Lecture "Pattern Recognition and Machine Learning"
Basic Information | |
---|---|
Lecturers: | Gerhard Schmidt (lecture) and Erik Engelhardt (exercise) |
Room: | KS2/Geb.F - SR-III |
E-mail: | |
Language: | English |
Target group: | Students in electrical engineering and computer engineering |
Prerequisites: | Basics in system theory |
Contents: |
In this lecture the basics of speech, audio, and music signal processing are treated. Often schemes that are based on statistical optimization are utilized for these applications. The involved cost function are matched to the human audio perception. Topic overview:
|
News
A preliminary lecture and exercise schedule for WS 23/24 is now available.
The lecture will be given in seminar room KS2/Geb.F - SR-III and can be attended according to the university's current rules.
There is no exercise after the first lecture. Instead, the time allocated for the exercise will be used for the continuation of the lecture.
Remember to register for the exam in the QiS system. Without such a registration we will have to cancel any exam slot you booked with us. Booking of exam slots is possible here.
Schedule
The following schedule regarding lectures and excercises is preliminary and may be adapted during the semester. The lecture will usually take place from 8:15 h - 10:45 h.
Date | Lecture | Exercise |
---|---|---|
25.10.2023 | Introduction | - |
01.11.2023 | Noise Suppression + Beamforming | Noise Suppression (video) |
08.11.2023 | Beamforming + Feature Extraction | Beamforming (video) |
15.11.2023 | Feature Extraction + Codebook Training | Feature Extraction (video) |
22.11.2023 | Codebook Training + Bandwidth Extension | Codebook Training (video) |
29.11.2023 | Bandwidth Extension | Bandwidth Extension (video) |
06.12.2023 | Gaussian Mixture Models | Gaussian Mixture Models (video) |
13.12.2023 | Student Talks | Student talks |
10.01.2023 | Neural Networks | - |
17.01.2024 | Neural Networks | Neural Networks (video) |
24.01.2024 | Hidden Markov Models | Hidden Markov Models (video) |
31.01.2024 | Explainable artificial intelligence | Speaker and Speech Recognition (video) |
Lecture Slides
Matlab Demos
Link | Content |
---|---|
Matlab demo (GUI based) for adaptive noise suppression | |
Matlab demo (GUI based) for linear prediction |
Exercises
For each lecture topic on-demand video will be provided. There will be an in-presence exercises to discuss your questions and requested topics. You may send in questions (if you want the answer to be supported by slides) or exercise topic suggestions to
Video | Content | Material |
---|---|---|
Noise suppression:
|
||
Beamforming:
|
||
Feature extraction:
|
||
Codebook training:
|
||
Bandwidth extension:
|
||
Gaussian Mixture Models:
|
||
Neural Networks:
|
||
Hidden Markov Models:
|
||
Speaker and Speech Recognition:
|
Talks
Each student will give a talk about a certain topic. The aim is both to give you the chance to work on a pattern recognition-related topic that interests you, and to improve your presentational skills. The talk is also a prerequisite for your admission to the exam. The talks should be held in English and should take ten minutes, plus 2.5 minutes of discussion and 2.5 minutes of feedback. Please write an email to
Date | Room | Time | Topic | Presenter(s) |
---|---|---|---|---|
13.12.2023 | KS2/Geb.F - SR-III | 08:15 h | Opening | Gerhard Schmidt |
13.12.2023 | KS2/Geb.F - SR-III | 08:25 h | Machine-learning-based ECG Analysis | Maureen Petersilka |
13.12.2023 | KS2/Geb.F - SR-III | 08:40 h | Machine Learning for Optical Communication Systems | Henning Eikens |
13.12.2023 | KS2/Geb.F - SR-III | 08:55 h | Edge Computing for Artificial Intelligence (Edge-AI) | Daniel Wittmann |
13.12.2023 | KS2/Geb.F - SR-III | 09:10 h | Spiking Neural Networks | Tilman Müller |
13.12.2023 | KS2/Geb.F - SR-III | 09:25 h | Gaussian Splatting | Alberto Rodriguez Botejara |
13.12.2023 | KS2/Geb.F - SR-III | 09:40 h | Marine Autopilot Applications | Jonas Huwer |
Evaluation
Evaluation | |||
---|---|---|---|
Current evaluation | Completed evaluations |