Pattern Formation – Hans Olischläger

Show general imports

%load_ext autoreload
%autoreload 2

import os

os.environ["KERAS_BACKEND"] = "jax"

import numpy as np
import keras
import bayesflow as bf
import matpl…

Ensembles of conditional distribution learners

Bayesian Inference

Python

Ensembles of neural networks helps us understand learner variability.

Hans Olischläger

What now is the fasted generalized inverse algorithm?

*in this highly specific case: Graph Laplacian. Exploiting matrix properties.

Julia

Python

matrix inversion

performance optimization

graphs

I share some performance benchmarks for different algorithms of (generalized) matrix inversion.

Hans Olischläger

Invert the Simulation

Bayesian Inference

Python

Can we explicitly invert models?

Hans Olischläger

Differentiable Programming

Seminar on Scientific Machine Learning

Python

Julia

ML

Differentiable Programming is when your code – understood as defining some mapping from inputs to outputs – can be differentiated algorithmically.

Valentin Pratz, Hans Olischläger

Ising model and Renormalization

Do you notice something in this image? Anything sticking out?

Hans Olischläger