Sheshka (PhD)'s Projects
Prototype of an AI artist
aRtsy is an R package that implements algorithms for making generative art in a straightforward and standardized manner using 'ggplot2'.
Hey, I'm Ayce!
Analysis of kinetic models for the Bacterial Flagella Motor stator assembly
Biologically-informed neural networks
Restricted Boltzmann Machines in Julia
GPU-accelerated simulations of Voronoi and vertex models of cells. Initial version published in Computer Physics Communications: https://doi.org/10.1016/j.cpc.2017.06.001
ETH course - Solving PDEs in parallel on GPUs
An extension of the previous cellGPU package (and, currently, less well documented), that allows for simulations of 2D vertex models in curved space
Code for "Learning data-driven discretizations for partial differential equations"
This implementation of DeePyMoD is no longer maintained! We switched to a PyTorch based implementation: https://github.com/PhIMaL/DeePyMoD_torch
Code to accompany the paper "Discovery of Physics from Data: Universal Laws and Discrepancies"
Deep Neural Networks Entropy from Replicas
Set of Lecture at Duke in 2018 by Lenka Zdeborova and Florent Krzakala "Statistical Physics For Optimization and Learning"
Using Geopandas to Plot Brazil Maps
Code for "Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data"
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
kapre: Keras Audio Preprocessors
INTRODUCTION TO MACHINE LEARNING: An introductory practical course by Florent Krzakala and Antoine Baker
The framework for inferring Langevin dynamics from spike data
Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations
PyDEns is a framework for solving Ordinary and Partial Differential Equations (ODEs & PDEs) using neural networks