Asagodi
Follow
Stars
Code for paper "Full-Capacity Unitary Recurrent Neural Networks"
LSTM copy task in which a pattern is stored in memory and reproduced again
Supplementary code for the paper "Linking connectivity, dynamics and computations in low-rank recurrent neural networks" by F. Mastrogiuseppe and S. Ostojic (2018)
Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.
Code for "Latent ODEs for Irregularly-Sampled Time Series" paper
A Hidden Markov Model implementation in Python for single feature / symbols, and multiple features with Poisson distributions. Developed for spiking neural activity analysis.
A Python library for working with and training Hidden Markov Models with Poisson emissions.
Matlab toolbox for set-oriented numerics in dynamical systems
Dimensionality reduce the neural activity of C. elegans and fit a nonlinear control model to the PCA activity.
CHomP (Computational Homology Project) with Python bindings
This is matlab code to run simulations for the CTLN model introduced in https://arxiv.org/abs/1605.04463 .
RIVET is a tool for Topological Data Analysis, in particular two-parameter persistent homology.
This project contains the implementation of the Dimensional Causality method proposed in Bayesian inference of causal relations between dynamical systems (Benkő, Zsigmond ; Zlatniczki, Ádám* ; Stip…
In graph algorithms, the widest path problem, also known as the bottleneck shortest path problem or the maximum capacity path problem, is the problem of finding a path between two designated vertic…
Fit an Ising model with neural spike train data using Minimum Probability Flow Learning. Based on code from Jascha Sohl-Dickstein.
Matlab code implementing Minimum Probability Flow Learning.
Maximum Entropy Modeling Toolkit for Python and C++
Robot evolution framework for the Triangle of Life project
An open source Python framework for transition interface and path sampling calculations.