Jo is a digital producer at Pattern. Jo has a background in communication, and has worked as a producer and editor for organisations such as Les Mills International, Tailor, Auckland Libraries and XtraMSN/Telecom. From 2007-2009, Jo was the web editor for Taste and Metro magazines.
AI vs ML vs DL: what's the difference?
We delve into what the various terms: artificial intelligence (AI), machine learning (ML) and deep learning (DL) mean, and check out a real-life example of a well-known AI-ML application.
Artificial intelligence is an all-encompassing concept of how machines and computers can increasingly perform and mimic human-like behaviours and tasks.
Machine learning is a branch (subset) of AI which consists of using algorithms to parse and learn from data in order to deliver AI applications.
Deep learning is an artificial neural network that structures algorithms in layers in order to learn and make intelligent decisions on its own.
Above: The AI stack, explained by Andew Moore, Professor and Dean of the School of Computer Science, Carnegie Mellon University.
Spotify, the freemium audio streaming platform, is a great example of a product that has been pushing AI, ML and DL boundaries since it was created by Swedish programmer, Daniel Ek, in 2006.
Spotify’s technology enhances and personalises your music not just through one, but three models, hence mixing some of the world’s best strategies to create its own discovery engine.
Spotify uses: Audio models to analyse the raw audio tracks. Natural Language Processing (NLP) models to analyse text. Collaborative filtering models to analyse both your behaviour and others’ behaviours.
In practical reality, what you get from Spotify’s algorithms are fabulously personalised daily, weekly and new recommendations automatically customised based on your own song and genre choices.
Here’s further reading on why Spotify knows you so well.
Check out our other articles on artificial intelligence.