Welcome to Introduction to Machine Learning for Everyone. After watching this video, you will be able to: Define the term machine learning. Explain how machine learning works. Describe use-cases of machine learning. Differentiate between AI, machine, and deep learning. And finally, list the different categories and branches of machine learning. Machine learning is the subfield of computer science that gives "computers the ability to learn without being explicitly programmed.” Arthur Samuel, American pioneer in the field of computer gaming and artificial intelligence, coined the term "machine learning" in 1959 while at IBM. Let’s explore what “without being explicitly programmed” means. Assume that you have a data set of animal images such as cats and dogs, and you want to create a program that can recognize which images are cats and which images are dogs. You first interpret the images as a set of features. For example, does the image show the animal’s eyes, and if so, what is the size? Does it have ears or a tail? How many legs? Prior to machine learning, each image would be transformed into an ordered collection of features and then you define some rules or methods to teach the computers how to detect the animals. This approach failed. The rules were numerous, highly dependent on the current data set, and not generalized enough to detect out-of-sample cases. This is when machine learning entered the scene. Machine learning lets you build a model that looks at all the feature sets and their corresponding types of animals to learn the patterns of each animal. So, machine learning algorithms, inspired by the human learning process, iteratively learn from data and allow computers to find hidden insights. These models are helpful in a variety of tasks, such as object recognition, summarization, recommendation, and so on. This is a human cell sample extracted from a patient. The cell has many characteristics, for example, its clump thickness is 6, its uniformity of cell size is 1, its marginal adhesion is 1, and so on. An interesting question you can ask at this point is, “Is this a benign or malignant cell?” Unlike the cells of a benign tumor, a malignant tumor may invade its surrounding tissue or spread around the body and diagnosing it early might be the key to a patient’s survival. You might think that only a doctor with years of experience could diagnose that tumor and say if the patient is developing cancer or not. Right? Imagine you have obtained a data set containing characteristics of thousands of human cell samples extracted from patients believed to be at risk of developing cancer. Analysis of the original data showed that many of the characteristics differed significantly between benign and malignant samples. You can use the values of these cell characteristics in samples from other patients to give an early indication of whether a new sample might be benign or malignant. You should clean your data, select a proper algorithm for building a prediction model, and train your model to understand patterns of benign or malignant cells within the data. Once the model has been trained by iteratively going through data, it can be used to predict a new or unknown cell with rather high accuracy. This is machine learning! Accordingly, a machine learning model can perform a doctor’s task or at least help make the process faster. Machine learning impacts society in a very influential way. Here are some real-life examples. Netflix and Amazon recommend videos, movies, and TV shows to their users, based on their knowledge of the types of shows they like to watch, banks decide when to approve a loan application by using machine learning to predict the probability of default for each applicant and then approve or deny the loan application based on that probability. Telecommunication companies use their customers’ demographic data to segment them or predict if they will unsubscribe from their company in the next month. There are many other applications of machine learning in our daily life, such as chatbots and computer games using face recognition. Each of these uses different machine learning techniques and algorithms. By this point, you are probably wondering, “What is the difference between current buzzwords such as artificial intelligence (or AI), machine learning, and deep learning?” Well, let’s look at the differences: Briefly, AI tries to make computers intelligent enough to mimic humans’ cognitive functions. So, AI is a general field with a broad scope, including computer vision, language processing, creativity, and summarization. Machine learning (or ML) is the branch of AI that covers the statistical part of artificial intelligence. It teaches the computer to solve problems by looking at hundreds or thousands of examples, learning from them, and then using that experience to solve the same problem in new situations. And deep learning is an exceptional field of machine learning where computers can learn and make intelligent decisions independently. Deep learning involves a deeper level of automation in comparison to most machine learning algorithms. The two categories for machine learning are supervised and unsupervised learning. Supervised learning uses labeled data to train your model. It can be split into two subcategories. Regression techniques are used for predicting a continuous value. For example, predicting the price of a house based on its characteristics or estimating the CO2 emission from a car’s engine. And classification techniques are used for predicting the class or category of a case. For example, if a cell is benign or malignant, or whether a customer will churn. Unsupervised learning uses unlabeled data and algorithms to detect patterns in the data. An example of unsupervised learning is clustering. Clustering algorithms are used to group similar cases, for example, they can be used to find similar patients or to segment bank customers. Branches of the machine learning field include the following: Deep learning deals with algorithms inspired by the human brain and how humans learn. Natural language processing encompasses how a machine understands written or spoken human language. Computer vision deals with how computers see and understand digital images. And reinforcement learning includes teaching a machine to make decisions by rewarding desired actions and punishing undesired actions. In this video, you learned that: Machine learning techniques teach computers to perform tasks without explicitly being programmed to do so. Machine learning can be used in industries such as banking and telecommunications and for generating Netflix and Amazon recommendations. The two machine learning categories are supervised and unsupervised learning. And finally, the branches of machine learning are deep learning, natural language processing, computer vision, and reinforcement learning.