If you’re in tech, you hear these terms all the time and probably wonder what the differences are. They can get a bit confusing, which is why I make these kinds of articles.
Approaches to Artificial Intelligence
- Machine Learning: An approach to AI that focuses on enabling computers to learn without being explicitly programmed. They can be summarized as systems that learn from data instead of from just their programming like normal computers.
- Neural Networks: A type of Machine Learning, Artificial Neural Networks (ANNs) attempt to model biological systems, such as the brain, in order to be able to learn when exposed to unknown inputs. They’re made up of a serious of nodes that are connected to each other much like in the brain.
- Deep Learning: A branch of machine learning that attempts to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and non-linear transformations (Wikipedia). Note that deep learning is considered by many to be a simple rebranding of Neural Networks.
- Supervised Learning A type of Machine Learning where data you provide is already labeled. For example, you might some samples that are clearly smiling faces and some that are clearly frowning, and you’re looking to train the algorithm to tell the difference.
- Unsupervised Learning: A type of Machine Learning algorithm where the data you’re providing is not labeled, so you’re looking for the algorithms to tell YOU about patterns that it finds, which you might not even be aware of.
- Expert Systems: A computer system that emulates the decision-making ability of a human expert. Expert systems are designed to solve complex problems by reasoning about knowledge, represented primarily as if–then rules rather than through conventional procedural code.
I hope this has been useful.
[ Created: May 2016, Updated: August 2016 ]