Search this site

Teaching

Current Courses

SS 2012


Bachelor-Level Courses

89-7002 Lernen und Wahrnehmen

Anwendung von Lernmethoden zur Lösung von Problemen, wie Wahrnehmung und Steuerung, Bildverarbeitung, Multimediale Datenbanken, Data Mining, Informationssicherheit, Agentensysteme und autonome Systeme.  Verständnis von grundlegenden Konzepten des maschinellen Lernens, der neuronalen Netze, der Bildverarbeitung, Mustererkennung, Entscheidungstheorie und Bayesschen Methoden, Fourietransformationen.  Bayesian Methods, Maximum Likelihood Methods, Nearest Neighbor Classification, Feature Extraction, Neural Networks, Perceptrons, Clustering, Vector Quantization, linear and non-linear Filters, Template Matching, Multi-Agent Systems, Self-Organization.
http://lw.iupr.com/

Bachelor / Master-Level Courses

89-7231 Neural Systems and Self-Organization

Knowledge of machine learning methods with a focus on massively parallel systems.  Understanding of biological analogs, and the computational capabilities and limitations of neural systems.  Understanding of other methods and approaches to natural computation.  Ability to apply these techniques to the solution of real-world problems.  Ability to test and validate massively parallel classifiers.  Ability to implement massively parallel classifier and learning systems using GPU and distributioned computations. Basics of machine learning.  Statistical foundations. Neural hardware and brain architecture.  Simulations of neural systems. Traditional neural network models.  Gradient descent learning. Parallel implementations.  Deep learning.  Clustering.  Independent component analysis.  Bayesian networks.  Reinforcement learning.  Testing and application of neuromorphic systems. Self-assembly, self-organization.  Multi-agent systems.
http://ncso.iupr.com/

Master-Level Course

72-59-V-7 Advanced Machine Learning

Support Vector Machines, Graphical Models (Markov Random Fields), Markov Chain Monte Carlo, Decision Trees (CART), VC Dimension, Hidden Markov Models, exploration of current research questions in the field.

Planned Courses


These courses aren't offered this semester but may be offered again in upcoming semesters.

Master-Level Courses

89-7257 Foundations and Frontiers of Artificial Intelligence

An understanding of the foundational issues of artificial intelligence, including philosophical, computational, and biological. The course examines a number of foundational topics in artificial intelligence, including: theories of consciousness, free will, dualism, strong/weak AI, and other philosophical arguments, game theory, the Chinese room, symbol grounding; brain machine interfaces, augmented cognition, nanotechnology, transhumanism, virtual worlds, and the singularity; automated scientific discovery.

89-7258 Self-Organization and Simulation

An understanding of the mathematical principles and models of self-organization and their computational realization and simulation.  Applications in biology, economics, social sciences, and physics. Mathematical models of competition, evolution, and economic activities.  Ontogeny and phylogeny.  Pattern formation and communication in biological systems.  Multi-agent and intelligent agent modeling and analysis.  Techniques for large-scale simulation.  Applications of self-organization to the creation of structures.  Applications of computational science to testing biological, social, and economic theories.  Organic computing.

89-7254 Document and Content Analysis

Most of the data we interact with day-to-day does not come in the form of data structures or databases, but instead in the form of documents and document images. This course introduces students to the formats, techniques, and algorithms used for representing, compressing, analyzing, processing, and displaying documents.


89-7253 Image Processing and Image Understanding

The course covers image sensors, color and color theory, linear filters, mathematical morphology, spectral methods, template matching, geometric matching (Hough transform, RANSAC), digital photography / computational photography, medical image processing, image databases, object recognition, document analysis and OCR, digital libraries.


89-7256 Multimedia Information Retrieval

The course provides an introduction to information retrieval, evaluation of IR systems, retrieval based on colro/texture/shape/motion, SURF/SIFT feature extraction, edge detection, VQ methods, fast nearest neighbor methods, learning and MLPs, segmentation and grouping, geometric matching (RANSAC, RAST, Hough transform), neurobiology, psychophysics, image database systems.


82-7255 Computational Forensics

The course covers methods for computational analysis of digital data and physical evidence.  An emphasis is on the use of statistical, pattern recognition, and machine learning techniques.  We will be examining how personal information and identity can be leaked and what techniques there are for protecting personal information.


Old Courses

The following courses aren't offered anymore in this form, but they may be offered in revised form later.

89-7231 (old) Pattern Recognition

The course introduces basic techniques in pattern recognition, including 
  • nearest neighbor classification and nearest neighbor algorithms
  • feature extraction and common feature types
  • neural networks, gradient descent
  • RBF networks and interpolation
  • perceptrons and support vector machines
  • k-means clustering, Gaussian mixtures, and semi-supervised learning
  • VQ, principal components analysis and compression
  • hierarchical clustering, dimensionality reduction
  • decision trees
  • pattern recognition with graphs
  • generative data models and model-based classification
  • Bayesian decision theory
  • ML and Bayesian parameter estimation