What is Machine Learning and why is it important

Gilbert Tanner
Sep 4, 2018 · 4 min read
Figure 1: “flat lay photography of MacBook Pro, coffee cup and phone” by rawpixel on Unsplash

Machine Learning and Artificial Intelligence, in general, have been around since the middle of the twentieth century but only got popular in the last few years. Why is that so and why does Machine Learning matter and what is it in the first place. That are the things I will answer in this post.


What is Machine Learning

Machine Learning is a field of computer science which gives the computer the ability to learn without being explicitly programmed. Machine Learnings main focus is to provide algorithms which can be trained to perform a task.

It is closely related to the field of computational statistics as well as mathematical optimization. It contains multiple methods like Supervised Learning, Unsupervised Learning, Semi-supervised Learning, and Reinforcement Learning which each has there own use cases and algorithms.

Supervised Learning maps an input to an output based on example input-output pairs also known as labeled data. Supervised Learning has two subclasses:

  • Classification
  • Regression

A task is considered a classification task if the output is categorical and a regression task if the output is a continuous value.

Figure 2: Linear Regression best fit line from Wikipedia

Unsupervised Learning deals with unlabeled data (data that doesn’t have a label). Unsupervised Learning is mostly used for finding relationships in datasets, reducing dimensionality or identifying anomalies.

Figure 3: DBSCAN Clustering from Wikipedia

Semi-supervised learning is a mixture of supervised and unsupervised learning. It typically works with a small amount of labeled data and a large amount of unlabeled data. This addition of a little bit of labeled data to an unlabeled dataset has been shown to sometimes improve results significantly.

Figure 4: Semi-supervised learning from Wikipedia

Reinforcement Learning deals with how an agent takes actions in an environment to maximize a reward. Reinforcement Learning saw huge successes in the last few years especially in the context of game theory with an example being the Dota Bot from OpenAI.

Figure 5: Reinforcement Learning from Wikipedia

Why did Machine Learning start growing in the last few years

Machine Learning has started growing at an accelerating rate because nowadays we have cheap computational power as well as lots of data which we can use the train our models.


Why is Machine Learning important?

Recent years have shown that Machine Learning can be used to automate a lot of different tasks that were thought of as tasks that only humans can to like Image Recognition, Text Generation or playing games.

In 2014 Machine Learning and AI experts thought it would take at least 10 years before a machine could beat the world’s best player at the board game Go. But Googles DeepMind proved them wrong. They showed that even in such a complex game as Go machines could learn which moves to consider. There are a lot more of advances in the field of machines playing games like the Dota Bot from the OpenAI Team.

Machine Learning is going to have huge effects on the economy and living in general. Entire work tasks and industries can be automated and the job market will be changed forever.

If you want to start learning about Machine Learning it’s the perfect time because Machine Learning Engineers are desperately needed because a lot of companies want to get their foot in the door of Machine Learning and Artificial Intelligence.

Now that Machine Learning has all the attention it needs it’s on us the Engineers and Researchers to drive for new big advances in the field of Machine Learning.



Conclusion

This was a short article about Machine Learning and why it is important.

If you liked this article consider subscribing on my Youtube Channel and following me on social media.

If you have any questions feel free to dm me on Twitter or leave a comment on one of my Youtube Videos.

Data Driven Investor

from confusion to clarity, not insanity

Gilbert Tanner

Written by

AI Enthusiast | Educator | Website: https://gilberttanner.com/ | Youtube: https://www.youtube.com/c/GilbertTanner | Support me: buymeacoff.ee/gilberttanner

Data Driven Investor

from confusion to clarity, not insanity

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade