Neural networks are among the most important technologies of our time. They are closely linked to AI, deep learning, and computer vision. Understanding what they are, how they work, and where they are applied is essential for anyone working with research and development projects or in the field of EU project management.
Find out more! Keep reading.
Table of contents
What are neural networks?
Neural networks are mathematical models inspired by how the human brain works. They use artificial neurons organised into interconnected nodes capable of processing input data (audio, text, images, etc.) and producing outputs. Each interconnection makes it possible to identify recurring patterns, make predictions, and classify information.
Who invented neural networks?
The concept of neural networks emerged in the 1940s—less than a century ago—and originates from the work of American researchers Warren McCulloch and Walter Pitts, who first proposed mathematical predictive models inspired by the neurons of the human brain.
However, the real breakthrough came only in 1986 with the development of the backpropagation algorithm (literally “error backpropagation”), formalised by researchers David Rumelhart, Geoffrey Hinton, and Ronald Williams.
The key feature of the backpropagation algorithm is that it enables increasingly efficient predictive models to be trained by calculating how much each error parameter influences the result. As a result, machine learning takes a major step forward: the machine begins to correct itself.
What is deep learning used for?
Deep learning is a branch of machine learning that uses complex neural networks with many layers—often called multilayer networks—that can:
- recognising images and videos;
- “understanding” natural language;
- driving vehicles;
- performing medical diagnoses;
- identifying the most effective business and industrial growth strategies.
For example, when a neural network recognises an image, the first layers detect simple features such as facial traits, object boundaries, edges, and similar elements, while deeper layers identify more complex shapes and patterns. Well-known AI systems such as ChatGPT, Gemini, and Copilot all rely on deep learning algorithms.
How are neural networks connected to European projects?
Modern neural networks represent a key technology in R&D projects. The European Union (EU), through programmes such as Horizon Europe and Digital Europe, is investing significantly in artificial intelligence. Here are two concrete examples:
1. AI-SPRINT
The European project AI-SPRINT (Artificial Intelligence in Secure Privacy-preserving computing coNTinuum), funded under the Horizon Europe programme, aims to make the development of artificial intelligence applications easier.
AI-SPRINT combines AI, cloud computing, and the Internet of Things (IoT) to standardise neural network programming models, making them readily applicable to sectors such as Agriculture 4.0 and deep tech.
2. CLARIFY
CLARIFY (Cancer Long Survivors Artificial Intelligence Follow-up) uses machine learning to improve the quality of life of cancer patients who have already undergone treatment. The goal is to prevent complications or relapses by identifying potential risk factors in advance.
In CLARIFY, the algorithm analyses electronic health records (EHRs) from patients across different healthcare institutions to identify recurring patterns and support more informed decision-making.
Do you want to develop a project based on neural networks? Contact us
Neural networks are a cornerstone of Industry 5.0. The European Union is creating an increasing number of programmes to support innovation ecosystems. Universities, research organisations (ROs), start-ups, SMEs and large enterprises now can fund their projects, provided they align with European strategic priorities.
If your organisation is working on concepts such as AI, deep learning, machine learning, or neural networks, contact us to build an international consortium and develop new projects.
Our R&D centre, PMF Research, is currently looking for partners. If you are interested in collaborating, get in touch and share your project idea with us. You can fill in the contact form below or message us on WhatsApp. Building the partnerships of the future has never been easier.
