What is deep learning?

Deep learning is a subset of machine learning, where computers process large datasets using neural networks modeled after the human brain.

In deep learning, the focus is primarily on the autonomous learning process of these neural networks. They consist of an input layer, one or more hidden layers, and an output layer. Information enters the input layer as a vector, is weighted through artificial neurons in the hidden layers, and finally produces a specific pattern in the output layer. The more layers a neural network has, the more complex the tasks it can handle, enabling artificial intelligence to tackle intricate problems.

How does deep learning work?

Sorting images according to whether dogs, cats or people can be seen in them is a challenging task for a computer. Something that is immediately clear at a glance to humans requires a computer to analyze individual image characteristics.

With deep learning the raw data input, in this case the image, is analyzed layer by layer. In the first layer of an artificial neural network, for example, the system examines the colors in the individual image pixels. Each image pixel is processed with its own neuron. In the following layer, edges and shapes are identified and, in the layer after that, more complex characteristics are examined.

The information collected is displayed in a flexible algorithm. The results from one layer are carried onward into the following layer and change the algorithm. In this way, the computer is able to use a variety of operations to come to the conclusion of whether an image can be categorized as a dog, cat or human.

At the start is the training period, errors in categorization are corrected by humans, allowing the algorithm to adapt. After a short time, it can improve its image recognition independently. As the interlinking between the neurons in the network changes and the weighting of variables within the algorithm is adapted, certain input patterns (different kinds of cat pictures) lead more and more accurately to the same output patterns (the cat being recognized). The more image material is available to the system for it to learn from, the better.

With deep learning, it isn’t always possible for humans to understand which patterns the computer recognized in order to reach its conclusions, particularly since the system continuously optimizes its own decision-making rules.

History of deep learning

Deep learning is actually quite a recent term – it was first used in 2000 – yet the method of using artificial neural networks to enable computers to make intelligent decisions is several decades old.

Basic research in the field goes all the way back to the 1940s. Artificial neural networks were first developed in the 1980s. Back then, though, the quality of the decisions was disappointing, because machines’ independent learning – deep learning – requires large quantities of data, which at the time just weren’t available digitally. Only around the turn of the millennium did the age of big data begin, making deep learning interesting again for science and business.

Strengths and weaknesses

Compared with earlier AI technologies, deep learning is significantly more effective. Before the technology can reach its full potential, though, some weaknesses still have to be overcome.

Strengths of deep learning

One of the most important arguments is the quality of its results. In image recognition and speech processing, in particular, the technology is clearly superior to all others. Provided with high-quality training data, deep learning can carry out routine work much more efficiently and much faster than any human – without any signs of fatigue either, and with no change in quality.

With other forms of machine learning, developers analyze the raw data and periodically define additional features that the algorithm is to take into account while learning in order to improve the AI’s forecasting power. With deep learning, the system itself recognizes useful variables and incorporates these into its learning process. After the initial training period it can learn without any human guidance, saving both time and money since skilled employees aren’t necessary for future development.

Up to now, large quantities of data had to be labeled manually in order to make machine learning possible. In image recognition, for example, employees were required that would assign the label dog or cat to the images. With deep learning, the manual training period is significantly shorter. Above all this is relevant because, while general corporate practice certainly does involve collecting large quantities of data, only in rare cases does it exist in the form of structured data (telephone numbers, address, credit cards, etc.). In most cases it is stored as unstructured data (images, documents, emails, etc.). Unlike alternative methods of machine learning, deep learning can evaluate different sources of unstructured data while considering the task at hand.

The argument that the technology is too costly in practice for it to be applicable on a large scale is losing traction. Services like Google Vision or IBM Watson are increasingly emerging, allowing companies to build on existing neural networks instead of having to develop them from scratch. With this, in the future deep learning will be more and more capable of playing on its strengths in corporate practice.

An overview of the strengths

• Better results than with other methods of machine learning
• No feature development and no data labeling necessary
• Efficient execution of routine tasks without affecting quality
• Problem-free handling of unstructured data
• More and more services to make it easier to use artificial neural networks

Weaknesses of deep learning

Deep learning requires an enormous amount of processing power. This largely depends on the complexity and difficulty of the task to be accomplished and the size of the data set used. Up to now, that made the technology expensive and only practicable for research and a handful of mega-corporations.

There has indeed been observable progress in this respect. What won’t change in the foreseeable future, though, is the fact that decisions made by deep learning are no longer transparent to humans. The neural network is (so far) a black box. For some applications where transparency is decisive, this makes the technology irrelevant.

For deep learning to work at all, large sets of training data are required. If these quantities of data aren’t available, computers aren’t yet able to deliver reliable results with the help of deep learning. The first libraries of neural networks are indeed being published, making the application of deep learning easier for the general public. However, the services are not suitable for every application, meaning that the development of learning algorithms for deep learning still demands a lot of time investment, and potentially takes more time than using alternative methods.

An overview of the weaknesses

• Requires high processing power
• Developing learning algorithms is relatively time-consuming
• A large data pool is necessary
• More training data needed than with other methods of machine learning
• Decisions difficult or impossible to understand (black box)

Application areas for deep learning

Deep learning is already being implemented in various sectors, and in the future we will come across it in many more areas of our day-to-day lives.

• User experience: Some chatbots are already optimized using deep learning and leverage Natural Language Processing to respond better to customer inquiries, easing the workload on human customer support teams.
• Voice assistants: As mentioned, deep learning is used in various voice assistants like Alexa, Google Assistant, or Siri through speech synthesis. These systems autonomously expand their vocabulary and improve their language comprehension.
• Translations: Deep-learning-powered translators, such as DeepL, produce high-quality translations. Thanks to this technology, dialects and text from images can be automatically translated into other languages.
• Content creation: LLMs like ChatGPT use deep learning to generate text that is not only grammatically correct but can also mimic an author’s style—provided they have sufficient training material. Early experiments have seen AI systems create Wikipedia articles and remarkably authentic Shakespearean texts using deep learning.
• Cybersecurity: Deep learning-powered AI systems are particularly suited for detecting irregularities in system activity, helping to identify potential hacker attacks.
• Finance: The ability to detect anomalies is especially useful in financial transactions. Properly trained algorithms can help prevent attacks on banking networks and credit card fraud more effectively than traditional methods.
• Marketing and sales: AI systems can use deep learning to perform sentiment analysis and autonomously implement defined actions to restore customer satisfaction.
• Autonomous driving: While fully autonomous vehicles remain a vision for the future, the technology already exists. It combines various deep learning algorithms: one to recognize traffic signs, another to detect pedestrians, and so on.
• Industrial robots: Robots equipped with deep learning AI could be deployed across numerous industrial sectors. By simply observing a human operator, these systems could learn how to operate machines and optimize their own performance.
• Maintenance: Deep Learning offers significant potential in industrial maintenance, where complex systems require continuous monitoring of numerous parameters. Additionally, it can predict which components of a system are likely to require servicing soon (Predictive Maintenance).
• Medicine: Deep learning AI systems can scan images for anomalies far more accurately than even a trained human eye. As a result, diseases can be detected earlier than ever on CT or X-ray images using these intelligent systems.

Deep learning has great potential but isn’t a universal solution

In public discourse to some extent there is the impression that deep learning is the only technology of the future for AI. It’s true that, in many application areas, deep learning makes much better results possible than previous procedures did.

However, deep learning is not the best technological solution for every problem. There are other strategies to make computers “intelligent” – solutions that can also work with small datasets and where the decision-making is transparent for humans.

Some AI researchers view deep learning as a transitional phenomenon and believe that better approaches, not based on the human brain, will emerge. Google’s company strategy proves that these critical voices are not to be ignored: There, deep learning is just one part of the AI strategy. Alongside it are also further methods of machine learning, like the development of quantum computers.