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.

mind neural-network prediction machine-learning learning sigmoid network neuron neural nn

pytorch-book - PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation

•    Jupyter

---

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation

pytorch pytorch-tutorials pytorch-tutorials-cn deep-learning neural-style charrnn gan caption neuraltalk image-classification visdom tensorboard nn tensor autograd jupyter-notebook

node-nanomsg - Node.js binding for nanomsg

•    Javascript

---

This is the default way of installing node-nanomsg. Behind the scenes, nanomsg library will be downloaded, built and statically linked, providing the simplest and easiest way to start working. Starts a new socket. The nanomsg socket can bind or connect to multiple heterogeneous endpoints as well as shutdown any of these established links.

nanomsg native binding addon nn nanømsg

tensorflow-node - Tensorflow for node.js

•    C++

---

Tensorflow for node.js

tensorflow tf machinelearning ml deeplearning dl neuralnetworks nn js

neatjs - A javascript implementation of Neuro Evolution of Augmenting Topologies

•    Javascript

---

NeuroEvolution of Augmenting Topologies (NEAT) implemented in Javascript (with tests done in Mocha for verification). Can be used as a node module or in a browser

neural-network nn artificial-neural-networks ann cppn neat hyperneat

juggernaut - Neural Network in Rust

•    Rust

---

and the output of think is the prediction of the network after training.

nn neural-network

static-kdtree - A static kdtree data structure

•    Javascript

---

kd-trees are a compact data structure for answering orthogonal range and nearest neighbor queries on higher dimensional point data in linear time. While they are not as efficient at answering orthogonal range queries as range trees - especially in low dimensions - kdtrees consume exponentially less space, support k-nearest neighbor queries and are relatively cheap to construct. This makes them useful in small to medium dimensions for achieving a modest speed up over a linear scan. It is also worth mentioning that for approximate nearest neighbor queries or queries with a fixed size radius, grids and locality sensitive hashing are strictly better options. In these charts the transition between "Medium" and "Big" depends on how many points there are in the data structure. As the number of points grows larger, the dimension at which kdtrees become practical goes up.

kdtree static pure range orthogonal bounding box point sphere query nearest neighbor knn nn rnn searching closest

nn - safe navigation of object trees

•    Javascript

---

NeverNull provides the ability to safely navigate an object tree, regardless if the object, its properties, or nested properties exist. The function-object returned from nn guarantees safe navigation of its object tree. This allows us to avoid boilerplate value checking.

null-pointer-exception never-null nn typeerror-cannot-access-property typeerror-cannot-access-property-of-undefined of-undefined safe-navigation existential-operator elvis-operator optional-chaining

node-i18n-iso-countries - i18n for ISO 3166-1 country codes

•    Javascript

---

If you use i18n-iso-countries with Node.js your are done. If you use the package in a browser environment you also have to register the languages you want to use to minimize file size.

i18n iso 3166 iso-3166 iso-3166-1 alpha alpha-2 alpha-3 numeric country countries ar az be bg bs ca cs da de el en es et fa fi fr he hr hu hy id it ja ka kk ko ky lt lv mk mn nb nl nn pl pt ro ru sk sl sr sv tg tk tr uk uz zh

Credit-Card-Fraud - A Very Deep Neural Network that can classify Credit Card Fraudulent Transaction with 99

•    Jupyter

---

In the world of Technology, Credit Card Fraudulent Transactions are fairly Common and this is a Deep Neural Network (Algorithm) that can classify these transactions just by looking at the data with 99.92% Accuracy which is likely to be very accurate. This Neural Network is based of the Credit-Card-Fraud Data available on Kaggle, It contains a whooping 248,407 Transactions which occurred in September 2013 by European Card Holders.

jupyter tensorflow keras deep neural network nn dnn kaggle credit card

wann - :balance_scale: Weight Agnostic Neural Networks in Go

•    Go

---

Weight Agnostic Neural Networks is a new type of neural network, where the weights of all the neurons are shared and the structure of the network is what matters. This makes sense, since taking the third number in the input data (index 2), running it through a swish function and then inverting it should be a usable detector for the up pattern.

neural-network nn svg-diagram wann weight-agnostic-neural-network