Fast linear discrete time filtering in PyTorch.

Koopman Kernels for Learning Dynamical Systems from Trajectory Data

A Python package to learn the Koopman operator.

Differentiable, Hardware Accelerated, Molecular Dynamics

Repository for the workshop titled 'Modelling room acoustics for immersive audio applications'

This is a Python implementation of the Auditory Toolbox

A State-Space Model with Rational Transfer Function Representation.

Tile primitives for speedy kernels

Repo to the paper "Lie Point Symmetry Data Augmentation for Neural PDE Solvers"

A Python package for probabilistic state space modeling with JAX

Reference implementation of Finite Element Networks as proposed in "Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks" at ICLR 2022

Differentiable Finite Element Method with JAX

Machine learning library for symbolic fitting: the unknown system/function is described via NARMAX algebraic expressions being linear combinations of arbitrary non-linear terms provided by the user…

Android-based Child Monitor

A Jupyter book accompanying the ISMIR 2023 tutorial Introduction to DIfferentiable Audio Synthesiser Programming

A Fast Modular Synthesizer in JAX @ AES'23

Code for the paper Physical Modelling of Stiff Membrane Vibration Using Neural Networks with Spectral Convolution Layers

GPU/TPU accelerated nonlinear least-squares curve fitting using JAX

Functional models and algorithms for sparse signal processing

Fast, differentiable audio processors on the CPU or GPU, controlled from the browser. The goal is to parameterize audio graphs in real-time to resemble incoming audio streams. Built with JAX, WebRT…

Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"

Fast and differentiable time domain all-pole filter in PyTorch.

ETH Zürich Deep Learning in Scientific Computing Master's course 2023

A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations

Differentiable computations for the signature-PDE-kernel on CPU and GPU.

This library allows the creation and manipulation of vector shapes using audio signals sent directly to oscilloscopes, modified Vectrex consoles, ILDA laser displays, and oscilloscope emulation sof…

A compilation of abstractions and instruments compatible with Pure Data vanilla.

The simplest, fastest repository for training/finetuning medium-sized GPTs.