People may wonder how Google is able to translate an entire web page to a different language in a matter of seconds, or how their phone photo gallery groups images based on the location where the pictures were taken. These are all products of deep learning.
Deep learning is a subset of machine learning, which in turn, is a subset of Artificial Intelligence (AI). AI is a technique that enables a machine to mimic human behaviour, while machine learning is a technique to achieve AI through algorithms (a process or set of rules to be followed in calculations or other problem-solving operations, especially by a computer)trained with data. Deep learning is a type of machine learning inspired by the structure of the human brain. In terms of deep learning, this structure is called an artificial neural network.
How is deep learning different from machine learning?
With machine learning, human intervention is needed to tell the machine features needed to differentiate between two or more different items. For example, a machine developed to separate yams from potatoes has to be told the unique features of both items to enable it separate them. However, with deep learning, the features are picked out by the neural network without human intervention. That kind of independence comes at the cost of having a much higher volume of data to train a machine. Deep learning is the most efficient way to deal with unstructured data.