Under the Hood of Machine and Deep Learning
A Comprehensive Overview of Classical ML Methods
Modern Deep Learning methods deliver extraordinary results every day. To understand its foundations, it is advisable to understand the classic Pattern Recognition and Machine Learning methods as well. In the Winter Semester 2020/21, I was teaching a class on this topic which is entirely available as Open Access material. You can find the slides in PDF Format on Zenodo and the corresponding TeX sources on github. All material is licensed under CC 4.0 BY license. …
On peer review and some of its most significant failures
Scientific Peer Review affects all computer science researchers and academics in their daily life. More often than we actually want to admit, the process causes severe problems and wrong decisions are being made.
PEER REVIEW EXAMPLE
Reviewer 1: Good paper — accept
Reviewer 2: Paper OK — weak accept
Reviewer 3: Paper not so great , might be useful after changes— weak rejectMeta Reviewer:
THIS PAPER IS BROKEN BEYOND ALL REASON — REJECT!
All scientists face such situations, eventually. They hurt every time. So, is this system broken? Why the heck do we even play this game?! It’s time…
Seven common mistakes that break your machine learning experiments’ credibility
Machine learning is a great tool that is revolutionizing our world right now. There are lots of great applications in which machine and in particular deep learning has shown to be way superior to traditional methods. Beginning from Alex-Net for Image Classification to U-Net for Image Segmentation, we see great successes in computer vision and medical image processing. Still, I see machine learning methods fail every day. In many of these situations, people fell for one of the seven sins of machine learning.
While all of them are severe and lead to wrong conclusions, some are worse than others and…
FAU LECTURE NOTES ON DEEP LEARNING
In Comprehensive Videos & Blog Posts
Corona was a huge challenge for many of us and affected our lives in a variety of ways. I have been teaching a class on Deep Learning at Friedrich-Alexander-University Erlangen Nuremberg, Germany for several years now. This summer, our university decided to go “virtual” completely. Therefore, I started recording my lecture in short clips fo 15 minutes each.
Wir durchleben gerade die größte Krise in der Geschichte der Bundesrepublik Deutschland. Um erfolgreich durch COVID zu kommen hat unsere Regierung vielfach auf zentralisierte staatliche Maßnahmen gesetzt, um das Leben in unserem Land wieder auf geregelte Bahnen zu bringen. Über den Erfolg der Maßnahmen und deren negative Effekte wird heftig debattiert. Auch schon leichte Kritik an unserer Corona-Politik kann zu massiven Diffamierungen in der Öffentlichkeit führen, wie die Ereignisse um Jan Josef Liefers zeigten. Durch solche Vorgänge verschwinden die Grautöne in unserer Medienlandschaft. Während der Pandemie hat sich eine Vielzahl an Beispielen angesammelt, an denen man diesen Effekt deutlich machen…
Lecture Notes in Pattern Recognition
The Viola-Jones Algorithm
These are the lecture notes for FAU’s YouTube Lecture “Pattern Recognition”. This is a full transcript of the lecture video & matching slides. The sources for the slides are available here. We hope, you enjoy this as much as the videos. This transcript was almost entirely machine generated using AutoBlog and only minor manual modifications were performed. If you spot mistakes, please let us know!
Navigation
Previous Chapter / Watch this Video / Top Level
Welcome back to Pattern Recognition. Today we want to have the last video of our lecture and we actually want to look into an application of…
FAU Lecture Notes in Pattern Recognition
Adaboost & Exponential Loss
These are the lecture notes for FAU’s YouTube Lecture “Pattern Recognition”. This is a full transcript of the lecture video & matching slides. The sources for the slides are available here. We hope, you enjoy this as much as the videos. This transcript was almost entirely machine generated using AutoBlog and only minor manual modifications were performed. If you spot mistakes, please let us know!
Navigation
Previous Chapter / Watch this Video / Next Chapter / Top Level
Welcome back to Pattern Recognition. Today we want to continue looking into AdaBoost and in particular, we want to see the relation between…
FAU Lecture Notes in Pattern Recognition
The Concept of Adaboost
These are the lecture notes for FAU’s YouTube Lecture “Pattern Recognition”. This is a full transcript of the lecture video & matching slides. The sources for the slides are available here. We hope, you enjoy this as much as the videos. This transcript was almost entirely machine generated using AutoBlog and only minor manual modifications were performed. If you spot mistakes, please let us know!
Navigation
Previous Chapter / Watch this Video / Next Chapter / Top Level
Welcome back to Pattern Recognition. Today we want to look into a particular class of classification algorithms and these are boosting algorithms that…
FAU Lecture Notes in Pattern Recognition
Performance Measures on Finite Data
These are the lecture notes for FAU’s YouTube Lecture “Pattern Recognition”. This is a full transcript of the lecture video & matching slides. The sources for the slides are available here. We hope, you enjoy this as much as the videos. This transcript was almost entirely machine generated using AutoBlog and only minor manual modifications were performed. If you spot mistakes, please let us know!
Navigation
Previous Chapter / Watch this Video / Next Chapter / Top Level
Welcome back to Pattern Recognition! Today we want to look a bit more into model assessment. And then particularly, we want to know…
FAU Lecture Notes in Pattern Recognition
No Free Lunch Theorem & Bias-Variance Trade-off
These are the lecture notes for FAU’s YouTube Lecture “Pattern Recognition”. This is a full transcript of the lecture video & matching slides. The sources for the slides are available here. We hope, you enjoy this as much as the videos. This transcript was almost entirely machine generated using AutoBlog and only minor manual modifications were performed. If you spot mistakes, please let us know!
Navigation
Previous Chapter / Watch this Video / Next Chapter / Top Level
Welcome back to Pattern Recognition. Today we want to look a bit into model assessment and in particular, we want to talk about…
Andreas Maier
I do research in Machine Learning. My positions include being Prof @FAU_Germany, President @DataDonors, and Board Member for Science & Technology @TimeMachineEU
