Our ability to learn from the past and get better at tasks through experience is what makes us humans. When we are born, we know nothing and can do almost nothing by ourselves. But soon, we’re learning and becoming more capable every day. Machines such as computers follow instructions given by humans. But what if humans can train the machines from past data and do what humans can do, only much faster? Well, that’s what is called Machine Learning. But it’s a lot more than just recalling previous data, it’s also about understanding and reasoning.
Introduction To Machine Learning
Machine Learning brings together information and data with computer science to enable computers to learn how to do a task without being programmed to do so. Just as your brain uses experience to improve a task, so can a computer. Say you need a computer that can tell the difference between a picture of a dog and a picture of a cat. You can begin by feeding it images and telling it which images are those of dogs and which are of cats. A computer programmed to learn with seek statistical patterns within the data, which will enable it to recognize a cat or a dog in the future. It might figure out on its own that cats have shorter noses and dogs come in a variety of sizes, and then represent that information numerically. But the crucial part is that these patterns are identified by the computer, not the programmer. The computer then establishes the algorithms by which future data is sorted out.
Of course, there can be mistakes. But that’s where feedback from humans can help them refine these patterns and algorithms further. The more data the computer receives, the more finely tuned its algorithm becomes, and the more accurate it can be in its predictions.
Machine Learning is divided into three broad categories:
- Supervised Learning
- Unsupervised Learning, &
- Reinforced Learning.
In the earlier examples, showing the computer pictures of cats and dogs is an example of Unsupervised Learning. When we start adding Labels to these pictures (like Cat for one photo and Dog for another photo), it is an example of Supervised Learning. And when we correct mistakes or provide additional algorithms, it is an example of Reinforced Learning.
There are a lot of Applications of Machine Learning out there. To name a few, Machine Learning is used in
- Healthcare, where diagnostics are predicted for doctor’s review
- Sentiment Analysis which tech giants like Facebook and Instagram are using on social media
- Fraud Detection in the financial sector
- E-Commerce Firms using ML to predict customer churn and buying patterns
Another common example in everyday life which you might have encountered while booking cabs is Surge Pricing. Often, when it says “Fare has been updated. Continue Booking?”, that is an interesting Machine Learning Model which is being used by taxi companies like Uber, when they introduce differential pricing in real-time based on
- Number of cars available on the roads
- Bad Weather
- Rush Hour, etc.
They use the Surge Pricing Model to ensure that those who need a cab can get one. Also, it uses Predictive Modeling to predict where the demand will be high with the goal that drivers can take care of the demand, and surge pricing can be minimized.
Now’s time for a small quiz to share if the models given below are using Supervised or Unsupervised Machine Learning.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs.
Scenario 2: Netflix recommends new movies based on someone’s past movie choices.
Scenario 3: Analyzing bank data for suspicious transactions and flagging fraud transactions.
Think wisely and share your answers in the comments below.
So does Machine Learning sound interesting? There are companies like UpGrad which have Courses designed for Machine Learning. Be sure to