t.BA.XWV.MLDM2.20HS (Machine Learning and Data Mining 2) 
Module: Machine Learning and Data Mining 2
This information was generated on: 28 May 2024
No.
t.BA.XWV.MLDM2.20HS
Title
Machine Learning and Data Mining 2
Organised by
T CAI
Credits
4

Description

Version: 1.0 start 01 February 2023
 

Short description

(max. 300 characters. Text is displayed in module box in the Internet) 
We  focus on the theory and practical application of deep learning (DL). We start with the DL foundations and dive into the details of the most frequently used modern deep learning models, their capabilities and limitations and their application on real-world use cases from different domains.

Module coordinator

Bogojeska Jasmina (bogo)

Learning objectives (competencies)

Objectives Competences Taxonomy levels
(1) You can explain the main concepts of (deep) neural networks: linear/nonlinear modules, depth, width, gradient-based learning, backpropagation, regularization, optimization, hyperparameters D C2
… and can describe the advantages and limitations of certain deep neural networks architectures, algorithms and methods covered in the course D, M C2, C4
… and can explain their application and discuss their challenges D, M C3, C4
…and can provide example tasks where they are applicable D, M C3
(2) You can design, implement, train, tune and properly evaluate the discussed deep learning methods on your own in a DL framework D, M C3
… and can apply them to real-world tasks and datasets D, M C5

Module contents

Advanced machine learning (ML) solutions based on deep learning (DL) have shown impressive performance on challenging, practically relevant problems in many different domains and are also present in increasingly many aspects of our lives, such as image analysis (face recognition, quality control); speech technologies (virtual assistants, emotion recognition); time series analysis (investment modeling, sensor data fusion); personalized healthcare (diagnosis, drug design); personalized advertising; or autonomous vehicles. Deep neural networks have thus become a critical component of computing in general and are an important element of many job profiles in computer and data science. 

In this module we will provide a thorough introduction to deep learning, starting by covering the fundamentals (main concepts, basic building blocks of neural networks, backpropagation, gradient descent, optimization) that will lay the way for the deep dive into the details of modern deep neural architectures, such as different variants of convolutional neural networks, recurrent neural networks, graph neural networks, and transformers. We will investigate these models and algorithms, analyze their advantages, limitations and discuss the challenges. 
 

List of topics covered:

  • Introduction to DL (e.g., current applications and success, fundamental principles, deep feedforward networks, gradient-based learning, backpropagation, optimization, regularization)
  • Convolutional neural networks (e.g., VGG, ResNet)
  • Sequence modeling (e.g., RNN, LSTM, attention mechanism and transformers)
  • Graph neural networks (e.g, GCN)
  • Generative models
  • Selected topics (e.g., deep RL, explainable AI, meta learning)


Accompanying Labs

To apprehend the proper application of the deep learning methods in practice, we will discuss real-world applications from several different domains (e.g., computer vision, natural language processing, healthcare) and provide a large set of practical examples on real-world datasets using state-of-the-art tools and frameworks. In a real-world practical project the participants can apply and deepen the acquired knowledge and skills. 


 

Teaching materials

  • Lecture slides
  • Lab descriptions

Supplementary literature
 

  • Simon J.D. Prince: "Understanding Deep Learning", MIT Press, 2023 https://udlbook.github.io/udlbook/  
  • I. Goodfellow, Y. Bengio, and A. Courville: “Deep Learning”, MIT press, 2016, https://www.deeplearningbook.org/
  • S. Raschka, Y. Liu, V. Mirjalili: “Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python”, Packt Publishing, 2022.  https://sebastianraschka.com/blog/2022/ml-pytorch-book.html
  • Scientific literature as introduced in the course

Prerequisites

  • General introduction to machine learning and neural networks, such as successful completion of MLDM1
  • Python

Teaching language

() German (X) English

Part of International Profile

( ) Yes (X) No

Module structure

Type 3a

 

For more details please click on this link: T_CL_Modulauspraegungen_SM2025

Exams

Description

Type

Form

Scope

Grade

Weighting

Graded project(s) during teaching semester

Practical project

Written

 

20 points

20%

End-of-semester exam

Test (online or on paper)

Written

90 minutes

max. 80 points

80%

Remarks

 

Legal basis

The module description is part of the legal basis in addition to the general academic regulations. It is binding. During the first week of the semester a written and communicated supplement can specify the module description in more detail.

Course: Maschinelles Lernen und Data Mining 2 - Praktikum
No.
t.BA.XWV.MLDM2.20HS.P
Title
Maschinelles Lernen und Data Mining 2 - Praktikum

Note

  • No module description is available in the system for the cut-off date of 02 August 2099.
Course: Maschinelles Lernen und Data Mining 2 - Vorlesung
No.
t.BA.XWV.MLDM2.20HS.V
Title
Maschinelles Lernen und Data Mining 2 - Vorlesung

Note

  • No module description is available in the system for the cut-off date of 02 August 2099.