This is an archived profile. The information it contains is no longer updated.

Keck, Ingo
uri icon qr icon

Keck, Ingo

Positions

selected publications

keywords

  • blockchain
  • machine learning
  • networks
  • open data

teaching overview

  • University of Regensburg
    Winter Term 2012/13
    • Machine Learning I (lecture, 2h per week):
      Neural networks (perceptron, MLP, Hebb learning, SOM, recurrient and reward learning), estimation and information theory (ML, MAP, EM), clustering and classification (kmeans, hiearchical, SVM), Bayes' networks and graphical models.
    • Neuro-Informatics (lecture, 2h per week):
      Biological neuron, telegraphers equation, Hodgkin-Huxley modell, Bonhoeffer-Van der Pol oscillator, artificial neural networks (perceptron, MLP), brain imaging (EEG, MEG, PET, fMRI), general linear model, independent component analysis.
    • Practical Introduction To Functional Brain Imaging and Statistical Parametric Mapping (SPM) (practical course, 2h per week):
      Experiment design, data pre-processing, general linear model, Students t-test, Dynamic causal modelling (DCM)
    • Brain Imaging In Clinical Psychology (seminar, 2h per week):
      Pre-operative fMRI, neural plasticity, default mode network, degenerative deseases, pain, tinnitus, depression, brain imaging and genetics.
    • Introduction To fMRI For students Of The International Master For Experimental And Clinical Neurosciences (practical course, 2h per week):
      Experiment design, implementation and analysis.
    Summer Term 2012
    • Machine Learning II (lecture, 2h per week):
      Principal component analysis (PCA), singular spectrum analysis (SSA), kernel methods, independent component analysis (ICA), non-negative matrix factorisation (NMF), sparse component analysis, empirical mode decomposition (EMD).
    • Bioinspired Optimisation (lecture, 2h per week):
      Convex optimisation, neural networks, reinforcement learning, genetic algorithms, ant and bee colony optimisation, particle swarm, physarum solver, taboo search.
    • Practical Introduction To Functional Brain Imaging and Statistical Parametric Mapping (SPM) (practical course, 2h per week):
      Experiment design, data pre-processing, general linear model, Students t-test, Dynamic causal modelling (DCM).
    • Signal Processing In Medical Physics (lecture, 2h per week):
      Biomedical data preprocessing using Principal component analysis (PCA) and singular spectrum analysis (SSA); data analysis with (spatio-temporal) independent component analysis (ICA), non-negative matrix factorisation (NMF) and empirical mode decomposition (EMD).
    Winter Term 2011/12
    • Machine Learning I (lecture, 2h per week):
      Neural networks (perceptron, MLP, Hebb learning, SOM, recurrient and reward learning), estimation and information theory (ML, MAP, EM), clustering and classification (kmeans, hiearchical, SVM), Bayes' networks and graphical models.
    • Neuro-Informatics (lecture, 2h per week):
      Biological neuron, telegraphers equation, Hodgkin-Huxley modell, Bonhoeffer-Van der Pol oscillator, artificial neural networks (perceptron, MLP), brain imaging (EEG, MEG, PET, fMRI), general linear model, independent component analysis.
    • Practical Introduction To Functional Brain Imaging and Statistical Parametric Mapping (SPM) (practical course, 2h per week):
      Experiment design, data pre-processing, general linear model, Students t-test, Dynamic causal modelling (DCM).
    • Brain Imaging In Clinical Psychology (seminar, 2h per week):
      Pre-operative fMRI, neural plasticity, default mode network, degenerative deseases, pain, tinnitus, depression, brain imaging and genetics.
    • Explorative Brain Imaging Data Analysis (practical course, 2h per week):
      Data preprocessing, independent component analysis (ICA) and it's application to fMRI data, introduction to resting state experiments.
    Summer Term 2011
    • Machine Learning (lecture, 2h per week):
      Neural networks (perceptron, MLP, Hebb learning, SOM, recurrient and reward learning), estimation and information theory (ML), clustering and classification (kmeans, hiearchical, SVM), Principal component analysis (PCA), singular spectrum analysis (SSA), kernel methods, independent component analysis (ICA).
    • Neuro-Informatics (lecture, 2h per week):
      Biological neuron, telegraphers equation, Hodgkin-Huxley modell, Bonhoeffer-Van der Pol oscillator, artificial neural networks (perceptron, MLP), brain imaging (EEG, MEG, PET, fMRI), general linear model, independent component analysis.
    • Practical Introduction To Functional Brain Imaging and Statistical Parametric Mapping (SPM) (practical course, 2h per week):
      Experiment design, data pre-processing, general linear model, Students t-test, Dynamic causal modelling (DCM).

full name

  • Ingo Keck

primary email

  • ingo.keck@tib.eu
Publications in VIVO
  • Contact Info
  • Websites