Scientists created neural networks by way of mimicry of the human brain. Neuron-like nodes compose a neural network. The neural network works by first receiving input, which is processed by the neurons of the network. After processing the input, the neurons then give output. What's special is the neurons can be trained before use.
Machine learning is a large field, including many types of learning methods. It is a form of data analysis and model-building that can improve by itself or by way of human assistance. For example, in supervised machine learning, a machine begins by taking in data with which to train and make a model. After the model is made, the machine uses it to make predictions on some data. The human then gives feedback to the machine, which the machine uses to improve its performance.
The main advantage of neural networks and machine learning lies in their ability to handle complex relationships between the input and output of large data sets. This is something humans cannot do without the aid of a machine. In addition, neural networks and machine learning also benefit from being able to learn as they gain more experience analyzing data. Perhaps the most amazing thing about them is that they can analyze linear and nonlinear relationships in the data merely by inputting the data.