A machine is said to be "learning" if its performance or efficiency for a given task improves with the experience (past data). Machine Learning uses advanced algorithms to analyze and learn relationships between the data to make intelligent decisions on what it has learned. The algorithms use a large amount of data to find the relationship. This relationship is called a "model" which is used to make useful predictions or generate content from the data.
For example, we need physics-based mathematical equations of Earth's atmosphere to 
predict rainfall using traditional methods. Solving these complex equations requires massive computing resources and time, making the prediction task difficult. With the ML approach, we could provide enormous data to an ML model until the ML model eventually learned the mathematical relationship between weather factors producing varying quantities of rain. If we give this model the current weather data, it would predict the amount of rain in the future.

Figure 1 shows the difference between hardcoding the instructions to carry out a specific task versus using ML.
Figure 1: Achieving a task with and without ML [1]
How generic AI differs from ML?
AI system: Recommend songs to EVERYONE based on number of copies sold, top 10 in Billboard list, Grammy award winners, etc.
ML system: Recommend songs to each INDIVIDUAL based on previous songs played, other people with similar playlist, choice of singer, genre, etc.
When using Machine Learning, Neural Networks, or Deep Learning, it is important to know the meaning of the following terms:
There are 4 major types of ML problems:
Figure (2) gives the example of supervised and unsupervised Learning. In figure (2), the classification task is to predict if the user has purchased or not (1 or 0). The regression task is to predict the wind speed.


Figure 2: Example of supervised and unsupervised learning