Table of contents
The rapid pace of technological evolution has brought about a significant boom in Artificial Intelligence (AI) and Machine Learning (ML) technologies. From image generation to natural language processing, there has been remarkable progress. While these technologies have existed previously, the emergence of GPT models has added a new dimension to this landscape, making things even more intriguing.
The Start
The future is here, and its name is machine learning. With applications spanning across nearly every industry, from medicine to banking, from self-driving cars to coffee ordering, the interest in machine learning has been steadily increasing day by day. But what exactly is machine learning?
When I read a book or attend a class about machine learning, it's usually packed with complicated math formulas or lines of computer code. For a while, I thought that's all there was to it, and that only super smart folks who know a lot about math and computers could understand it.
But then I started comparing machine learning to something more familiar, like music. Music theory can be really complex, but when we think about music, we don't just think about notes and scales; we think about songs and tunes.
So, I started wondering if machine learning might have a similar side to it. Is it more than just a bunch of formulas and code? Could there be a cool, catchy "melody" hidden in there somewhere?
Machine learning is spreading everywhere, making life better in many ways. It's hard to think of something that can't be improved by it. If a task involves doing the same thing over and over or sorting through lots of data to figure things out, machine learning can help.
In recent years, machine learning has grown a lot because computers are getting more powerful, and we're collecting more data than ever before. There are tons of things machine learning can do: suggest what you might like online, recognize pictures, understand text, help cars drive themselves, spot spam emails, diagnose medical problems, and more.
Maybe you've got a goal or an area where you want to make a difference — or maybe you're already doing it!
How it is similar to humans then??
Let’s go back to looking at how humans make decisions. In general terms, we make decisions in the following two ways:
• By using logic and reasoning • By using our experience
Let's say you're trying to pick a car to buy. You could carefully compare things like price, gas mileage, and navigation systems to find the best one for your budget. That's using logic and thinking things through.
Or, you could ask all your friends about their cars—what they like and don't like about them—and make your decision based on their experiences. That's using your friends' experiences to help you choose.
Machine learning is more like the second way. Instead of just using logic, it's like using all the info we've gathered over time. In computer talk, we call this info "data." So, in machine learning, computers make decisions based on data. Whenever we get a computer to solve a problem or make a decision using only data, that's machine learning in action.
So, to sum it up in simple terms: machine learning is like teaching computers to learn from all the information they have, just like we learn from our experiences and the experiences of others.
For this, let’s again analyze the process humans use to make decisions based on experience. This is what is called the remember-formulate-predict framework, The goal of machine learning is to teach computers how to think in the same way, following the same framework. How do humans think? When we, as humans, need to make a decision based on our experience, we normally use the following framework:
1. We remember past situations that were similar.
2. We formulate a general rule.
3. We use this rule to predict what may happen in the future.
Just like humans make decisions based on experience, computers can make decisions based on previous data. This is what machine learning is all about.