2021 machine learning:What are the elements of machine learning?
As mentioned, machine learning is a subset of AI and is generally split into two main categories: supervised and unsupervised learning.
A common technique for teaching AI systems is by training them using many labelled examples. These machine-learning systems are fed huge amounts of data, which has been annotated to highlight the features of interest. These might be photos labelled to indicate whether they contain a dog or written sentences that have footnotes to indicate whether the word ‘bass’ relates to music or a fish. Once trained, the system can then apply these labels to new data, for example, to a dog in a photo that’s just been uploaded.
This process of teaching a machine by example is called supervised learning. Labelling these examples is commonly carried out by online workers employed through platforms like Amazon Mechanical Turk.
Training these systems typically requires vast amounts of data, with some systems needing to scour millions of examples to learn how to carry out a task effectively –although this is increasingly possible in an age of big data and widespread data mining.
Training datasets are huge and growing in size — Google’s Open Images Dataset has about nine million images, while its labelled video repository YouTube-8M links to seven million labelled videos. ImageNet, one of the early databases of this kind, has more than 14 million categorized images. Compiled over two years, it was put together by nearly 50 000 people — most of whom were recruited through Amazon Mechanical Turk — who checked, sorted, and labelled almost one billion candidate pictures.
Having access to huge labelled datasets may also prove less important than access to large amounts of computing power in the long run.
In recent years, Generative Adversarial Networks (GANs) have been used in machine-learning systems that only require a small amount of labelled data alongside a large amount of unlabelled data, which, as the name suggests, requires less manual work to prepare.
This approach could allow for the increased use of semi-supervised learning, where systems can learn how to carry out tasks using a far smaller amount of labelled data than is necessary for training systems using supervised learning today.
In contrast, unsupervised learning uses a different approach, where algorithms try to identify patterns in data, looking for similarities that can be used to categorise that data.
An example might be clustering together fruits that weigh a similar amount or cars with a similar engine size.
The algorithm isn’t set up in advance to pick out specific types of data; it simply looks for data that its similarities can group, for example, Google News grouping together stories on similar topics each day.
A crude analogy for reinforcement learning is rewarding a pet with a treat when it performs a trick. In reinforcement learning, the system attempts to maximise a reward based on its input data, basically going through a process of trial and error until it arrives at the best possible outcome.
An example of reinforcement learning is Google DeepMind’s Deep Q-network, which has been used to best human performance in a variety of classic video games. The system is fed pixels from each game and determines various information, such as the distance between objects on the screen.
By also looking at the score achieved in each game, the system builds a model of which action will maximise the score in different circumstances, for instance, in the case of the video game Breakout, where the paddle should be moved to in order to intercept the ball.
The approach is also used in robotics research, where reinforcement learning can help teach autonomous robots the optimal way to behave in real-world environments.