Hey there!
If you clicked in this story, its because you want to learn or expand your knowledge about Machine Learning(M.L), maybe because you’re a curious person, you have a relative working on this area or just stumbbled upon this story. M.L is a data learning method that is changing the way we think about the boundaries of technology. It surely creates some fuzz, its everywhere, radio, newspapers, internet!
Independet of your age and area of expertise, after reading this story you’ll understand the big picture of this topic, what’s machine learning? will robots take our jobs? are we really safe? stick with me and read carefully.
Artificial Intelligence
Early AI research in the 1950s explored topics like problem solving and symbolic methods. In the 1960s, the US Department of Defense took interest in this type of work and began training computers to mimic basic human reasoning. For example, the Defense Advanced Research Projects Agency (DARPA) completed street mapping projects in the 1970s.
Here’s a formal definition of A.I by SAAS:
Artificial intelligence (A.I) makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. Computers can be trained to accomplish specific tasks by processing large amounts of data and recognizing patterns in the data.
Yes, you just read it. Computers can be trained to have a simplier version of human-like intelligence.
Here are some A.I applications, we’ll focus in Machine Learning.
Applications of Artificial Intelligence
Machine Learning
Because of new computing technologies, machine learning was born from pattern recognition, and the theory that computers can learn without being programmed to perform specific tasks. They learn from previous computations to produce reliable, repeatable decisions and results.
Here’s a formal definition of M.L by SAAS:
“ Machine learning (M.L) is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.”
In a summary, machine learning is a method used by computers to learn from data and calculations by using mathematical algortihms (a fancy word for mathematical operations). As we stated before, machine learning is everywhere, some examples of their applications are:
- Online recommendation offers such as those from Amazon and Netflix? Machine learning applications for everyday life.
- Knowing what customers are saying about you on Twitter? Machine learning combined with linguistic rule creation.
- Fraud detection? One of the more obvious, important uses in our world today.
Think of a little kid, he starts by knowing nothing of the world that surrounds him, there’s no concept of maths, religion or politics, is like a blank page.
Thanks to instructions tought by their parents and teachers, kids learn how their surroundings work and their place in society, same happens with machines in a much simplier way. They can be trained to learn.
Why is it important?
As a specie, humans have certain limitations that were routed by the use of tools, fire cooks meat, stone chops trees and computers process data, things like growing volumes and varieties of available data, computational processing that is cheaper and more powerful, and affordable data storage.
All of these things mean it’s possible to quickly and automatically produce models that can analyze bigger, more complex data and deliver faster, more accurate results. Let the hard work for machines!
Are we safe?
There’s no reason to worry, humanity has been struggling for thousands of years to fully understand the human brain and emotions, and yet, we are far from a definitive answer.
There are almost 0% possibilities that a machine will become sentient and destroy humanity.
Machine Learning is yet but another tool for humanity, like a hammer or a candle. Big companies and even the goverment lay their trust on machines, our creations are ment to help, no to harm.
Machine Learning methods
So long we went from what is Artifial Intelligence to Machine Learning, here is a short summary:
Artifial Intelligence (A.I) — makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks.
Machine Learning (M.L) — is a method used by computers to learn from data and calculations by using mathematical algortihms.
After this short reminder, I’ll ask you the following, when you were at school, university or even at your job, did you have a method for learning?
Some people prefer reading books, others prefer having a teacher, others just love to try, fail and learn. Everyone has their unique way to learn, that’s other thing that differenciates us from machines.
Machines have fixed methods to learn, for easy understanding of this topics, we’ll use a the following case.
A machine learns to bake a cake.
Supervised learning:
Machines are trained using labeled examples, such as an input where the desired output is known. For example, a piece of equipment could have data points labeled either “F” (failed) or “R” (runs). The learning algorithm receives a set of inputs along with the corresponding correct outputs, and the algorithm learns by comparing its actual output with correct outputs to find errors. It then modifies the model accordingly.
The machines knows the result is a cake and the ingedients are given to it.
By knowing the recipe to bake a cake, the machine does this process to find errors in the recipe and fix them for a better version of the recipe.
Unsupervised learning:
Is used against data that has no historical labels. The system is not told the “right answer” The machine must figure out what is being shown. The goal is to explore the data and find some structure within.
The machine knows the result is a cake but no ingedients are given to it.
By using clustering and sorting techniques the machine learns which ingredients does it need and the recipe to bake the cake.
Semisupervised learning:
Is used for the same applications as supervised learning. But it uses both labeled and unlabeled data for training — typically a small amount of labeled data with a large amount of unlabeled data (because unlabeled data is less expensive and takes less effort to acquire).
The machine knows the result is a cake but not all the ingredients are given to it.
By using clustering, sorting techniques and a given recipe, the machine learns which ingredients does it need, while finding errors in the recipe and fixing them for a better version of the recipe.
Reinforcement learning:
is often used for robotics, gaming and navigation. With reinforcement learning, the algorithm discovers through trial and error which actions yield the greatest rewards.
The machines knows the result is a cake and the ingedients are given to it.
By trying, failing and learning from those failures, the machine is able to learn how a cake is baked, and the recipe for baking a cake.
