Siraj Raval explores generative modeling technology.

This innovation is changing the face of the Internet as you read this. It’s now possible to design automated systems that can write novels, act as talking heads in videos, and compose music.

In this episode, Siraj explains how generative modeling works by demoing 3 examples that you can try yourself in your web browser. 

Of all the machine learning algorithms, the most fascinating are neural networks. They don’t require statistical hypothesis or rigorous data preparation save for normalization.

The power of a neural network lies in its architecture, its activation functions, its regularization, etc.

Here’s an interesting article exploring a particular kind of neural network: the autoencoder.

Fraud detection, a common use of AI, belongs to a more general class of problems — anomaly detection.

An anomaly is a generic, not domain-specific, concept. It refers to any exceptional or unexpected event in the data: a mechanical piece failure, an arrhythmic heartbeat, or a fraudulent transaction.

Basically, identifying a fraud means identifying an anomaly in the realm of a set of legitimate transactions. Like all anomalies, you can never be truly sure of the form a fraudulent transaction will take on. You need to take all possible “unknown” forms into account.

Here’s an interesting article on doing anomaly/fraud detection with a neural autoencoder.

Using a training set of just legitimate transactions, we teach a machine learning algorithm to reproduce the feature vector of each transaction. Then we perform a reality check on such a reproduction. If the distance between the original transaction and the reproduced transaction is below a given threshold, the transaction is considered legitimate; otherwise it is considered a fraud candidate (generative approach). In this case, we just need a training set of “normal” transactions, and we suspect an anomaly from the distance value.

Based on the histograms or on the box plots of the input features, a threshold can be identified. All transactions with input features beyond that threshold will be declared fraud candidates (discriminative approach). Usually, for this approach, a number of fraud and legitimate transaction examples are necessary to build the histograms or the box plots.