Neataptic offers flexible neural networks; neurons and synapses can be removed with a single line of code. No fixed architecture is required for neural networks to function at all. This flexibility allows networks to be shaped for your dataset through neuro-evolution, which is done using multiple threads.
// this network learns the XOR gate (through neuro-evolution)var network = 21;var trainingSet =input: 00 output: 0input: 01 output: 1input: 10 output: 1input: 11 output: 0;await network;
Neataptic also backpropagates more than 5x faster than competitors. Run the tests yourself. This is an example of regular training in Neataptic:
// this network learns the XOR gate (through backpropagation)var network = 2 4 1;// training set same as in above examplenetwork;network; // 0.9824...
Use any of the 6 built-in networks with customisable sizes to create a network:
var myNetwork = 1 10 5 1;
Or built your own network with pre-built layers:
var input = 2;var hidden1 = 5;var hidden2 = 3;var output = 1;input;hidden1;hidden2;var myNetwork = architect;
You can even built your network neuron-by-neuron using nodes and groups!
Neural networks can be used for nearly anything; driving a car, playing a game and even to predict words! At this moment, the website only displays a small amount of examples. If you have an interesting project that you want to share with other users of Neataptic, feel free to create a pull request!
Neuroevolution examples (supervised)
LSTM timeseries (supervised)
Color classification (supervised)
Target seeking AI (unsupervised)
Neataptic files are hosted by rawgit, just copy this link into the
Installing with node is also possible:
npm install neataptic
Make sure you have Node.js
v7.6 or higher installed!
Parts of Synaptic where used to develop Neataptic.
The neuro-evolution algorithm used is the Instinct algorithm.