Displaying 1 to 13 from 13 results

genann - simple neural network library in ANSI C

  •    C

Genann is a minimal, well-tested library for training and using feedforward artificial neural networks (ANN) in C. Its primary focus is on being simple, fast, reliable, and hackable. It achieves this by providing only the necessary functions and little extra. Genann is self-contained in two files: genann.c and genann.h. To use Genann, simply add those two files to your project.

nest-simulator - The NEST simulator

  •    C++

NEST is a simulator for spiking neural network models that focuses on the dynamics, size and structure of neural systems rather than on the exact morphology of individual neurons. The development of NEST is coordinated by the NEST Initiative. General information on the NEST Initiative can be found at its homepage at http://www.nest-initiative.org. For copyright information please refer to the LICENSE file and to the information header in the source files.

Brayns - Interactive raytracing of neuroscience data

  •    C++

One of the keys towards understanding how the brain works as a whole is visualisation of how the individual cells function. In particular, the more morphologically accurate the visualisation can be, the easier it is for experts in the biological field to validate cell structures; photo-realistic rendering is therefore important. The Blue Brain Project has made major efforts to create morphologically accurate neurons to simulate sub-cellular and electrical activities, e.g. molecular simulations of neuron biochemistry or multi-scale simulations of neuronal function. Ray-tracing can help to highlight areas of the circuits where cells touch each other and where synapses are being created. In combination with ‘global illumination’, which uses light, shadow, and depth of field effects to simulate photo-realistic images, this technique makes it easier to visualise how the neurons function.

eFEL - Electrophys Feature Extraction Library

  •    C++

The Electrophys Feature Extraction Library (eFEL) allows neuroscientists to automatically extract features from time series data recorded from neurons (both in vitro and in silico). Examples are the action potential width and amplitude in voltage traces recorded during whole-cell patch clamp experiments. The user of the library provides a set of traces and selects the features to be calculated. The library will then extract the requested features and return the values to the user. The core of the library is written in C++, and a Python wrapper is included. At the moment we provide a way to automatically compile and install the library as a Python module. Instructions on how to compile the eFEL as a standalone C++ library can be found here.

NeuroM - Neuronal Morphology Analysis Tool

  •    Jupyter

NeuroM is a Python toolkit for the analysis and processing of neuron morphologies. This work has been partially funded by the European Union Seventh Framework Program (FP7/2007­2013) under grant agreement no. 604102 (HBP). For license and authors, see LICENSE.txt and AUTHORS.md respectively.

BluePyOpt - Blue Brain Python Optimisation Library

  •    Python

The Blue Brain Python Optimisation Library (BluePyOpt) is an extensible framework for data-driven model parameter optimisation that wraps and standardises several existing open-source tools. It simplifies the task of creating and sharing these optimisations, and the associated techniques and knowledge. This is achieved by abstracting the optimisation and evaluation tasks into various reusable and flexible discrete elements according to established best-practices.

NeuroMorphoVis - A lightweight, interactive, extensible and cross-platform framework for building, visualizing and analyzing digital reconstructions of neuronal morphology skeletons extracted from microscopy stacks

  •    Python

NeuroMorphoVis is an interactive, extensible and cross-platform framework for building, visualizing and analyzing digital reconstructions of neuronal morphology skeletons extracted from microscopy stacks. The framework is capable of detecting and repairing several tracing artifacts, allowing the generation of high fidelity surface meshes and high resolution volumetric models for simulation and in silico studies. NeuroMorphoVis is primarily designed as a plug-in in Blender. It comes with a user-friendly GUI and a rich set of command line options. Moreover, the tool is configurable via input configuration files making it possible to link it to web interface or using it on massively parallel visualization clusters for batch production.

python-neuron - Neuron class provides LNU, QNU, RBF, MLP, MLP-ELM neurons

  •    Python

Neuron class provides LNU (Linear Neural Unit), QNU (Quadratic Neural Unit), RBF (Radial Basis Function), MLP (Multi Layer Perceptron), MLP-ELM (Multi Layer Perceptron - Extreme Learning Machine) neurons learned with Gradient descent or LeLevenberg–Marquardt algorithm. This class is suitable for prediction on time series. Neuron class needs pandas and numpy to work propertly.

spiketorch - Experiments with spiking neural networks (SNNs) in PyTorch

  •    Python

Python package used for simulating spiking neural networks (SNNs) in PyTorch. At the moment, the focus is on replicating the SNN described in Unsupervised learning of digit recognition using spike-timing-dependent plasticity (original code found here, extensions thereof found in my previous project repository here).


  •    Matlab

This code helps you classify malignant and benign tumors using Neural Networks. The example code is in Matlab (R2016 or higher will work).

BrabeNetz - 🧠 A fast and clean supervised neural network in C++, capable of effectively using multiple cores

  •    C++

I've written two examples of using BrabeNetz in the Trainer class to train a XOR ({0,0}=0, {0,1}=1, ..) and recognize handwritten characters. In my XOR example, I'm using a {2,3,1} topology (2 input-, 3 hidden- and 1 output-neurons), but BrabeNetz is scalable until the hardware reaches its limits. The digits recognizer is using a {784,500,100,10} network to train handwritten digits from the MNIST DB.

ntnu-som - Using Self-Organizing Maps for Travelling Salesman Problem

  •    Python

Self-organizing maps (SOM) or Kohonen maps are a type of artificial neural network (ANN) that mixes in an interesting way the concepts of competitive and cooperative neural networks. A SOM behaves as a typical competitive ANN, where the neurons fight for a case. The interesting twist added by Kohonen is that when a neurons wins a case, the prize is shared with its neighbors. Typically, the neighborhood is bigger at the beginning of the training, and it shrinks in order to let the system converge to a solution. One of the most interesting applications of this technique is applying it to the Travelling Salesman Problem, in which we can use a coordinate map and trace a route using the neurons in the ANN. By defining weight vectors as positions in the map, we can iterate the cities and treat each one as a case that can be won by a single neuron. The neuron that wins the case gets it weight vector updated to be closer to the city, but also its neighbors get updated. The neurons are placed in a 2D space, but they are only aware of a single dimension in their internal ANN, so their behavior is like an elastic ring that will eventually fit all the cities in the shortest distance possible.

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.