Unsure about the similarities and differences between artificial intelligence, machine learning and deep learning? This blog post introduces the quick basics.
The definition of artificial intelligence is wide
According to Andrew Moore, Dean of the School of Computer Science at Carnegie Mellon University, ‘Artificial intelligence is the science and engineering of making computers behave in ways that, until recently, we thought required human intelligence.’ These machines don’t simply perform actions that are repetitive, but they can be programmed to different situations. Simply put, AI is a wide umbrella term for any computer programme that does something smart. It doesn’t need to follow a pattern nor be continuous.
Machine learning is technically a subset of artificial intelligence
Machine learning is a branch of AI; it’s more specific than the overall concept. Machine learning bases itself on the notion that we can build machines to learn on their own – from patterns and inferences – without constant supervision by humans. Machine learning algorithms build a mathematical model of sample data, known as “training data”, in order to make predictions or decisions without being explicitly programmed to perform the task. According to Professor and Former Chair of the Machine Learning Department at Carnegie Mellon University, Tom M. Mitchell, ‘Machine learning is the study of computer algorithms that improve automatically through experience.’ Machine learning and its dynamism is one of the ways we expect to achieve AI.
What then, is deep learning?
The same way machine learning is a branch of artificial intelligence, deep learning is a sub-field of machine learning. Deep learning is usually associated with deep artificial neural networks – a set of algorithms loosely modelled after the human brain to recognise patterns. ‘Deep’ refers to the number of layers in a neural network – and a deep network has more than one hidden layer. According to experts at Skymind, multiple hidden layers allow deep neural networks to learn features of the data in a feature hierarchy. To illustrate: simple features (e.g. two pixels) recombine from one layer to the next, to form more complex features (e.g. a line).
As Daniel Tunkelang – a computer scientist who led machine learning projects at Endeca, Google and LinkedIn – put it, AI is not going to become self-aware, rise up, and destroy humanity. But it can indeed make various processes easier in the world we live in. What are your insights?
Look out for more of our articles on digital technologies.
Sources: https://georgianpartners.com/investment-thesis-areas/applied-artificial-intelligence/ https://www.forbes.com/sites/forbestechcouncil/2018/07/11/machine-learning-vs-artificial-intelligence-how-are-they-different/#4a45b4293521 https://medium.com/datadriveninvestor/differences-between-ai-and-machine-learning-and-why-it-matters-1255b182fc6 https://machinelearningmastery.com/what-is-deep-learning/
About the author
- Inland water2019.07.11Best practices for successful coastal flooding adaptation
- Digital technologies2019.03.13The very basics of artificial intelligence, machine learning and deep learning
- Customer experience2019.02.01Why empathy is the key to providing a great customer experience
- Inland water2019.01.10What has climate change got to do with increased groundwater salinity?