Machine Learning: What actually is it?

Introduction: What is Machine Learning?

Before giving you a technical definition of what machine learning is let us look at an example. We all know that humans learn from their past experiences and as for machines, they follow instructions given by us.

Take online shopping for an example. An estimated 1.8 billion people worldwide purchase online goods. So imagine this, you shopped for a product online a few days back and then you keep on receiving emails for shopping suggestions. If not this, then you might have noticed that the shopping website or the app recommends you some items that somehow matches with your taste. Certainly, this refines the shopping experience. But, have you ever thought how this magic is happening. This is no coincidence, it is the AI using the customer’s data, machine learning and other computational concepts to predict a customer’s wants.

Artificial Intelligence uses Machine Learning to learn a task from experience without programming them specifically about that task. To put this simpler, machine learning is when a machine learns automatically from given data without any or limited human assistance.

How does Machine Learning Work?

Data, data is the keyword here. The process of machine learning starts off with feeding them good quality data and then training the machines by building various machine learning models using the data and different algorithms. The choice of algorithms depends on what type of data do we have and what kind of task we are trying to automate. It is complicated at the start, let’s look at it step by step. However, before starting to learn about Machine Learning always remember this, More Data> Better Model> Higher accuracy.

Two types of techniques are mainly used in the process of Machine Learning: supervised learning, which trains a model on known input and output data so that it can predict future outputs, and unsupervised learning, which finds hidden patterns or intrinsic structures in input data. We will look deeply into both.

Supervised Learning

To understand supervised learning, imagine this, you have a billionaire friend probably Elon Musk. He gives you one million coins of three different currencies. A Rupee, Euro, and Dhiram. All three types of coins weigh differently. Rupee weighs three-grams, Euro weighs seven-grams, and as for Dhiram four-grams. So now, the weight of the coins becomes the feature, and the currency becomes the label. Now, let us give a new coin to the machine which weighs three-grams. The model will predict that it is a Rupee.

Supervised learning uses labelled data to train the model. In this scenario, the machine knew the features of the object and also the labels associated with it. Supervised learning, builds a model that makes predictions based on evidence in the presence of uncertainty. A supervised learning algorithm takes a known set of input data and known responses to the data (output) and trains a model to generate reasonable predictions for the response to new data. We can use supervised learning if we have known data for the output we are trying to predict.

Unsupervised Learning

Unsupervised learning is no different from supervised. However, unlike supervised learning above there are no correct answers and there is no teacher. Algorithms are left to their own devices to discover and present the interesting structure in the data. It is used to draw inferences from datasets consisting of input data without labelled responses.

A technique commonly used in unsupervised learning is known as clustering. It is used for exploratory data analysis to find hidden patterns or groupings in data.

Why not look at another example to understand it better? Let’s, take the case of a baby and her family dog.

The baby recognises and identifies the dog. Another dog comes along a few weeks later and tries to play with the baby. Baby has not seen this dog earlier. But it recognizes many features (2 ears, eyes, walking on 4 legs) are like her pet dog. She identifies the new animal as a dog. This is unsupervised learning, where you are not taught but you learn from the data (in this case data about a dog.) Had this been supervised learning, the family friend would have told the baby that it’s a dog.

Unsupervised learning allows the model to work on its own to discover new information. I hope you have a better understanding of the two techniques.

Uses Of Machine Learning

Without machine learning, AI is probably nothing. It has numerous uses. Self-driving cars, I am sure you have heard of the concept. Actually, it is not a concept anymore, it is reality. Thanks to Tesla. So how does self-driving machine learning?

Machine Learning is a crucial component of the centralized electronic control unit (ECU) in an autonomous car. You see, an autonomous car uses numerous sensors that help them make sense of their surroundings, including GPS, radar, lidar, sonar, odometry, and inertial measurement units. Furthermore, there many more complex control systems that can interpret sensory information to identify obstacles and figure out suitable navigation paths.

Still no use of machine learning you might be thinking. Well, all the data collected by these components is received by the computer, the machine learning application. It then uses this information to predict accordingly.

Another major use of machine learning is energy. Massive organizations such as BP use technology to enhance their performance, improve the use of resources and safety and reliability of oil and gas production and refining. The organization uses big data, machine learning and Internet of Things (IoT) technology to build an “internet of energy.” Advanced analytics and machine learning enable predictive maintenance and power, operations and business optimization to help GE Power work toward its vision of a “digital power plant.”

Conclusion

In conclusion, Machine learning is everywhere. It is certainly a difficult concept to wrap your head around. But when you learn it, AI will seem like something so common and easy to understand. Consider using machine learning when you have a complex task or problem involving a large amount of data and lots of variables, but no existing formula or equation. Machine Learning has countless benefits, it can be used to diagnose diseases by looking at previous data.

COVID-19, most certainly humanities greatest threat at this moment. With no cure, the virus is still rampaging. However, with the use of machine learning it can:

• Identify who is most at risk,
• Diagnose patients,
• Develop drugs faster,
• Predict the spread of the disease,
• Understand viruses better,
• Map where viruses come from, and
• Predict the next pandemic.

I will talk more about how machine learning can help solve the pandemic in my next blog. Machine learning will truly revolutionize how we live.