ML is a sub-area of AI that aims to create systems and machines that can learn from experience, without being explicitly programmed. As the name suggests, the system can observe its underlying environment, learn, and adapt itself without human intervention. Algorithms behind ML systems usually extract and improve knowledge from the data and conditions that are available to them.
Figure 1.2 – Hierarchy of AI, ML, and DL
You should keep in mind that there are different classes of ML algorithms. For example, decision tree-based models, probabilistic-based models, and neural network models. Each of these classes might contain dozens of specific algorithms or architectures (some of them will be covered in later sections of this book).
As you might have noticed in Figure 1.2, you can be even more specific and break the ML field down into another very important topic for the Machine Learning Specialty exam: deep learning, or DL for short.
DL is a subset of ML that aims to propose algorithms that connect multiple layers to solve a particular problem. The knowledge is then passed through, layer by layer, until the optimal solution is found. The most common type of DL algorithm is deep neural networks.
At the time of writing this book, DL is a very hot topic in the field of ML. Most of the current state-of-the-art algorithms for machine translation, image captioning, and computer vision were proposed in the past few years and are a part of the DL field (GPT-4, used by the ChatGPT application, is one of these algorithms).
Now that you have an overview of types of AI, take a look at some of the ways you can classify ML.
ML is a very extensive field of study; that’s why it is very important to have a clear definition of its sub-divisions. From a very broad perspective, you can split ML algorithms into two main classes: supervised learning and unsupervised learning.
Acedexam Training Policies
Learning resources
Other resources
Our Training Providers
