Maak kennis met Joeri

Describe and apply key concepts in data processing and signal analysis by using Matlab.
Master basic programming skills and the syntax of the Matlab programming language.
Implement a magneto-encephalographic (MEG) data analysis in the frequency domain.
Build a full brain fMRI analysis using the required theoretical knowledge.

Understand and reason using basic aspects of computational complexity theory, such as NP-hardness and reductions.
Understand, apply, and implement search algorithms for finding shortest paths, maximum flow, and minimum spanning trees:
Understand the simulated annealing and Monte Carlo search strategies;
Understand, apply, and reason about planning and scheduling aspects using various representations (feature based, STRIPS, constraint satisfaction) and optimization strategies (regression-based, forward-based, CSP resolution, and linear programming);
Understand, apply, and implement the Variable Elimination algorithm for inference approximation, learning, and decision making in Bayesian Networks;
Understand, apply, and reason with important aspects from Markov Decision Processes and Machine Learning, such as model based versus model free learning, exploration and exploitation, and Markov properties;
Understand important algorithms such as value and policy iterations, and their mathematical background, in particular the Bellman equations.

Dit vak heb ik niet letterlijk gevolgd, maar ik gebruik python voor al mijn praktische projecten, dus de stof is voor mij erg bekend.

Solve problems in a functional way
Choose and develop suitable data structures for given problems
Use and deploy modern programming language concepts such as higher-order functions, polymorphism, overloading, recursive data structures
Reason about functional programs.

how to write better academic English and
how to evaluate their own writing and that of others.
have learned different research methodologies in AI
have learned how to formulate research questions in AI
be able to critically read and evaluate academic articles
be able to translate a theory into a practical framework, algorithm or a computational model.

After successful completion of this course, students have an understanding, both at the conceptual and the technical level, of the application of natural language processing (NLP) and multimedia processing techniques to the areas of text and multimedia mining. Students can design models for machine learning algorithms, and they can evaluate and report on the developed models. Also students understand, from a theoretical perspective, which tools are applicable in which situations, and which real-world challenges prevent the application of certain techniques (such as language variation and noise due to document processing errors or user interpretations).

Have a broad overview of the basic principles of neuromorphic computing and the difference with traditional computer architectures and computing paradigms;
Have familiarized themselves with information processing and encoding in the brain and the physical and computational motivation for e.g. rate vs temporal coding, analog vs. spiking behavior, event-driven information processing, and the differences between brain and silicon implementations and considerations;
Are familiar with the state-of-the-art neuromorphic hardware systems including some hands-on experience with such architectures;
Are familiar with practical learning algorithms for spiking neural networks and the pros and cons for using spiking architectures rather than deep neural networks;
Have some experience with neuromorphic algorithm design and recent research at the Donders Institute in this area;
Are familiar with the relation between neuromorphic architectures and neuroscience research in areas such as the Bayesian Brain hypothesis, memory and plasticity, and information processing.