We dived head first into the world of ANN. ANN are computer approximations of human nerve cell processes, and are composed of artificial neurons. Each neuron has several parts: inputs, weights, bias, and activation.
The ANN can be thought of as a stepwise non-linear approximation function that slowly adjusts itself to fit a curve that matches the desired input to the desired output. This process happens through the learning function. The learning process has several steps, including preparing data, labeling data, creating the network, initializing the weights, the forward pass that provides the output, and the calculation of loss (also called error). The weights of the individual neurons are adjusted by backpropogation, which starts at the output and works backward to apportion error to each neuron and each neuron input.
We created a CNN to examine images. The network...
