Artificial Intelligence 101

Artificial Intelligence

Artificial Intelligence (AI) is not a new concept. Over the last couple of decades, it has experienced several hype cycles, which were alternating with phases of disillusionment and funding cuts ("AI winter"). The massive investments into AI by today`s hyper scalers and other companies has significantly fueled the progress made with AI, with many practical applications being deployed today.

A highly visible break-through event was the development of AlphaGo (developed by DeepMind Technologies which was later acquired by Google), which in 2015 became the first computer Go program to beat a human professional Go player without handicap on a full-sized 19×19 Go board. Until then, Go was thought of as being "too deep" for a computer to master on the professional level. AlphaGo is using a combination of machine learning and tree search techniques.

Many modern AI methods are based on advanced statistical methods. However, finding a commonly accepted definition of AI is not easy. A quip in Tesler's Theorem says "AI is whatever hasn't been done yet". As computers are becoming increasingly capable, tasks previously considered to require intelligence are later often removed from the definition of AI. The traditional problems of AI research include reasoning, knowledge representation, planning, learning, natural language processing, perception and the ability to move and manipulate objects.

Probably the currently most relevant AI method is Machine Learning (ML). ML refers to a set of algorithms which improve automatically through experience and by the use of data. Within ML, an important category is Deep Learning (DL), which utilizing so-called multi-layered neutral networks. Deep Learning includes Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs), amongst others. See below for an example of a CNN.

The three most common ML methods include supervised, unsupervised and reinforcement learning. The supervised learning method relies on manually labeled sample data, which is used to train a model so that it can then be applied to similar, but new and unlabeled data. The unsupervised method attempts to automatically detect structures and patterns in data. With reinforcement learning, a trial and errror approach is combined with rewards or penalties. Each method will be discussed in more detail in the following.

Some of the key concepts common to these ML methods are summarized in the table below.

Supervised Learning

The first AI/ML method we want to look at is supervised learning. Supervised learning requires a data set with some observations (e.g. images) and the labels of the observations (e.g. classes of objects on these images, like "traffic light", "pedestrian", "speed limit", etc.).

The models are trained on these labeled data sets, and can then be applied to previously unknown observations. The supervised learning algorithm produces an inferred function to make predictions about new, unseen observations which are provided as input to the model. The model can be improved further by comparing its actual output with the intended output: So-called "backward propagation" of errors.

The two main types of supervised models are regression and classification:

• Classification: The output variable is a category e.g. "stop sign", "traffic light", etc.
• Regression: The output variable is a real continuous value, e.g. electricity demand prediction

Some widely used examples of supervised machine learning algorithms are:

• Linear regression, mainly used for for regression problems
• Random forest, mainly used for for classification and regression problems
• Support vector machines, mainly used for classification problems

Unsupervised Learning

The next ML method is Unsupervised Learning, which is a type of algorithm that learns patterns from untagged data. The main goal is to uncover previously unknown patterns in data. Unsupervised machine learning is used when one has no data on desired outcomes.

Typical applications of Unsupervised Machine learning include:

• Clustering: automatically split the data set into groups according to similarity (not always easy)
• Anomaly detection: used to automatically discover unusual data points in a data set, e.g. to identify a problem with a physical asset or equipment.
• Association mining: used to identify sets of items that frequently occur together in a data set, e.g. "people that buy X also tend to buy Y"
• Latent variable models: commonly used for data pre-processing, e.g. reducing the number of features in a data set (dimensionality reduction)

Reinforcement Learning

The third common ML method is Reinforcement Learning (RL). In RL, a so-called Agent learns to achieve its goals in an uncertain, potentially complex environment. This can be, for example, a game-like situation, where the agent is deployed into a simulation where it gets rewards or penalties for the actions it performs. The goal of the agent is to maximize the total reward.

One main challenge in Reinforcement Learning is to create a suitable simulation environment. For example, the RL environment for training autonomous driving algorithms must realistically simulate situations like braking, collisions, etc. The benefit is that it is usually much cheaper to train the model in a simulated environment, rather than risking damaged to real physical objects using immature models. The challenge is then to transfer the model out of the training environment into the real world.

Example: Convolutional Neural Network