Pattern Recognition and Machine Learning

Lecture "Pattern Recognition and Machine Learning"

Basic Information
Lecturers:	Gerhard Schmidt (lecture) and Erik Engelhardt (exercise)
Room:	KS2/Geb.F - SR-III
E-mail:	This email address is being protected from spambots. You need JavaScript enabled to view it.
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: Preprocessing to reduce signal distortions Noise reduction Beamforming Feature extraction and data compression Pattern recognition and data regression Learning types Unsupervised learning Supervised learning Reinformcement learning Codebooks Gaussian mixture models (GMMs) Artificial Neural Networks (ANNs) Multilayer perceptron Convolutional neuronal networks (CNNs) Recurrent neural networks (RNNs) Autoencoder networks Generative adversarial networks (GANs) Hidden Markov models (HMMs) Explainable artificial intelligence (EAI)

News

A preliminary lecture and exercise schedule for WS 22/23 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
26.10.2022	Introduction	-
02.11.2022	Noise Suppression + Beamforming	Noise Suppression (video)
09.11.2022	Beamforming + Feature Extraction	Beamforming (video)
16.11.2022	Feature Extraction + Codebook Training	Feature Extraction (video)
23.11.2022	Codebook Training + Bandwidth Extension	Codebook Training (video)
30.11.2022	Bandwidth Extension	Bandwidth Extension (video) + Question time with content per request (start time will be approx. 10:45 h)
07.12.2022	Gaussian Mixture Models	Gaussian Mixture Models (video)
14.12.2022	Student Talks	Student talks
11.01.2023	Neural Networks	Neural Networks (video)
18.01.2023	Neural Networks	Question time with content per request (start time will be approx. 10:45 h)
25.01.2023	Hidden Markov Models	Hidden Markov Models (video)
01.02.2023	Explainable artificial intelligence	Speaker and Speech Recognition (video) + Question time with content per request (start time will be approx. 10:45 h)

Lecture Slides

Link	Content
	Slides of the lecture "Introduction" (Introduction, boundary conditions of the lecture, applications)
	Slides of the lecture "Noise Suppression" (Noise suppression, dereverberation, speech reconstruction)
	Slides of the lecture "Beamforming" (Fixed and adaptive beamforming, postfiltering)
	Slides of the lecture "Feature Extraction" (Linear prediction, cepstrum, mel-filtered cepstral coefficients)
	Slides of the lecture "Codebook Training" (K-means algorithm, LBG algorithms)
	Slides of the lecture "Bandwidth Extension" (Model-bases approaches, evaluation)
	Slides of the lecture "Gaussian Mixture Models (GMMs)" (Training with the EM algorithm, applications)
	Slides of the lecture "Neural networks" (Network types, training procecures)
	Slides of the lecture "Hidden Markov Models (HMMs)" (Efficient probability calculation, training of HMMs)
	Slides of the lecture "Explainable artificial intelligence" (Understanding what had contributed mainly to the decision of neural networks, etc.)

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. On 30.11.2021 and on 01.02.2022 there will be an in-presence exercise 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 This email address is being protected from spambots. You need JavaScript enabled to view it. at any time.

Video	Content	Material
	Noise suppression: Wiener Filter summary comprehension questions python demo
	Beamforming: beamforming summary comprehension questions python demo
	Feature extraction: linear prediction LPC, LPCC, MFCC features comprehension questions python demo
	Codebook training: codebooks codebook training comprehension questions python demo
	Bandwidth extension: bandwidth extension summary comprehension questions python demo
	Gaussian Mixture Models: Gaussian Mixture Models EM algorithm comprehension questions python demo
	Neural Networks: neural networks summary comprehension questions python demo
	Hidden Markov Models: hidden markov models summary comprehension questions python demo
	Speaker and Speech Recognition: speaker and speech recognition summary comprehension questions python demo

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 This email address is being protected from spambots. You need JavaScript enabled to view it. to reserve your topic. The talk registration deadline is 7.12.2022.

Below you can find the preliminary schedule of the talks.

Date	Room	Time	Topic	Presenter(s)
14.12.2022	KS2/Geb.F - SR-III	08:20 h	A Neural Network Based Approach for Diagnosis of Breast Cancer	Usama Adeel
14.12.2022	KS2/Geb.F - SR-III	08:35 h	Gato - A Generalist Agent	Arber Ramadani
14.12.2022	KS2/Geb.F - SR-III	08:50 h	Using Supervised and Unsupervised Learning for Improving Network Security in IoT	Aida Habibipoor
14.12.2022	KS2/Geb.F - SR-III	09:05 h	Support Vector Machines: Theory and Application	Marten Finch and Luca Lohmann
14.12.2022	KS2/Geb.F - SR-III	09:35 h	Break
14.12.2022	KS2/Geb.F - SR-III	09:45 h	Viola-Jones Face Detection Algorithm	Torben Kannengießer and Tom Jürgensen
14.12.2022	KS2/Geb.F - SR-III	10:15 h	Recognition of Deseases Based on VOC Biomarker With Pattern Recognition and Machine Learning	Lukas Nolte
14.12.2022	KS2/Geb.F - SR-III	10:30 h	Machine Learning for Optimization Problems and its Application: A Real Time Energy Management for EV Charging Station	Tailei Wang
14.12.2022	KS2/Geb.F - SR-III	10:45 h	Usage of Convolutional Auto-Encoder Networks in Image Proccessing	Agit Culcu
14.12.2022	Online (Zoom)	11:00 h	Handwriting Recognition using the SFR model	Firdous Bin Ismail
Tbd	KS2/Geb.F - SR-III	Tbd	Image Segmentation with Keras	Ralf Burgardt und Hannes Dreier

Evaluation

Evaluation
	Current evaluation		Completed evaluations

The Physikalisch-Technische Bundesanstalt (PTB) in Berlin invited Eric to give a talk as part of their colloquium for the Department 8.2 Biosignals. In his presentation titled "Magnetoelectric Thin-film Sensors Toward Biomagnetic Sensor Systems", Eric discussed the latest advancements in the field of magnetoelectric (ME) sensors and their prospective application in biomagnetic sensor systems.

Furthermore, Eric offered an in-depth overview of the upcoming collaborative research activities scheduled for 2023 between the Collaborative Research Center 1261 (CRC 1261) and the PTB. This collaboration aims to combine the knowledge and expertise of the involved institutions. All parties involved eagerly anticipate the forthcoming experimental campaigns and are confident that this collaboration will lead to significant advancements in the domain of biomagnetic sensing.