Hello, everyone. You have probably heard of machine learning before, enough to grab your attention and bring you to this class. However, you might be wondering what machine learning is. We will talk about that in this lecture and discuss how we can see machine learning in action in our day-to-day life. After this video you will be able to explain what machine learning is. And list three applications of machine learning encountered in everyday life. Since this course is about machine learning, lets define what that means. We hear this term a lot these days used in many contexts. So it's good to start out with a solid definition of what machine learning means. Machine learning is the field of study that focuses on computer systems that can learn from data. That is the system's often called models can learn to perform a specific task by analyzing lots of examples for a particular problem. For example, a machine learning model can learn to recognize an image of a cat by being shown lots and lots of images of cats. This notion of learning from data means that a machine learning model can learn a specific task without being explicitly programmed. In other words, the machine learning model is not given the step by step instructions on how to recognize the image of a cat. Instead, the model learns what features are important in determining whether it picture contains a cat from the data that has analyzed. Because the model learns to perform this task from data it's good to know that the amount and quality of data available for building the model are important factors in how well the model learns the task. Because machine learning models can learn from data that can be used to discover hidden patterns and trends in the data. These patterns and trends lead to valuable insights into the data. Thus the use of machine learning allows for data driven decisions to be made for a particular problem. So to summarize, the field of machine learning focuses on the study and construction of computer systems that can learn from data without being explicitly programmed. Machine learning algorithms and techniques are used to build models, to discover hidden patterns and trends in the data allowing for data-driven decisions to be made. You may have heard that machine learning is an inter-disciplinary field. This is very true. Machine learning combines concepts and methods from many disciplines, including math, statistics, computer science, artificial intelligence, and optimization. In applying machine learning to a problem, domain knowledge is essential to the success of end results. By domain knowledge we mean an understanding of the application or business domain. Knowledge about the application, the data related to the application, and how the outcomes will be used are crucial to driving the process of building the machine learning model. So domain knowledge is also an integral part of a machine learning solution. Machine learning has been used in many different learning application, many of which you'll probably encounter in your daily life, perhaps without realizing it. One application of machine learning that you likely used this past weekend, or even just today, is credit card fraud detection. Every time you use your credit card, the current purchase is analyzed against your history of credit card transactions to determine if the current purchase is a legitimate transaction or a potentially fraudulent one. If the purchase is very different from your past purchases, such as for a big ticket item in a category that you had never shown an interest in or when the point of sales location is from another country, then it will be flagged as a suspicious activity. In that case, the transaction may be denied. Or you may get a call from your credit card company to confirm that the purchase was indeed made by you. This is a very common use of machine learning that is encountered in everyday life. Another example application of machine learning encountered in daily life is handwritten digit recognition. When you deposit a hand-written check into an ATM, a machine learning process is used to read the numbers written on the check to determine the amount of the deposit. Handwritten digits are trickier to decipher than typed digits due to the many variations in people's handwriting. A machine learning system can sift through the different variations to find similar patterns to distinguish a one from a nine, for example. Recommendations in what sites is another example application of machine learning that most people have experienced first hand. After you buy an item on a website you will often get a list of related items. Often this will be displayed as customers who bought this item also bought these items, or you may also like. These related items have been associated with the item you purchased by a machine learning model, and are now being shown to you since you may also be interested in them. This is a common application of machine learning used often in sales and marketing. Here are some other examples of where machine learning has been used. Like targeted ads on mobile devices. Sentiment analysis of social media data, climate monitoring to detect seasonal patterns, crime pattern detection, and a healthiness analysis of drugs among many other applications. As you can see from this short list, machine learning has been used in various applications including science, medicine, retail, law enforcement, education and many others. Let's take a few minutes to discuss the different terms which refer to this field. The term we are using for this course is machine learning, but you may have heard other terms such as data mining, predictive analytics and data slangs. So what is the difference between these different terms? As we have discussed, machine learning has its roots since statistics, artificial intelligence, and computer science among other fields. Machine learning encompasses the algorithms and techniques used to learn from data. The term data mining became popular around the time that the use databases became common place. So data mining was used to refer to activities related to finding patterns in databases and data warehouses. There are some practical data management aspects to data mining related to accessing data from databases. But the process of finding patterns in data is similar, and can use the same algorithms and techniques as machine learning. Predictive analytics refers to analyzing data in order to predict future outcomes. This term is usually used in the business context to describe activities such as sales forecasting or predicting the purchasing behavior of a customer. But again the techniques used to make these predictions are the same techniques from machine learning. Data science is a new term that is used to describe processing and analyzing data to extract meaning. Again machine learning techniques can also be used here. Because the term data science became popular at the same time that big data began appearing, data science usually refers to extracting meaning from big data and so includes approaches for collecting, storing and managing big data. These terms evolved at different times and may have encompassed different sets of activities. But there have always been more similarities than differences between them. Now they are often used interchangeably and have come to mean essentially the same thing. The process of extracting valuable insight from data, the core algorithms and techniques for doing this do not change with different terms. To summarize, in this lecture we've discussed what machine learning is and how it is being used. Machine learning models learn from data to perform a task without being explicitly programmed. They are used to discover patterns and trends in the data. And a lab for data driven decisions to be made for the problems being studied. We also discuss in this lecture examples of how machine learning is being used. We see how the example applications that machine learning can be applied to many different areas.