cazala/synaptic
A JavaScript neural network library for building and training neural network architectures in Node.js and browsers.
Not currently ranked — collecting fresh signals.
star history
Synaptic is an architecture-free neural network library for JavaScript that supports various neural network types including multilayer perceptrons, LSTM networks, liquid state machines, and Hopfield networks. It includes a built-in trainer capable of training any given network architecture, with built-in tasks like solving XOR, completing Distracted Sequence Recall, and passing the Embedded Reber Grammar test. The library implements generalized algorithms derived from Derek D. Monner’s paper on LSTM-like training for second-order recurrent networks.
Frequently asked
- What is cazala/synaptic?
- A JavaScript neural network library for building and training neural network architectures in Node.js and browsers.
- Is synaptic open source?
- Yes — cazala/synaptic is an open-source project tracked on heatdrop.
- What language is synaptic written in?
- cazala/synaptic is primarily written in JavaScript.
- How popular is synaptic?
- cazala/synaptic has 6.9k stars on GitHub.
- Where can I find synaptic?
- cazala/synaptic is on GitHub at https://github.com/cazala/synaptic.