Author: AI for Women

Let’s face it – EVERYONE wants to know about Machine Learning. Considering the immense job-creating, life-revolutionising potential that it has, it is no surprise that it is in such high demand now. There are so many articles, videos, and books everywhere! The amount of online content is truly spectacular, but for a beginner, it can be quite intimidating. It’s almost like being given a plethora of cuisines, and then being instructed to review them all. Where would you start? How would you consume all of it? How much of each would you need to have until you can come up with an accurate review? For this reason, this article aims to consolidate some of the Machine Learning fundamentals into one easy-to-understand article. Thus, those of you who are just getting started can easily learn the basics without being overwhelmed by the technical details. That said, we will now get into the “What”, “Why”, “When”, “Where”, and “How” of Machine Learning.  Let’s begin! WHAT is Machine Learning? Machine Learning is the process by which a machine learns how to think like a human being in order to perform a specific task, without being explicitly programmed. WHY do we use Machine Learning? By training a machine to think like a human being, the execution of certain tasks becomes easier, quicker, and much more efficient. WHEN do we use Machine Learning? Machine Learning was invented by some very ambitious people who desired to develop an intelligence that could resemble, if not surpass, natural human intelligence. The term ‘Machine Learning’ was coined by Arthur Samuel in the 1950s. This was a time when Alan Turing proposed the ‘Learning Machine’, and Marvin Minsky and Dean Edmonds built the first Neural Network machine. Within that same decade, Arthur Samuel invented a Checkers playing machine, and Frank Rosenblatt developed the very first Perceptron. From there, Machine Learning steadily began to grow. WHERE do we use Machine Learning? Machine Learning has come so far, from playing games to recommending products to customers. The more the technology advanced, the better its applicability became. Listed below are five important applications of Machine Learning that are commonly used, easy to remember, and good to know – Spam Filter: Spam emails can automatically be detected within your inbox and stored in your Spam folder. That way, it doesn’t interfere with your more important emails. It also reduces the amount of time and effort you would have to spend sorting out your inbox. Recommendation Systems: Most online stores use Machine Learning to recommend items based on the user’s recent activity and requirements. This prevents customers from getting irrelevant suggestions, and increases the chances of them making a purchase. Virtual Assistants: They assist users in their daily requirements like setting alarms, making lists, and so on. They then store data from previous tasks, and tailor their performance based on these preferences. Search Engines: Search Engines use Machine Learning Algorithms to find and display results that are most accurate to a user’s search. They even filter them out based on the user’s past activity. GPS: Travelling has become so much easier thanks to GPS apps. These systems use Machine Learning to make travelling less difficult. They can show people their current location, the distance between two places, the estimated time it would take to reach another location, and the amount of traffic that could either increase or decrease their time of arrival. HOW does Machine Learning Work? Now that we know some of the important facts of Machine Learning, we shall proceed to the more interesting part – Understanding how Machine Learning works. The first thing to know is that Machine Learning is mainly of two types: Supervised Learning: It involves the use of labelled data (where the number of classes are known). Unsupervised Learning: It involves the use of unlabelled data (where the number of classes are unknown). Let’s have a look at five differences between Supervised Learning and Unsupervised Learning. Supervised Learning: It is a method of Machine Learning that deals with labelled input data. It is used for Regression (predicting continuous variables) and Classification (predicting categorical variables). It is more time consuming and accurate. Some applications of include stock price prediction, object detection, spam detection, and sentiment analysis. Unsupervised Learning:  It is a method of Machine Learning that deals with unlabelled input data. It is used for Clustering (finding patterns in the data) and Association (identifying relationships between elements in the dataset). It is less time consuming and accurate. Some applications include credit card fraud detection and customer behavior analysis.   There is also a third type of Machine Learning method, known as Reinforcement Learning.  Reinforcement Learning: It is a method of Machine Learning that aims to make the most optimal decision in order to maximize the reward.  It uses algorithms that learn from previous outcomes and then decide what action to take next. Thus, decisions are made sequentially, i.e., the next input is based on the previous output, unlike supervised and unsupervised learning, in which decisions are made only based on the initial input data. There are two types of reinforcement learning – Positive Reinforcement (adding a positive stimulus or reward after some behavior to increase the likelihood of its recurrence) and Negative Reinforcement (removing a negative stimulus after some behavior to increase the likelihood of its recurrence).  For example, positive reinforcement would be giving a dog their favorite toy as a reward for behaving, whereas negative reinforcement would be taking the dog’s favorite toy away when it misbehaves.  Some applications include text prediction and gaming.   Now that we are familiar with the types of Machine Learning, let’s briefly go through some of the different algorithms used in Machine Learning.    Types of Supervised Machine Learning Algorithms:   Linear Regression Support Vector Machines (SVM) Neural Networks Decision Trees Naive Bayes Nearest Neighbour Types of Unsupervised Machine Learning Algorithms:   k-means clustering Association rule Principal component analysis Types of Reinforcement Learning    Q-Learning Deep Adversarial Networks   Last but not