What is deep learning?

Deep learning illustrated by a brain over a microchip
(Image credit: Shutterstock)

Machine learning has many broad methods, of which deep learning is perhaps the most well-known. A type of artificial intelligence (AI) technology, the ‘deep’ in deep learning refers to the layered and hierarchical nature of the algorithms it uses to train AI.

The real-world applications of deep learning are broad but can most commonly be found in use cases such as voice recognition in smart home assistants, and natural language processing models used by AI-driven chatbots, for instance.

The ultimate ambition of deep learning is to teach an AI to make its own decisions based on the data it is fed, such as a question submitted to a home assistant like Amazon Alexa or Google Home. To hard-code all the different types of questions a user could ask a home assistant would be nigh-on impossible and incredibly laborious. The more efficient, and perhaps more time-consuming in the short-term, method of building such an AI would be to train it using deep learning to recognise what it's being asked and how to appropriately respond.

Deep learning models are trained using data. Tons of data. Large volumes of data are required so it can make more accurate decisions based on past experiences – it learns the appropriate responses to the different types of data it’s fed. Many deep learning models take inspiration from the structure of the human brain, using neural networks that arrange analytical nodes in interconnecting pathways, allowing them to replicate the multi-layered (deep) connections found in the human brain.

Is deep learning supervised or unsupervised?

Image of brain with dark background

(Image credit: Shutterstock)

The special draw of deep learning that’s attracting so many to study the field is the potential for both supervised learning and unsupervised learning, although it's the latter that has opened up so many avenues for research.

Supervised deep learning definition

Supervised learning refers to the approach of training a deep learning model using labelled data. This data is prepared by the researcher before the training begins, with both the input and output data labelled so the model can specifically analyse the relationship between the two sets. Once the model has defined the relationship and why it exists, it can be used to accurately analyse additional data sets and predict the outcomes.

This type of training is considered 'supervised' due to the need for human intervention – labelling the data so the model knows what it’s looking at specifically. It's considered the most popular form of training in machine learning, commonly used for purposes such as object detection.

There is also a semi-supervised approach to deep learning that involves using a small proportion of the entire training data set and labelling it, and simultaneously using a much larger proportion of unlabelled data to analyse a problem. This is a middle ground between supervised and unsupervised and can be used to train models to predict new outcomes from unseen data.

Unsupervised deep learning definition

RELATED RESOURCE

IT Pro 20/20: The quest to humanise AI

Issue 28 looks at recent developments in artificial intelligence that are pushing businesses to be more creative

FREE DOWNLOAD

Unsupervised learning refers to the process of using entirely unlabelled data, and feeding it into the deep learning model with a view to training said model to recognise patterns in completely new data. The lack of human intervention creates potential for unforseen determinations to be made by the model, something that forms the basis of a huge body of research today.

There are three main tasks when it comes to unsupervised learning. These are:

  • Clustering: Involves looking at unlabelled data and grouping similar data points into groups. This task is often used for training models to compress digital images, for example
  • Association: Somewhat similar to clustering, the association approach is used to understand why there is a relationship between data points and how the data points connect rather than just knowing that there is a relationship there
  • Dimensionality reduction: Often performed during the pre-processing of data, where researchers attempt to reduce the noise in the training data. This refers to ‘simplifying’ a given data set that has too many features, or dimensions, to accurately analyse. It involves reducing the number of data inputs so that a relationship between input and output data can be established

Examples of deep learning today

A woman reading a book in the driver's seat while the car drives itself

(Image credit: Shutterstock)

Many of today's most advanced machine learning systems use a neural network to process data. Recent successes in the driverless cars industry have been made possible because of deep learning, while the principles are also being deployed in the defence and aerospace sectors in order to identify objects from space.

While the potential of deep learning is vast, it has limitations when it comes to more human-like tasks. Deep learning excels at pattern recognition, like the complex but fixed rules of Go. A vast amount of training data is also still required to teach a machine only a specific set of rules.

Pattern recognition is perhaps exemplified most prominently in conversation AI, with deep learning acting as the supporting network. Multimodal inputs including voice and recognition capabilities are processed alongside multimodal outputs such as images and synthesized voices. Enterprises from Starbucks to Apple are deploying this intelligence, giving customers the option to place orders through their applications via voice commands and the ease of logging onto their devices with sight alone.

At the current stage of development, it does not appear possible for deep learning to perform the same elaborate, adaptive thought processes as humans, however, the technology continues to evolve at quite a rate.

The future of deep learning

The Pentagon as seen from an aerial angle

(Image credit: Shutterstock)

Deep learning may not result in killer robots anytime soon, but that isn't to say it won't fundamentally alter aspects of society in other ways.

The research group Google Brain demonstrated how its deep learning AI was thinking for itself. Without specifying any experimental parameters for cat identification, millions of cats were put forward to the 'Google Brain', and the network successfully identified the images without the help of labelled data.

RELATED RESOURCE

Modernise your IA for AI and hybrid cloud

Building an artificial intelligence (AI) information architecture (IA)

FREE DOWNLOAD

Identifying cats may seem rudimentary, but it isn't difficult to see how such a breakthrough could be put to more practical use.

In medicine, deep learning has been found to be on par with human expertise when it comes to interpreting medical images. The study, carried out by the University of Birmingham, may pave the way for AI to play a greater role in the medical field going forwards, easing the strain on resources and allowing doctors to spend more time with patients.

Perhaps the most exciting area where deep learning is being touted as a possible springboard to discovery is in the cosmos. Researchers from ETH Zurich university released a paper in which they employed neural networks to study dark matter. When compared to the Hubble telescope, deep learning was found to deliver 30% more accurate values when breaking down the composites of the universe, apportioning baryonic matter, dark matter and dark energy. The researchers concluded by claiming that deep learning is a promising prospect for cosmological data analysis in the future.

What is certain, is that with funding being poured into AI - the Pentagon allocated nearly $1 billion to AI in 2020 - and specifically deep learning research studies, the technologies' influence will only grow.