Machine learning is a term coined around 1960 composed of two words—machine corresponding to a computer, robot, or other device, and learning an activity, or event patterns, which humans are good at.

So why do we need machine learning, why do we want a machine to learn as a human? There are many problems involving huge datasets, or complex calculations for instance, where it makes sense to let computers do all the work. In general, of course, computers and robots don't get tired, don't have to sleep, and may be cheaper. There is also an emerging school of thought called active learning or human-in-the-loop, which advocates combining the efforts of machine learners and humans. The idea is that there are routine boring tasks more suitable for computers, and creative tasks more suitable for humans. According to this philosophy, machines are able to learn, by following rules (or algorithms) designed by humans and to do repetitive and logic tasks desired by a human.

Machine learning does not involve the traditional type of programming that uses business rules. A popular myth says that the majority of the code in the world has to do with simple rules possibly programmed in Cobol, which covers the bulk of all the possible scenarios of client interactions. So why can't we just hire many software programmers and continue programming new rules?

One reason is that defining, maintaining, and updating rules becomes more and more expensive over time. The number of possible patterns for an activity or event could be enormous and therefore exhausting all enumeration is not practically feasible. It gets even more challenging to do so when it comes to events that are dynamic, ever-changing, or evolve in real-time. It is much easier and more efficient to develop learning rules or algorithms which command computers to learn and extract patterns, and to figure things out themselves from abundant data.

Another reason is that the volume of data is exponentially growing. Nowadays, the floods of textual, audio, image, and video data are hard to fathom. The Internet of Things (IoT) is a recent development of a new kind of Internet, which interconnects everyday devices. The Internet of Things will bring data from household appliances and autonomous cars to the forefront. The average company these days has mostly human clients, but, for instance, social media companies tend to have many bot accounts. This trend is likely to continue and we will have more machines talking to each other. Besides the quantity, the quality of data available has kept increasing over the past few years due to cheaper storage. These have empowered the evolution of machine learning algorithms and data-driven solutions.

Jack Ma from Alibaba explained in a speech that Information Technology (IT) was the focus over the past 20 years and now, for the next 30 years, we will be at the age of Data Technology (DT). During the age of IT, companies have grown larger and stronger thanks to computer software and infrastructure. Now that businesses in most industries have already gathered enormous amounts of data, it is presently the right time for exploiting DT to unlock insights, derive patterns, and to boost new business growth. Broadly speaking, machine learning technologies enable businesses to better understand customer behavior and engage with customers, also to optimize operations management. As for us individuals, machine learning technologies are already making our life better every day.

An application of machine learning that we all are familiar with is spam email filtering. Another is online advertising where ads are served automatically based on information advertisers have collected about us. Stay tuned for the next chapters where we will learn how to develop algorithms in solving these two problems. An application of machine learning we basically can not live without is search engines. Search engines involve information retrieval which parses what we look for and queries related records, and contextual ranking and personalized ranking which sorts pages by topical relevance and to the user's liking. E-commerce and media companies have been at the forefront of employing recommendation systems, which help customers find products, services, articles faster. The application of machine learning is boundless and we just keep hearing new examples everyday, credit card fraud detection, disease diagnosis, presidential election prediction, instant speech translation, robo-advisor, you name it!

In the 1983 War Games movie, a computer made life and death decisions, which could have resulted in Word War III. As far as we know, technology wasn't able to pull off such feats at the time. However, in 1997 the Deep Blue supercomputer did manage to beat a world chess champion. In 2005, a Stanford self-driving car drove by itself for more than 130 kilometers in a desert. In 2007, the car of another team drove through regular traffic for more than 50 kilometers. In 2011, the Watson computer won a quiz against human opponents. In 2016, the AlphaGo program beat one of the best Go players in the world. If we assume that computer hardware is the limiting factor, then we can try to extrapolate into the future. Ray Kurzweil did just that and according to him, we can expect human level intelligence around 2029. What's next?

Machine learning mimicking human intelligence is a subfield of artificial intelligence—a field of computer science concerned with creating systems. Software engineering is another field in computer science. Generally, we can label Python programming as a type of software engineering. Machine learning is also closely related to linear algebra, probability theory, statistics, and mathematical optimization. We usually build machine learning models based on statistics, probability theory, and linear algebra, then optimize the models using mathematical optimization. The majority of us reading this book should have at least sufficient knowledge of Python programming. Those who are not feeling confident about mathematical knowledge, might be wondering, how much time should be spent learning or brushing up the knowledge of the aforementioned subjects. Don't panic. We will get machine learning to work for us without going into any mathematical details in this book. It just requires some basic, 101 knowledge of probability theory and linear algebra, which helps us understand the mechanics of machine learning techniques and algorithms. And it gets easier as we will be building models both from scratch and with popular packages in Python, a language we like and are familiar with.

A machine learning system is fed with input data—this can be numerical, textual, visual, or audiovisual. The system usually has outputs—this can be a floating-point number, for instance, the acceleration of a self-driving car, can be an integer representing a category (also called a class), for example, a cat or tiger from image recognition.

The main task of machine learning is to explore and construct algorithms that can learn from historical data and make predictions on new input data. For a data-driven solution, we need to define (or have it defined for us by an algorithm) an evaluation function called loss or cost function, which measures how well the models are learning. In this setup, we create an optimization problem with the goal of learning in the most efficient and effective way.

Depending on the nature of the learning data, machine learning tasks can be broadly classified into three categories as follows:

• Unsupervised learning: when learning data contains only indicative signals without any description attached, it is up to us to find structure of the data underneath, to discover hidden information, or to determine how to describe the data. This kind of learning data is called unlabeled data. Unsupervised learning can be used to detect anomalies, such as fraud or defective equipment, or to group customers with similar online behaviors for a marketing campaign.
• Supervised learning: when learning data comes with description, targets or desired outputs besides indicative signals, the learning goal becomes to find a general rule that maps inputs to outputs. This kind of learning data is called labeled data. The learned rule is then used to label new data with unknown outputs. The labels are usually provided by event logging systems and human experts. Besides, if it is feasible, they may also be produced by members of the public through crowdsourcing for instance. Supervised learning is commonly used in daily applications, such as face and speech recognition, products or movie recommendations, and sales forecasting.
• We can further subdivide supervised learning into regression and classification. Regression trains on and predicts a continuous-valued response, for example predicting house prices, while classification attempts to find the appropriate class label, such as analyzing positive/negative sentiment and prediction loan defaults.
• If not all learning samples are labeled, but some are, we will have semi-supervised learning. It makes use of unlabeled data (typically a large amount) for training, besides a small amount of labeled. Semi-supervised learning is applied in cases where it is expensive to acquire a fully labeled dataset while more practical to label a small subset. For example, it often requires skilled experts to label hyperspectral remote sensing images, and lots of field experiments to locate oil at a particular location, while acquiring unlabeled data is relatively easy.
• Reinforcement learning: learning data provides feedback so that the system adapts to dynamic conditions in order to achieve a certain goal. The system evaluates its performance based on the feedback responses and reacts accordingly. The best known instances include self-driving cars and chess master AlphaGo.

Feeling a little bit confused by the abstract concepts? Don't worry. We will encounter many concrete examples of these types of machine learning tasks later in the book. In Chapter 3, Spam Email Detection with Naive Bayes, to Chapter 6, Click-Through Prediction with Logistic Regression, we will see some supervised learning tasks and several classification algorithms; in Chapter 7, Stock Price Prediction with Regression Algorithms, we will continue with another supervised learning task, regression, and assorted regression algorithms; while in Chapter 2, Exploring the 20 Newsgroups Dataset with Text Analysis Algorithms, we will be given an unsupervised task and explore various unsupervised techniques and algorithms.

In fact, we have a whole zoo of machine learning algorithms with popularity varying over time. We can roughly categorize them into four main approaches: logic-based learning, statistical learning, artificial neural networks, and genetic algorithms.

The logic-based systems were the first to be dominant. They used basic rules specified by human experts, and with these rules, systems tried to reason using formal logic, background knowledge, and hypotheses. In the mid-1980s, artificial neural networks (ANN) came to the foreground, to be then pushed aside by statistical learning systems in the 1990s. Artificial neural networks imitate animal brains, and consist of interconnected neurons that are also an imitation of biological neurons. They try to model complex relationships between inputs and outputs and to capture patterns in data. Genetic algorithms (GA) were popular in the 1990s. They mimic the biological process of evolution and try to find the optimal solutions using methods such as mutation and crossover.

We are currently (2017) seeing a revolution in deep learning, which we may consider to be a rebranding of neural networks. The term deep learning was coined around 2006, and refers to deep neural networks with many layers. The breakthrough in deep learning is amongst others caused by the integration and utilization of graphical processing units (GPU), which massively speed up computation. GPUs were originally developed to render video games, and are very good in parallel matrix and vector algebra. It is believed that deep learning resembles the way humans learn, therefore may be able to deliver on the promise of sentient machines.

Some of us may have heard of Moore's law-an empirical observation claiming that computer hardware improves exponentially with time. The law was first formulated by Gordon Moore, the co-founder of Intel, in 1965. According to the law, the number of transistors on a chip should double every two years. In the following graph, you can see that the law holds up nicely (the size of the bubbles corresponds to the average transistor count in GPUs):

The consensus seems to be that Moore's law should continue to be valid for a couple of decades. This gives some credibility to Ray Kurzweil's predictions of achieving true machine intelligence in 2029.