Parent class. The constructor is used to set properties for all the subclasses which inherits from this class.
The Input class with which we will input the data to mini-learn
performs linear transformation using the formula Y = mX + b
Represents a node that performs the sigmoid activation function. We use the formula ฯ = 1 / 1 + e**-x
The mean squared error cost function. More about MSE: https://en.wikipedia.org/wiki/Mean_squared_error
A class consisting of several static functions:
Sort the nodes in topological order using Kahn's Algorithm.
Performs a forward pass and a backward pass through a list of sorted Nodes.
Updates the value of each trainable with Stochastic gradient descent
This project must strictly be used for educational purposes only