Institute for Theoretical Computer Science, TU Graz

WeatherDiffusion

Code for "Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models" [TPAMI 2023]

LSNN-official

Long short-term memory Spiking Neural Networks

eligibility_propagation

LSM

Liquid State Machines in Python and NEST

L2L

Learning to Learn: Gradient-free Optimization framework

H-Mem

Code for Limbacher, T. and Legenstein, R. (2020). H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks

Cognitive-Map-Learner

This repo contains an example jupyter-notebook for the CML algorithm on all different kinds of the abstract random graph tasks.

SimManager

The Simulation Manager is a library for enabling reproducible scientific simulations.

SparseAdversarialTraining

Code for "Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling" [ICML 2021]

MemoryDependentComputation

Code for Limbacher, T., Özdenizci, O., & Legenstein, R. (2022). Memory-enriched computation and learning in spiking neural networks through Hebbian plasticity. arXiv preprint arXiv:2205.11276.

structured_information_representation

Simulation code für Müller et al., A model for structured information representation in neural networks of the brain

IGI-Reading-Group

IGI Reading Group

OutputCodeMatching

Code for "Improving Robustness Against Stealthy Weight Bit-Flip Attacks by Output Code Matching" [CVPR 2022]

Spike-Frequency-Adaptation-Supports-Network-Computations

Code for: Spike Frequency Adaptation Supports Network Computations on Temporally Dispersed Information

CSNN

dendritic_rewiring

Simulation code for Limbacher, T. and Legenstein, R. (2020). Emergence of Stable Synaptic Clusters on Dendrites Through Synaptic Rewiring

scoop

SCOOP (Scalable COncurrent Operations in Python)

SimRecorder

An high-performance library for recording and storing simulation data

SE-adlif

WIP

RobustSNNConversion

Code for "Adversarially Robust Spiking Neural Networks Through Conversion" [TMLR 2024]

StraightSkel

StraightSkel is an implementation of the Straight Skeleton in 2- and 3-dimensional space. It is used to animate the computation of offsets of polygons and polyhedrons. StraightSkel was written by Gernot Walzl in the years 2011, 2012, 2013, 2016

adaptation_working_memory

Spike frequency adaptation supports network computations on temporally dispersed information

dynamic_rnn_with_gradients

Fault-Pruning

Code for: Kraišniković, C., Stathopoulos, S., Prodromakis, T., & Legenstein, R. (2023, March). Fault pruning: Robust training of neural networks with memristive weights. In International Conference on Unconventional Computation and Natural Computation (pp. 124-139). Cham: Springer Nature Switzerland.

QuantizedRewiring

RobustModelCompression

Code for "Preserving Real-World Robustness of Neural Networks Under Sparsity Constraints" [ECML-PKDD 2024]

loggingext

Short for Logging Extensions, contains helper functions for python logging

LookbackNeuron

NEST related header and source files containing the relevant code to implement the feature of looking back into incoming synapses.

RapidLearningInMemoryComputing

TSP

code for Non-synaptic plasticity enables memory-dependent local learning paper