Machine Learning and AI (artificial intelligence) course teach the tools that can be used for building intelligent machines. Students learn SciPi, OpenCV, and TensorFlow in this level.
This is a great program for high-schoolers and middle-schoolers, that already have good Python Programming knowledge.
ML works with data and processes it to discover patterns that can be later used to analyze new data. ML usually relies on the specific representation of data, a set of “features” that are understandable for a computer. For example, if we are talking about text it should be represented through the words it contains or some other characteristics such as the length of the text, the number of emotional words etc. This presentation depends on the task you are dealing with and is typically referred to as “feature extraction”.
Types of ML
All ML tasks can be classified as several categories, the main ones are:
What do we need to use ML?
Given the fact that ML relies on data, the most important requirement of using ML is having the data you can use to train ML model. The amount of data needed depends on what you are looking for and how complex your problem is. However, collecting more data is always a good idea. One should also keep in mind that this data (that you want to train your ML on) should be similar to the one you want to make predictions on later. For example, looking at reviews of books and learning to predict opinions of people (positive or negative) about some books, may yield not really great results when applied to reviews of mobile phones or laptops.
Another requirement involves your ability to formulate the question you want to pose to an ML expert, you need to know what you want to get as a result. For example, you can ask to have a look at the purchases in your online shop over the last few years and predict sales for the next year. However, it would be unreasonable to ask for such an estimate if you just opened a shop and have no data available. ML is certainly powerful but it is not magic!