Let’s start with what is machine learning? The name itself might feel intimidating, but understanding machine learning is genuinely as easy as understanding human’s way of living. As one would say, “learn from your mistake,” it also applies to machine learning. Machine learning mimics human behavior, where it learns from data, patterns, and past errors to make the best decision with minimal human intervention. It is a branch of ArtificIal Intelligence based on the idea that it can learn from previous computations to produce reliable, repeatable decisions and results.
Around 50 years ago, machine learning was still considered the “utopia,” a science fiction fantasy. Shown below is the timeline of Machine Learning history with its prominent milestones.
The development of machine learning has grown exponentially since. There are three different types of Machine Learning;
1. Supervised learning is where you have input variables (x) and an output variable (Y) and you use an algorithm to learn the mapping function from the input to the output.
Y = f(X)
We can see this process as if a teacher is supervising students in the learning process. The teacher knows the correct answer to a question, and the algorithm (students) iteratively makes predictions on the training data and is corrected by the teacher until it achieves an acceptable level of performance.
2. Unsupervised learning, on the other hand, only has input data without any outcome variable to predict or set. There is no teacher nor a correct answer to the question. This method is used for collecting data from different groups and segmenting it to different groups based on its similarity and pattern. In this algorithm, we do not have any target or outcome variable to predict / estimate. It is used to cluster the population in different groups, which is widely used for segmenting customers in various groups for specific intervention.
3. Deep Learning, by using the algorithm, the machine is trained to make a specific decision by continually training itself using trial and error. It learns from past experiences and tries to come up with the best possible way to make the most accurate decision.
Today, machine learning algorithms enable computers to assist humans in many ways, such as self-driving car, personalized online recommendations, linguistic recognition, and fraud detection. Click here to see how machine learning is being applied to today’s trend.