algoulas Goto Github PK

bio2art

Convert biological neuronal networks to artificial recurrent neuronal networks

bio_rnn_mem

Predict sequential data with recurrent neural networks with biological wiring

connectome_ontogenesis

Generative model of the spatiotemporal development of complex networks

cross_species_connectomics

Uncover and predict network properties of the brain of different animals

differentiable-plasticity

Implementations of the algorithms described in Differentiable plasticity: training plastic networks with gradient descent, a research paper from Uber AI Labs.

echoes

Pythonic Machine Learning with Echo State Networks

ignite

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

modules

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

predict_network

Predict missing connections in networks

receptor_principles

Data mining of receptor autoradiography data with statistics and machine learning

synaptic-flow

torchknickknacks

Many simple useful PyTorch things related mainly to model manipulation (e.g. add, delete, record from layers) in one place