Artificial Intelligence (AI), the new buzzword in the world of technology, is set to change the way future generations will function. But what exactly is AI and how does AI work? You may not be aware of it, but you probably interact with AI on a daily basis. From smartphones to chatbots, AI is already prevalent in many aspects of our lives. Growing investments in this area and AI’s increasing use in the enterprise space are indicative of how the job market is warming up for AI experts.
What Is AI?
Let us begin this tutorial by first understanding what is AI and how does AI work. AI is probably one of the most exciting advancements that we're in the middle of experiencing as humans. It is a branch of computer science dedicated to creating intelligent machines that work and react like humans.
Let us cover the types of AI in the next section of this tutorial.
Types of AI
There are four main types of AI. They are:
1. Reactive Machines
This kind of AI is purely reactive and does not have the ability to form ‘memories’ or use ‘past experiences’ to make decisions. These machines are designed to perform specific tasks. For example, programmable coffeemakers or washing machines are designed to perform specific functions, but they do not have memory.
2. Limited Memory AI
This kind of AI uses past experiences and the present data to make a decision. Limited memory means that the machines are not coming up with new ideas. They have a built-in program running the memory. Reprogramming is done to make changes in such machines. Self-driving cars are examples of limited memory AI.
3. Theory of Mind
These AI machines can socialize and understand human emotions and will have the ability to cognitively understand somebody based on the environment, their facial features, etc. Machines with such abilities have not been developed yet. There is a lot of research happening with this type of AI.
4. Self-Awareness
This is the future of AI. These machines will be super-intelligent, sentient and conscious. They are able to react very much like a human being, although they are likely to have their own features.
The next section of this tutorial will help you get a better understanding on how exactly to implement AI.
Ways of Implementing AI
Let’s explore the following ways that explain how we can implement AI:
Machine Learning
It is machine learning that gives AI the ability to learn. This is done by using algorithms to discover patterns and generate insights from the data they are exposed to.
Deep Learning
Deep learning, which is a subcategory of machine learning, provides AI with the ability to mimic a human brain’s neural network. It can make sense of patterns, noise, and sources of confusion in the data.
Consider an image shown below:
Here we segregated the various kinds of images using deep learning. The machine goes through various features of photographs and distinguishes them with a process called feature extraction. Based on the features of each photo, the machine segregates them into different categories, such as landscape, portrait, or others.
Let us understand how deep learning works.
Consider an image shown below:
The above image depicts the three main layers of a neural network:
- Input Layer
- Hidden Layer
- Output Layer
Input Layer
The images that we want to segregate go into the input layer. Arrows are drawn from the image on to the individual dots of the input layer. Each of the white dots in the yellow layer (input layer) are a pixel in the picture. These images fill the white dots in the input layer.
We should have a clear idea of these three layers while going through this artificial intelligence tutorial.
Hidden Layer
The hidden layers are responsible for all the mathematical computations or feature extraction on our inputs. In the above image, the layers shown in orange represent the hidden layers. The lines that are seen between these layers are called ‘weights’. Each one of them usually represents a float number, or a decimal number, which is multiplied by the value in the input layer. All the weights add up in the hidden layer. The dots in the hidden layer represent a value based on the sum of the weights. These values are then passed to the next hidden layer.
You may be wondering why there are multiple layers. The hidden layers function as alternatives to some degree. The more the hidden layers are, the more complex the data that goes in and what can be produced. The accuracy of the predicted output generally depends on the number of hidden layers present and the complexity of the data going in.
Output Layer
The output layer gives us segregated photos. Once the layer adds up all these weights being fed in, it'll determine if the picture is a portrait or a landscape.
Example - Predicting Airfare Costs
This prediction is based on various factors, including:
- Airline
- Origin airport
- Destination airport
- Departure date
We begin with some historical data on ticket prices to train the machine. Once our machine is trained, we share new data that will predict the costs. Earlier, when we learned about four kinds of machines, we discussed machines with memory. Here, we talk about the memory only, and how it understands a pattern in the data and uses it to make predictions for the new prices as shown below:
Next up in this tutorial let us take a look at how does AI work and applications of AI.
How Does AI Work and applications of AI
A common AI application that we see today is the automatic switching of appliances at home.
When you enter a dark room, the sensors in the room detect your presence and turn on the lights. This is an example of non-memory machines. Some of the more advanced AI programs are even able to predict your usage pattern and turn on appliances before you explicitly give instructions.
Some AI programs are able to identify your voice and perform an action accordingly. If you say, “turn on the TV”, the sound sensors on the TV detect your voice and turn it on.
With the Google dongle and a Google Home Mini, you can actually do this every day.
The last section of this Artificial Intelligence tutorial discusses the use case of AI in healthcare.
Use Case - Predicting if a Person has Diabetes
AI has several amazing use cases, and this section of the tutorial will help you understand them better, beginning with the application of AI in the healthcare field. The problem statement is predicting whether a person has diabetes or not. Specific information about the patient is used as input for this case. This information will include:
- Number of pregnancies (if female)
- Glucose concentration
- Blood pressure
- Age
- Insulin level
Check out the Simplilearn's video on "Artificial Intelligence Tutorial" to see how a model for this problem statement is created. The model is implemented with Python using TensorFlow.
Learn from the best in the AI/ML industry with our Caltech Artificial Intelligence Course! Enroll now to get started!
Conclusion
AI is redefining the way business processes are carried out in various fields, such as marketing, healthcare, financial services, and more. Companies are continuously exploring the ways they can reap benefits from this technology. As the quest for improvement of current processes continues to grow, it makes sense for professionals to gain expertise in AI.
If you found this tutorial informative, you can also check out our Caltech AI Course. The course will help you learn the basic concepts of AI, data science, machine learning, deep learning with TensorFlow and more. Apart from the theory, you will also get the opportunity to apply your skills to solve real-world problems through industry-oriented projects. So, without further ado, start your career in AI and get ahead!
