Artificial Intelligence. You’ve probably heard the term before and imagined robots doing your work or driving for you, but that’s not all AI is. Every time you open your web browser, AI is guessing what you are going to search. All those ads you see on the side are companies targeting you based on what you searched.
So what exactly is AI?
In simple terms, AI is an area of computer science that aims to make machines behave the way humans do. To accomplish this we have 2 main ideas; narrow and general AI.
Narrow AI is all around us today, in our computers, phones, cars, and more. They all have intelligent systems that have learned how to accomplish specific tasks without being explicitly programmed to do so. Take a self-driving car for example; the programmers didn’t tell the car exactly how to turn left on Queen Street, they just told the car how to turn left. Through trial and error, the car learns the best way to turn left based on specific surroundings.
However, unlike humans, narrow AI can only learn how to do specific tasks, creating the need for many specialized AI machines.
General AI is the concept of one AI machine being able to carry out multiple tasks like a human can. This would decrease the need for many of specific AI machines, increasing the productivity of a singular one. General AI however, is still just seen in movies and not the real world. Despite that, many advances are being made to make this a reality.
How does AI work?
AI functions under three ideas; machine learning, deep learning, and neural networks.
Machine learning gives computers the opportunity to learn without being explicitly programmed, by using provided data to teach themselves. The computer looks for patterns in the data so that it can make better, more informed decisions in the future. Machine Learning can be used to understand different data sets like language, images, and sound, and can help with decisions that would take humans very long to figure out given the amount of data.
Deep learning is a form of machine learning where the computer goes in-depth on one specific feature. This helps it be more accurate which in turn can improve the outcome in the case of a self-driving car. Deep learning usually functions by using neural networks.
Neural networks consist of several layers that each process information like a human nervous system. There is an input and an output layer along with one or more hidden layers in between. All the layers are connected and use the output from the previous layer as it’s input.
The more the neural network is trained, the better accuracy there will be in the result. Neural networks are better than machine learning for accomplishing specific tasks.
- AI is an area of computer science that aims to make machines behave the way humans do
- There are two types of AI, narrow and general, but only narrow AI is a reality right now
- Machine learning is getting a computer to learn without it being explicitly programmed
- Deep learning is diving deeper into one specific feature of the data
- Neural Networks are how we process information in one specific feature
Thank you for reading my article on Artificial Intelligence and I hope you now have a better understanding of what AI is and how it works.