### CoreNeuron - Simulator optimized for large scale neural network simulations.

•        4

CoreNEURON is a simplified engine for the NEURON simulator optimised for both memory usage and computational speed. Its goal is to simulate massive cell networks with minimal memory footprint and optimal performance. If you are a new user and would like to use CoreNEURON, this tutorial will be a good starting point to understand complete workflow of using CoreNEURON with NEURON.

https://github.com/BlueBrain/CoreNeuron

 Tags neuron neural-network neuroscience compartmental simulation-framework supercomputing hpc Implementation C++ License Public Platform

## EmojiIntelligence - Neural Network built in Apple Playground using Swift

•    Swift

I used this challenge to learn more about neural networks and machine learning. A neural network consists of layers, and each layer has neurons. My network has three layers: an input layer, a hidden layer, and an output layer. The input to my network has 64 binary numbers. These inputs are connected to the neurons in the hidden layer. The hidden layer performs some computation and passes the result to the output layer neuron out. This also performs a computation and then outputs a 0 or a 1. The input layer doesn’t actually do anything, they are just placeholders for the input value. Only the neurons in the hidden layer and the output layer perform computations. The neurons from the input layer are connected to the neurons in the hidden layer. Likewise, both neurons from the hidden layer are connected to the output layer. These kinds of layers are called fully-connected because every neuron is connected to every neuron in the next layer. Each connection between two neurons has a weight, which is just a number. These weights form the brain of my network. For the activation function in my network, I use the sigmoid function. Sigmoid is a mathematical function. The sigmoid takes in some number x and converts it into a value between 0 and 1. That is ideal for my purposes, since I am dealing with binary numbers. This will turn a linear equation into something that is non-linear. This is important because without this, the network wouldn’t be able to learn any interesting things. I have already mentioned that the input to this network are 64 binary numbers. I resize the drawn image to 8x8 pixels which makes together 64 pixels. I go through the image and check each pixel if the pixel has a pink color I add a 1 to my array else I add a 0. At the end I will have 64 binary numbers which I can add to my input layer.

## nengo - A Python library for creating and simulating large-scale brain models

•    Python

Nengo is a Python library for building and simulating large-scale neural models. Nengo can create sophisticated spiking and non-spiking neural simulations with sensible defaults in a few lines of code. Yet, Nengo is highly extensible and flexible. You can define your own neuron types and learning rules, get input directly from hardware, build and run deep neural networks, drive robots, and even simulate your model on a completely different neural simulator or neuromorphic hardware. Nengo depends on NumPy, and we recommend that you install NumPy before installing Nengo. If you're not sure how to do this, we recommend using Anaconda.

## nnabla - Neural Network Libraries

•    C++

Neural Network Libraries is a deep learning framework that is intended to be used for research, development and production. We aim to have it running everywhere: desktop PCs, HPC clusters, embedded devices and production servers.This installs the CPU version of Neural Network Libraries. GPU-acceleration can be added by installing the CUDA extension with pip install nnabla-ext-cuda.

## brian2 - Brian is a free, open source simulator for spiking neural networks.

•    Python

Brian is a free, open source simulator for spiking neural networks. It is written in the Python programming language and is available on almost all platforms. We believe that a simulator should not only save the time of processors, but also the time of scientists. Brian is therefore designed to be easy to learn and use, highly flexible and easily extensible. Brian2 is released under the terms of the CeCILL 2.1 license.

## t81_558_deep_learning - Washington University (in St

•    Jupyter

Deep learning is a group of exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks of much greater complexity. Deep learning allows a neural network to learn hierarchies of information in a way that is like the function of the human brain. This course will introduce the student to computer vision with Convolution Neural Networks (CNN), time series analysis with Long Short-Term Memory (LSTM), classic neural network structures and application to computer security. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction mathematical foundations. Students will use the Python programming language to implement deep learning using Google TensorFlow and Keras. It is not necessary to know Python prior to this course; however, familiarity of at least one programming language is assumed. This course will be delivered in a hybrid format that includes both classroom and online instruction. This syllabus presents the expected class schedule, due dates, and reading assignments. Download current syllabus.

## mind - A neural network library built in JavaScript

•    Javascript

A flexible neural network library for Node.js and the browser. Check out a live demo of a movie recommendation engine built with Mind. Use plugins created by the Mind community to configure pre-trained networks that can go straight to making predictions.

## Applying_EANNs - A 2D Unity simulation in which cars learn to navigate themselves through different courses

•    ASP

Cars have to navigate through a course without touching the walls or any other obstacles of the course. A car has five front-facing sensors which measure the distance to obstacles in a given direction. The readings of these sensors serve as the input of the car's neural network. Each sensor points into a different direction, covering a front facing range of approximately 90 degrees. The maximum range of a sensor is 10 unity units. The output of the Neural Network then determines the car’s current engine and turning force. If you would like to tinker with the parameters of the simulation, you can do so in the Unity Editor. If you would simply like to run the simulation with default parameters, you can start the built file [Builds/Applying EANNs.exe](Builds/Applying EANNs.exe).

## Back-Propagation Neural Networks Simulation

•    CSharp

This is simple Back-Propagation Neural Network simulation using C#. This code is a part of my "Supervised Neural Network" book written in 2006.

## Amygdala Spiking Neural Network

•    C++

Amygdala is a C++ spiking neural network library. It includes several neuron models, SMP support and facilities for developing SNNs with genetic algorithms. Support for running Amygdala neural networks on workstation clusters and MPPs is also under way

## netcap - A framework for secure and scalable network traffic analysis

•    Go

The Netcap (NETwork CAPture) framework efficiently converts a stream of network packets into highly accessible type-safe structured data that represent specific protocols or custom abstractions. These audit records can be stored on disk or exchanged over the network, and are well suited as a data source for machine learning algorithms. Since parsing of untrusted input can be dangerous and network data is potentially malicious, implementation was performed in a programming language that provides a garbage collected memory safe runtime. It was developed for a series of experiments in my bachelor thesis: Implementation and evaluation of secure and scalable anomaly-based network intrusion detection. Currently, the thesis serves as documentation until the wiki is ready, it is included at the root of this repository (file: mied18.pdf). Slides from my presentation at the Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities are available on researchgate.

## graph-learn - An Industrial Graph Neural Network Framework

•    C++

Graph-Learn (formerly AliGraph) is a distributed framework designed for the development and application of large-scale graph neural networks. It abstracts a set of programming paradigms suitable for common graph neural network models from the practical problems of large-scale graph training, and has been successfully applied to many scenarios such as search recommendation, network security, knowledge graph, etc. within Alibaba. Graph-Learn provides both Python and C++ interfaces for graph sampling operations, and provides a gremlin-like GSL (Graph Sampling Language) interface. For upper layer graph learning models, Graph-Learn provides a set of paradigms and processes for model development. It is compatible with TensorFlow and PyTorch, and provides data layer, model layer interfaces and rich model examples.

## ngraph - nGraph is an open source C++ library, compiler and runtime for Deep Learning frameworks

•    C++

Welcome to the open-source repository for the Intel® nGraph™ Library. Our code base provides a Compiler and runtime suite of tools (APIs) designed to give developers maximum flexibility for their software design, allowing them to create or customize a scalable solution using any framework while also avoiding device-level hardware lock-in that is so common with many AI vendors. A neural network model compiled with nGraph can run on any of our currently-supported backends, and it will be able to run on any backends we support in the future with minimal disruption to your model. With nGraph, you can co-evolve your software and hardware's capabilities to stay at the forefront of your industry. The nGraph Compiler is Intel's graph compiler for Artificial Neural Networks. Documentation in this repo describes how you can program any framework to run training and inference computations on a variety of Backends including Intel® Architecture Processors (CPUs), Intel® Nervana™ Neural Network Processors (NNPs), cuDNN-compatible graphics cards (GPUs), custom VPUs like Movidius, and many others. The default CPU Backend also provides an interactive Interpreter mode that can be used to zero in on a DL model and create custom nGraph optimizations that can be used to further accelerate training or inference, in whatever scenario you need.

## komputation - Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C

•    Kotlin

Komputation is a neural network framework for the JVM written in the Kotlin programming language.

## ONE - On-device Neural Engine

•    Python

A high-performance, on-device neural network inference framework. This project ONE aims at providing a high-performance, on-device neural network (NN) inference framework that performs inference of a given NN model on processors, such as CPU, GPU, DSP or NPU.

## fann - Official github repository for Fast Artificial Neural Network Library (FANN)

•    C++

Fast Artificial Neural Network (FANN) Library is a free open source neural network library, which implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution in both fixed and floating point are supported. It includes a framework for easy handling of training data sets. It is easy to use, versatile, well documented, and fast.

## Java Neural Network Framework Neuroph

•    Java

Neuroph is lightweight Java Neural Network Framework which can be used to develop common neural network architectures. Small number of basic classes which correspond to basic NN concepts, and GUI editor makes it easy to learn and use.

## BrainCore - The iOS and OS X neural network framework

•    Swift

BrainCore is a simple but fast neural network framework written in Swift. It uses Metal which makes it screamin' fast. If you want to see it in action check out InfiniteMonkeys—an app that uses a recursive neural network to generate poems. When splitting, the inputSize of the target layers will determine where to split. If the sum of the target layers' inputSizes doesn't match the source layer's outputSize and error will be thrown.

## adanet - Fast and flexible AutoML with learning guarantees.

•    Jupyter

AdaNet is a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert intervention. AdaNet builds on recent AutoML efforts to be fast and flexible while providing learning guarantees. Importantly, AdaNet provides a general framework for not only learning a neural network architecture, but also for learning to ensemble to obtain even better models. This project is based on the AdaNet algorithm, presented in “AdaNet: Adaptive Structural Learning of Artificial Neural Networks” at ICML 2017, for learning the structure of a neural network as an ensemble of subnetworks.

## Eddie's Neural Network Framework

•

Eddie's Neural Network Framework is an experimental .NET Library to make the creation, modification and storage of Neural Networks easier. Technologies used: .NET 4.0, Entity Framework & SQL Server 2008 R2

## iqr large-scale neural systems simulator

•    C++

iqr is a simulation software to graphically design and control large-scale neuronal models. Simulations in iqr can control real-world devices in real-time. iqr can be extended by new neuron, and synapse types, and custom interfaces to hardware.

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.