Sebastian Gottwald

Post-doctoral researcher at the Institute of Neural Information Processing at Ulm University with a background in mathematics and physics.

Current research interests

Shared projects and notes

  • pr_func. Python class to simplify calculus with discrete probability distributions and other functions (see also these examples).
  • BA_class. Python class that contains a collection of Blahut-Arimoto type algorithms
  • BMA (Bounded-rational Multi-Agent systems). A modular implementation of Blahut-Arimoto algorithms for feed-forward systems of bounded-rational agents.
  • Coarse-graining and the Free Energy. Coarse-graining as a cause of Free Energy principles in thermodynamics and information theory.
  • Legendre Transform and Rate Distortion. The derivative of the rate-distortion curve is NOT the temperature.
  • Bayesian Inference for Mixtures. Different approaches to infer the components of a mixture distribution from data.
  • TensorFlow Comparison. Overview of how to implement a simple neural network (multi-layer perceptron) in raw NumPy, raw TensorFlow, the TensorFlow Layers API, Keras, and TFLearn.

Publications

sn

Academic positions

Education

Honors and Fellowships

Teaching Experience