Sitemap / Inhaltsverzeichnis
Data Mining Group – TU Dortmund / Data Mining Arbeitsgruppe – TU Dortmund- Accessibility Statement / Erklärung zur Barrierefreiheit
- Address / Adresse
- Imprint according to section 5 (1) of the German Telemedia Act (TMG) / Impressum nach § 5 Abs. 1 Telemediengesetz (TMG)
-
Machine Learning Bits
- Classification
- Naïve Bayes: Discussion
- Bayesian Classification
- Multivariate Gaussian Bayes Classification
- Conclusion of Supervised Learning Chapter
- Benefits and Drawbacks of Decision Trees
- Decision Tree Learning
- Pruning of Decision Trees
- Decision Tree Splitting
- Ensembles and Random Forests
- Boosting and Adaboost
- Evaluation and Selection of Classifiers
- Classification
- Accelerating k Nearest Neighbors
- Nearest Neighbor as Density Estimation
- Nearest Neighbors: Discussion
- Nearest Neighbor Classification
- Activation Functions
- General Artificial Neural Networks
- Autoencoders and Skip Connections
- Learning Neural Networks with Backpropagation
- Convolutional Neural Networks
- Deep Neural Networks
- Neural Networks
- Conclusions on Neural Networks
- Recurrent Neural Networks
- Regularization Techniques for Neural Networks
- Threshold Logic Units
- Transformer and Attention
- Vanishing and Exploding Gradients
- VC Dimension of Neural Networks
- Examples for Neural Networks
- Overfitting
- Affine Hyperplanes and Scalar Products
- SVM – Conclusions and Discussion
- SVM – Extensions
- Non-linear SVM and the Kernel Trick
- Maximum Margin Hyperplane
- Support Vector Machine Motivation
- Training Support Vector Machines
- Understanding the RBF Kernel
- Cluster Analysis
- BIRCH and BETULA
- Example for DBSCAN Clustering
- DBSCAN Extensions
- Density-Based Clustering Fundamentals
- DBSCAN Clustering
- DBSCAN Parameterization
- HDBSCAN*
- Motivation Density-Based Clustering
- Understanding the OPTICS Cluster Order
- Example for OPTICS Clustering
- Cluster Extraction from OPTICS
- OPTICS Clustering
- Gaussian Mixture Modeling Demonstration
- Discussion of Gaussian Mixture Modeling
- Gaussian Mixture Modeling and PCA
- Gaussian Mixture Modeling Introduction
- Evaluation of Clusterings
- Extrinsic Evaluation of Clusterings
- Extrinsic Evaluation Example
- Extrinsic Evaluation – Example
- Intrinsic Evaluation of Clusterings
- Intrinsic Evaluation Examples
- Intrinsic Evaluation – Examples
- Intrinsic Evaluation Measures
- Accelerating Hierarchical Clustering
- Demonstration of Anderberg’s Hierarchical Clustering
- Demonstration of NNChain Clustering
- Limitations of Hierarchical Clustering
- Demonstration of Hierarchical Clustering
- Hierarchical Agglomerative Clustering
- Derivation of Hierarchical Clustering Equations
- Hierarchical Clustering – Introduction
- Cluster Analysis Introduction
- Accelerating k-means Clustering
- Example Hamerly k-means Clustering
- Demonstration of k-means
- Extensions of k-means Clustering
- Initialization of k-means
- k-means Clustering
- Limitations of k-Means Clustering
- k-Means Clustering the Simpsons
- Partitioning Around Medoids (k-Medoids)
- Spectral Clustering
- Clusters are Subjective
- Further Clustering Approaches
- Foundations and Theory
- Bias-Variance Tradeoff
- Correlation does not Imply Causation
- Curse of Dimensionality
- Distance Functions
- Intrinsic Dimensionality
- Multiple Testing Problem
- No Free Lunch
- Occam’s Razor – Principle of Parsimony
- PAC Learning
- Principles in Machine Learning
- Spatial Index Structures
- VC Dimension
- Frequent Pattern Mining
- Scaling Frequent Itemset Mining
- Apriori Algorithm
- The Apriori Hash Tree
- Apriori Principle
- Association Rules
- Columnwise Mining
- Conclusions
- Frequent Itemset Mining
- Frequent Pattern Growth
- Mining the Frequent Pattern Tree
- Frequent Sequence Mining
- Interestingness of Association Rules
- Motivation Market Basket Analysis
- Maximal and Closed Frequent Itemsets
- The Naive Approach
- NetFlix Example
- Introduction
- Different Kinds of ML
- What is Learning?
- Literature
- Machine Learning and Statistics
- Motivation
- Archetypal Analysis
- Archetypal Analysis – Example
- Conclusions
- Motivation Matrix Factorization
- k-Means as Matrix Factorization
- Non-negative Matrix Factorization
- Examples for Nonnegative Matrix Factorization
- SVD as Matrix Factorization
- Basic Architectures for NLP
- Attention
- Beyond Transformers
- Beyond Word2Vec
- Decoder Models
- Encoder Models
- Finetuning and Optimization
- Neural Models for Word Similarity
- Discussion of Neural NLP
- Motivation of Neural Embeddings
- Deep Neural Network Embeddings
- Positional Encoding
- Retrieval-Augmented Generation
- Sentence- and Document Embeddings
- Transformer and Attention
- Outlier Detection
- Distance-Based Approaches
- Domain Adaptation
- Evaluation
- Introduction to Outlier Detection
- Local Outlier Detection
- LOF Variants
- One-Class Classification
- Other Outlier Detectors
- Scores and Ensembles
- Statistical Approaches
- Conclusions
- Conditional Random Fields
- Hidden Markov Models
- Algorithms for HMM
- Forward-Backward Example
- Maximum Entropy Markov Models (MEMM)
- Contextual Information
- Summary and Literature
- Vector Representations of Words
- Text Mining is Difficult
- Evaluation
- Exact Text Search and Ranked Retrieval
- Tokenization and Lexical Units
- Vector Space Model
- Evaluation of Topic Models
- Topic Modeling Motivation
- Latent Dirichlet Allocation
- Example for Latent Dirichlet Allocation
- LDA via Collapsed Gibbs Sampling
- Variational Inference for LDA
- Latent Semantic Indexing
- Example for Latent Semantic Indexing
- Detour: Probabilistic Graphical Models
- Probabilistic Latent Semantic Indexing (pLSI)
- Example for Probabilistic Latent Semantic Indexing
- Topic Modeling Conclusions
-
News
/ Neues
- YouTube lecture recordings / YouTube Vorlesungsmitschnitte
- Prof. Schubert in the "most influential scientists" / Prof. Schubert in den "most influential scientists"
- Teaching in summer 2023 / Vorlesungen im Sommersemester 2023
- New publications accepted / Aktuelle Publikationen
- Teaching in winter 2023/2024 / Lehre im Winter 2023/2024
- New publications accepted / Neue Publikationen
- Three awards in one week / Drei Preise in einer Woche
- Four new publications / Vier neue Publikationen
- Privacy Policy / Datenschutzerklärung
- Projects / Projekte
- Publications / Publikationsliste
- Research
-
Teaching
/ Lehrangebote der Arbeitsgruppe
- Teaching in summer term 2023 / Lehre im Sommersemester 2023
- Teaching in summer term 2024 / Lehre im Sommersemester 2023
- Templates for seminar papers and thesises / Vorlagen für Seminar- und Abschlussarbeiten
- Thesis Topics / Themen für Abschlussarbeiten
- Teaching in winter term 2023/2024 / Lehre im Wintersemester 2023/2024
- Teaching in winter term 2024/2025 / Lehre im Wintersemester 2024/2025
- Staff