This course introduces machine learning on Google Cloud Platform.
- What machine learning actually means
- The types of problems machine learning can solve
- The basics of how machine learning works
- Anyone interested in machine learning
- A basic understanding of computers
So you probably already heard the term “machine learning” before. You might have also heard about “artificial intelligence” and even “deep learning”. It seems like every new product touts one or more of those as a feature. Today we have robotic cars, vacuums, and even lawnmowers. But what do these terms actually mean? And do they all mean the same thing? Or are they different?
In this lesson, I am going to explain the differences between machine learning (ML), artificial intelligence (AI), and Deep Learning. I will also explain how they are related to each other.
Let’s first start with artificial intelligence. AI is a branch of computer science whose goal is to create an intelligent, thinking machine. So we want to build something like C3PO from Star Wars, or Commander Data from Star Trek. Essentially, we want a machine that can solve complex problems on its own, without needing a human. Today, machines only do exactly what they are told. But what if they could complete tasks just like a person?
Now the main problem with AI is that we have absolutely no idea how to accomplish this. We know where we are today, and we know where we want to be tomorrow. But how to connect those two points is frankly a mystery. The problem is just too big, and the gulf of knowledge is too wide.
So this is where machine learning comes in. Machine learning is a subset of artificial intelligence. You can think of it as being a small first step on the long road to creating an AI. Machine learning has a much more achievable goal than artificial intelligence. Machine learning is just trying to create algorithms that can “learn” or improve on their own.
Theoretically, if we can figure out how to make our current devices get smarter over time, then one day they might be smart enough to rival or even surpass a human. So AI has the bigger, loftier goal of creating intelligent machines. Machine learning is just concerned with figuring out how to make our current machines smarter.
There are different ways of accomplishing machine learning. One popular way is called deep learning. Just like machine learning is a subset of artificial learning, deep learning is a subset of machine learning. More accurately, deep learning is actually a subset of neural networks, which is a subset of machine learning.
Neural networks represent a specific implementation of ML. Essentially, in order to teach machines how to learn, neural networks try to copy the human brain. Neural networks are composed of a collection of nodes. These nodes basically mimic neurons or brain cells. Neural networks have a series of input nodes, a series of output nodes, and a hidden layer in between. By adding or changing connections, you can create a fairly complex problem-solving system.
Deep learning is a specific type of neural network. Essentially, deep learning is a neural network with multiple hidden layers. By adding additional layers of nodes and connections, you can potentially handle even greater complexity.
So AI is the end goal: a thinking, intelligent machine. It sits at the top and encompasses all the others. Machine learning is a smaller subset that is focused just on making machines learn. Then neural networks are a subset of ML that tries to make machines learn by copying the human brain. And finally, deep learning is an advanced form of neural networks that adds additional hidden layers of nodes to handle extra complexity.
Ok, so that’s a very high-level description and it leaves out some of the finer details. But it should give you a good starting point. Now when you see the terms “deep learning” or “artificial intelligence”, you should understand what they actually mean.
Daniel began his career as a Software Engineer, focusing mostly on web and mobile development. After twenty years of dealing with insufficient training and fragmented documentation, he decided to use his extensive experience to help the next generation of engineers.
Daniel has spent his most recent years designing and running technical classes for both Amazon and Microsoft. Today at Cloud Academy, he is working on building out an extensive Google Cloud training library.
When he isn’t working or tinkering in his home lab, Daniel enjoys BBQing, target shooting, and watching classic movies.