Answer: Deep learning is a subarea of machine learning which is a subarea of artificial intelligence. Data science is an interdisciplinary area that combines all of those with math and programming skills to extract useful insights from data.
“I’m trying to understand how the area of skills are related to each other, and one is a dependency of another. I hope you clarify for me where to start and how the path looks like. I know it’s a complicated question.” — Barakah, Python Freelancer Course Member
Let’s start with a simple visualization that’ll help you understand how these four areas — Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and Data Science — relate to each other.
Artificial Intelligence: A recent definition of artificial intelligence speaks from “imitating intelligent human behavior” by machines. It is in contrast to “natural”, i.e., biological, intelligence. Artificial intelligence consists of many subtopics such as reasoning, knowledge representation, logic, machine learning, planning, robotics. Hence, it’s a very broad term to describe the interdisciplinary field of creating machines that act intelligently. If you want to get a general overview, read this article.
Machine Learning: An excellent definition has been published in the Journal Machine Learning in Radiation Oncology:
💬 “Machine learning is an evolving branch of computational algorithms that are designed to emulate human intelligence by learning from the surrounding environment. They are considered the working horse in the new era of the so-called big data.”
An important highlight is that it’s learning based on observed data. Thus, it’s only one way of addressing the problem of creating artificial intelligence. If you want to get a thorough introduction in machine learning, dive into the free course from one of the world’s leading experts in machine learning, Andrew Ng.
Deep Learning: If you know about the general field of AI and the specific area of machine learning, it’s time to dive into the even more specific area of deep learning:
💬 “A class of machine learning techniques that exploit many layers of non-linear information processing for supervised or unsupervised feature extraction and transformation, and for pattern analysis and classification.” (source)
It’s a more complicated definition because it builds on terminology known by machine learning experts. It doesn’t make a lot of sense to learn deep learning before you have a basic understanding of machine learning—just as it makes no sense to read Shakespeare before you can read the alphabet. However, if you want to get a good overview of deep learning, read this article.
Data Science: In contrast to the other three definitions, data science is an interdisciplinary field leveraging insights from many fields to extract knowledge from data.
💬 “Data science is the field of study that combines domain expertise, programming skills, and knowledge of mathematics and statistics to extract meaningful insights from data.” (source)
It leverages different fields in artificial intelligence (and machine learning), statistics, math, and computer programming to extract meaning. If you want to improve your Python data science skills, start with the NumPy library by reading NumPy textbooks.
While working as a researcher in distributed systems, Dr. Christian Mayer found his love for teaching computer science students.
To help students reach higher levels of Python success, he founded the programming education website Finxter.com. He’s author of the popular programming book Python One-Liners (NoStarch 2020), coauthor of the Coffee Break Python series of self-published books, computer science enthusiast, freelancer, and owner of one of the top 10 largest Python blogs worldwide.
His passions are writing, reading, and coding. But his greatest passion is to serve aspiring coders through Finxter and help them to boost their skills. You can join his free email academy here.