1	Collect the dataset and define its path, epoch, and batch size
2	Extract images and class labels from existing files
3	Normalize the pixel value array
4	During network initialization, randomly determine a startup weight.
5	Choose the initial pair of exercises
6	The forward calculation, comprising the subsequent steps:
	a. Connect the input to the network.
	b. Figure out the result for each neuron from the input layer to the output layer through the hidden layer.
	c. Figure out the error at the output.
7	Countdown with the subsequent steps
	a. Use the result error to calculate the error signal for the pre-output layer.
	b. Use the error signal to calculate the weight correction.
	c. Make appropriate adjustments to weight
	d. Repeat the calculation in reverse for the remaining exercise pairs
	e. Perform periodic network performance evaluations
8	Iterate the calculation until the network reaches the desired exit.