This application enables you to construct Multi-Layer Neural Networks for the purpose of multi-class classification.

The main difference is, in addition to the Sigmoid function, the hidden layers can utilize activation functions such as ReLU, Leaky ReLU, and Tanh. For multi-class classification, the output function can be Softmax.

These datasets generated in Python using scikit-learn. Here is the code used to do this.

# Install dependencies
$ npm install

# Run the development server
$ npm run dev