Python has been the primary language for most Deep/Machine Learning enthusiasts, but there are quite a few JavaScript libraries that bring the magic of ML directly to the browser. Brain.js is one of the most popular JavaScript ML libraries known for its simple and easy usage. The library greatly simplifies building and training Neural Networks to just a few lines of code eliminating much of the math and jargon needed to fully understand the theoretical aspects of the model.

Brain.js supports a few different Neural Network type, for this demonstration I will be looking into a Feedforward (ANN) and LSTM network. For further exploration of the library, check out their repository here. In addition, the library has pros and cons like any other that we will explore in the end.

NOTE(s): I am much more of a Python developer and am still in the process of getting proficient with JavaScript, so feel free to point out any best practices coding wise. This article is also not meant to explore the theory behind Deep Learning, it is purely exploring how to create Neural Network architectures with Brain.js. If you want a video demo instead of the article, I am linking a simple, but clean Youtube video that goes through a Brain.js example.

#machine-learning #javascript #deep-learning #web-development #nodejs