Displaying 1 to 20 from 32 results

emoj - Find relevant emoji from text on the command-line :open_mouth: :sparkles: :raised_hands: :horse: :boom: :see_no_evil:

  •    Javascript

Uses the API from this great article on Emoji & Deep Learning. Check out the Dango app if you want something like this on your phone.Works best on macOS. Terminals on Linux render emojis in monochrome as they don't support color emojis. On Linux, I would recommend installing Emoji One for full emoji coverage. Doesn't really work on Windows.

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.

keras-js - Run Keras models in the browser, with GPU support using WebGL

  •    Javascript

**This project is no longer active. Please check out TensorFlow.js.** The Keras.js demos still work but is no longer updated. Run Keras models in the browser, with GPU support provided by WebGL 2. Models can be run in Node.js as well, but only in CPU mode. Because Keras abstracts away a number of frameworks as backends, the models can be trained in any backend, including TensorFlow, CNTK, etc.




opencv4nodejs - Asynchronous OpenCV 3

  •    C++

By its nature, JavaScript lacks the performance to implement Computer Vision tasks efficiently. Therefore this package brings the performance of the native OpenCV library to your Node.js application. This project targets OpenCV 3 and provides an asynchronous as well as an synchronous API. The ultimate goal of this project is to provide a comprehensive collection of Node.js bindings to the API of OpenCV and the OpenCV-contrib modules. An overview of available bindings can be found in the API Documentation. Furthermore, contribution is highly appreciated. If you want to get involved you can have a look at the contribution guide.

tinn - The tiny neural network library

  •    C

Tinn (Tiny Neural Network) is a 200 line dependency free neural network library written in C99. The training data consists of hand written digits written both slowly and quickly. Each line in the data set corresponds to one handwritten digit. Each digit is 16x16 pixels in size giving 256 inputs to the neural network.

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.

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.


regl-cnn - Digit recognition with Convolutional Neural Networks in WebGL

  •    Javascript

GPU accelerated handwritten digit recognition with regl. Note that this network will probably be slower than the corresponding network implemented on the CPU. This is because of the overhead associated with transferring data to and from the GPU. But in the future we will attempt implementing more complex networks in the browser, such as Neural Style, and then we think that we will see a significant speedup compared to the CPU.

NeoCognitron

  •    

This software simulator is proposed for a study of the Neocognitron neural network. Neocognitron was initially suggested by his author, Kunihiko Fukushima, as a neural model for pattern recognition which mimics the organization and processing in biological vision.

Toy-Neural-Network-JS - Neural Network JavaScript library for Coding Train tutorials

  •    Javascript

Please send PullRequests. These need to pass a automated Test first and after it will get reviewed and on that review either denied or accepted. Feel free to add your own libraries.

wAlnut - research into how to solve the AGI problem

  •    

The answer is you can not. I now believe AGI should not be built privately or publicly and instead one possible solution is to increase human intelligence with a privately built neural lace like Neuralink which you can read about here. Q2: How do you create a safe neural lace for anyone who wants one?.

node-facenet - Solve face verification, recognition and clustering problems: A TensorFlow backed FaceNet implementation for Node

  •    TypeScript

A TensorFlow backed FaceNet implementation for Node.js, which can solve face verification, recognition and clustering problems. FaceNet is a deep convolutional network designed by Google, trained to solve face verification, recognition and clustering problem with efficiently at scale.

neuraln

  •    C++

With Node.js and the V8, it is not possible to work with large datasets since the maximum allowed memory is around 512MB for 32-bits machines and 1GB for 64-bits machines. When you are working with datasets of several gigabytes, it quickly becomes difficult to train you network with all your data. NeuralN allows you to use datasets as big as your memory can contain.

neurolib - Neuron emulation tools

  •    Javascript

A collection of utilities that might be useful in the simulation or emulation of neurons for an artificial neural network.The focus of this library is an attempt to simulate the spike-timing-dependent plasticity learning mechanics of real neurons, as opposed to running math abstractions like stochastic gradient descent to accomplish machine learning.

netural - netural === neural net, simple AI for the web.

  •    Javascript

netural === neural net, simple AI for the web. This content is released under the MIT License.

nn - Fast and simple Neural Network for node.js

  •    Javascript

nn is a Neural Network library built for performance and ease of use. It is easy to configure and has sane defaults. You can use it for tasks such as pattern recognition and function approximation. Creates a Neural Network instance. Pass in an optional opts object to configure the instance. Any values specified in opts will override the corresponding defaults.

snakeneuralnetworkjs - Neuroevolution of Neural Network for snakes in the Browser

  •    Javascript

This is a demonstration of evolving a neural network thanks to genetics algorithms in the browser using a multilayer perceptron (150-15-15-1). The initial population contains 36 individuals, each assigned a different genome. They will fight following a round-robin tournament. At the end the top 7 are kept alive, and the remaining 29 are created by breeding from the 7.

neuroJS - Neural network implementation in JavaScript.

  •    Javascript

##About neuroJS is a neural network library written in JavaScript. ##Usage Use the library by opening test.html in either Chrome of Firefox and opening the console.

node-ml - A Collection of Machine Learning algorithms built for use with NodeJS

  •    Javascript

( Development is current suspended ). Models are acted upon by the perceive or predict functions. These functions currently do the same thing, the wording is indicative of the nature of the result, and the action the model has taken on the data.