merged
merged 2 commits into from
Jun 4, 2024
Merged

new links for regu #306

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
93a32f3
new links for regu
manuelhelmerichs Jun 4, 2024
e48b12b
fixed pdf link
manuelhelmerichs Jun 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions content/chapters/15_regularization/15-07-nonlin.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: "Chapter 15.07: Regularization in NonLinear Models"
title: "Chapter 15.07: Non-Linear Models and Structural Risk Minimization"
weight: 15007
---
In this section, we demonstrate regularization in non-linear models like neural networks.
Expand All @@ -8,7 +8,7 @@ In this section, we demonstrate regularization in non-linear models like neural

### Lecture video

{{< video id="MdwK9e2wR_U" >}}
{{< video id="_jNeD2AUJqI" >}}

### Lecture slides

Expand Down
4 changes: 2 additions & 2 deletions content/chapters/15_regularization/15-08-bayes.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: "Chapter 15.08: Regularization and Bayesian Priors"
title: "Chapter 15.08: Bayesian Priors"
weight: 15008
---
In this section, we motivate regularization from a Bayesian perspective, showing how different penalty terms correspond to different Bayesian priors.
Expand All @@ -8,7 +8,7 @@ In this section, we motivate regularization from a Bayesian perspective, showing

### Lecture video

{{< video id="MdwK9e2wR_U" >}}
{{< video id="d_FB9Vyp7oE" >}}

### Lecture slides

Expand Down
6 changes: 3 additions & 3 deletions ...15_regularization/15-09-geom-l2-wdecay.md → ...apters/15_regularization/15-09-geom-l2.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: "Chapter 15.09: Geometric Analysis of L2 Regularization and Weight Decay"
title: "Chapter 15.09: Geometry of L2 Regularization"
weight: 15009
---
In this section, we provide a geometric understanding of \\(L2\\) regularization, showing how parameters are shrunk according to the eigenvalues of the Hessian of empirical risk, and discuss its correspondence to weight decay.
Expand All @@ -8,8 +8,8 @@ In this section, we provide a geometric understanding of \\(L2\\) regularization

### Lecture video

{{< video id="_Y1eEMaxNl8" >}}
{{< video id="PhOL5HB8FIw" >}}

### Lecture slides

{{< pdfjs file="https://github.com/slds-lmu/lecture_sl/raw/main/slides-pdf/slides-regu-geom-l2-wdecay.pdf" >}}
{{< pdfjs file="https://github.com/slds-lmu/lecture_sl/raw/main/slides-pdf/slides-regu-geom-l2.pdf" >}}
4 changes: 2 additions & 2 deletions content/chapters/15_regularization/15-10-geom-l1.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: "Chapter 15.10: Geometric Analysis of L1 Regularization"
title: "Chapter 15.10: Geometry of L1 Regularization"
weight: 15010
---
In this section, we provide a geometric understanding of \\(L1\\) regularization and show that it encourages sparsity in the parameter vector.
Expand All @@ -8,7 +8,7 @@ In this section, we provide a geometric understanding of \\(L1\\) regularization

### Lecture video

{{< video id="1EZUDh45Rkg" >}}
{{< video id="txVJzfLEPmU" >}}

### Lecture slides

Expand Down
2 changes: 1 addition & 1 deletion content/chapters/15_regularization/15-11-early-stopping.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ In this section, we introduce early stopping and show how it can act as a regula

### Lecture video

{{< video id="wicBbjxFlS0" >}}
{{< video id="5e2fgW4Ok3s" >}}

### Lecture slides

Expand Down
Loading