Machine learning is the most exciting technology. We all use a learning algorithm many times a day without knowing about it. Every time we use a web search engine like Google or Bing to search anything, one of the reasons that it works so well is that because a learning algorithm, one implemented by Google or Microsoft, has learned how to rank web pages. Every time we use Facebook or Apple’s photo typing application and it recognizes our friends’ photos, that’s also machine learning. Every time we read our email and the spam filter saves us from having to wade through tons of spam email, that’s also a learning algorithm. one of the goals is to someday build machines as intelligent human beings. We’re a long way away from that goal, but many AI researchers believe that the best towards that goal is through learning algorithms that try to copy how the human brain learns. Machine learning is so prevalent today because it is a field that had grown out of the field of AI or artificial intelligence.
We wanted to build intelligent machines and it turns out that there are some of the basic things that we can program some machine to do such as how to find the shortest path between any two points. But for most of the part, we did not know how to write programs(of AI) to do the more interesting things such as browse the web or photo tagging or email anti-spam. There was a very important realization that the only way to do these things was to have a machine learn to do it by itself. So, machine learning was developed as a new capability for computers and today it touches many segments of industry and basic science. There is autonomous robotics, computational biology, tons of things that machine learning is having an impact on. Here are some other examples of machine learning. There’s data mining. One of the reasons machine learning has so spread is the growth of the web and the growth of automation. All this means that we have much larger data sets than ever before. So, for example, tons of companies are today collecting web click data, also called clickstream data, and are trying to use machine learning algorithms to mine this data to understand the users better and to serve the users better, that’s a huge segment of It sector right now. Medical records. With the advent of automation, we now have electronic medical records, so if we can turn medical records into medical knowledge, then we can start to understand the disease better. Computational biology. With automation again, biologists are collecting lots of data about gene sequences, DNA sequences, and many more, and machines running algorithms are giving us a much better understanding of the human genome, and what it means to be human. And in engineering also, in all fields of it, we have larger and larger data sets, that we’re trying to understand using learning algorithms.
A second range of machinery applications is ones that we cannot program by hand. So for example, suppose someone worked on autonomous helicopters for many years and he just did not know how to write a computer program to make that helicopter fly by itself. The only thing that worked was having a computer learn by itself how to fly this helicopter. Handwriting recognition : turns out one of the reasons it’s so inexpensive today to route a piece of mail across the countries is that when you write an envelope, there is a learning algorithm that has learned how to read your handwriting so that it can automatically route this envelope on the way, and so it costs us a few cents to send the message thousands of miles. And in fact, if you’ve seen the fields of natural language processing(NLP) or computer vision, these are the fields of AI related to understanding language or understanding images. Most of NLP and most of the computer vision today is Applied Machine Learning. Learning algorithms are also globally used for self-customizing programs. Every time you go to website or apps like Amazon or Netflix or iTunes, it recommends the movies or products and music to you, that is also a learning algorithm (recommender system). If you think about it they have a billion users, there is no way to write a billion different programs for your billion users. The only way is to have a software which give these customized recommendations which further learn by itself to customize itself according to your preferences. Learning algorithms are being used today to understand human learning and to understand the human brain. Many researches are using this to make progress towards the big AI dream. Machine learning is the top most much needed skill in the IT sector today. In the next topic, we’ll start to give a more formal definition of what is machine learning. And we’ll begin to talk about the main types of machine learning problems and algorithms. You’ll pick up some of the main machine learning terminology, and begin to get what are the different algorithms, and among them when each one will be appropriate.