A machine learning system is fed with input data—this can be numerical, textual, visual, or audiovisual. The system usually has an output—this can be a floating-point number, for instance, the acceleration of a self-driving car, or it 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 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 the following three categories:

• Unsupervised learning: When the learning data only contains indicative signals without any description attached, it's up to us to find the 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. Data visualization that makes data more digestible, and dimensionality reduction that distills relevant information from noisy data, are also in the family of unsupervised learning.
• Supervised learning: When learning data comes with a description, targets, or desired output besides indicative signals, the learning goal is to find a general rule that maps input to output. This kind of learning data is called labeled data. The learned rule is then used to label new data with unknown output. The labels are usually provided by event-logging systems or evaluated by human experts. Besides, if it's feasible, they may also be produced by human raters, through crowd sourcing, for instance. Supervised learning is commonly used in daily applications, such as face and speech recognition, products or movie recommendations, sales forecasting, and spam email detection.
• Reinforcement learning: Learning data provides feedback so that the system adapts to dynamic conditions in order to achieve a certain goal in the end. The system evaluates its performance based on the feedback responses and reacts accordingly. The best-known instances include robotics for industrial automation, self-driving cars, and the chess master, AlphaGo. The key difference between reinforcement learning and supervised learning is the interaction with the environment.

The following diagram depicts types of machine learning tasks:

Figure 1.4: Types of machine learning tasks

As shown in the diagram, we can further subdivide supervised learning into regression and classification. Regression trains on and predicts continuous-valued responses, for example, predicting house prices, while classification attempts to find the appropriate class label, such as analyzing a positive/negative sentiment and predicting a loan default.

If not all learning samples are labeled, but some are, we will have semi-supervised learning. This makes use of unlabeled data (typically a large amount) for training, besides a small amount of labeled data. Semi-supervised learning is applied in cases where it is expensive to acquire a fully labeled dataset and more practical to label a small subset. For example, it often requires skilled experts to label hyperspectral remote sensing images, while acquiring unlabeled data is relatively easy.

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 this book. For example, in Chapter 2, Building a Movie Recommendation Engine with Naïve Bayes, we will dive into supervised learning classification and its popular algorithms and applications. Similarly, in Chapter 7, Predicting Stock Prices with Regression, we will explore supervised learning regression. We will focus on unsupervised techniques and algorithms in Chapter 9, Mining the 20 Newsgroups Dataset with Text Analysis Techniques. Last but not least, the third machine learning task, reinforcement learning, will be covered in Chapter 14, Making Decisions in Complex Environments with Reinforcement Learning.

Besides categorizing machine learning based on the learning task, we can categorize it in a chronological way.

A brief history of the development of machine learning algorithms

In fact, we have a whole zoo of machine learning algorithms that have experienced varying popularity 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. Statistical learning theory attempts to find a function to formalize the relationships between variables. In the mid-1980s, artificial neural networks (ANNs) came to the fore, only to then be pushed aside by statistical learning systems in the 1990s. ANNs imitate animal brains and consist of interconnected neurons that are also an imitation of biological neurons. They try to model complex relationships between input and output values 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 seeing a revolution in deep learning, which we might consider 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 was the result of the integration and utilization of Graphical Processing Units (GPUs), which massively speed up computation.

GPUs were originally developed to render video games and are very good in parallel matrix and vector algebra. It's believed that deep learning resembles the way humans learn. Therefore, it may be able to deliver on the promise of sentient machines. Of course, in this book, we will dig deep into deep learning in Chapter 12, Categorizing Images of Clothing with Convolutional Neural Networks, and Chapter 13, Making Predictions with Sequences Using Recurrent Neural Networks, after touching on it in Chapter 8, Predicting Stock Prices with Artificial Neural Networks.

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 diagram, you can see that the law holds up nicely (the size of the bubbles corresponds to the average transistor count in GPUs):

Figure 1.5: Transistor counts over the past decades

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 by 2029.