NEMERFEC

Start date: 1 September 2024

End date: 28 February 2027

Grant agreement ID: 101110162

Artificial neural networks (ANNs) are simplified models and hardware that simulate how the brains of living beings, especially humans, process information. ANNs are inspired by the nervous system and biological behaviour, creating a layered interconnected system of artificial neurons that collaborate to process input data and generate output. ANNs differ from other AI models in that they have the ability to learn automatically (machine learning). This technology has a huge current and potential impact for future applications, just to name a few: autonomous vehicles, renewable energy, economic and financial forecasting, computer vision and discriminative medicine and healthcare services. In the last decade, ANNs have become a very popular topic, but the technology itself has existed for many decades with several problems still to be solved. For example, current computer systems are very inadequate in terms of data processing, storage and transmission. Energy consumption issues are also an unresolved problem, where the rational use of energy and natural resources is a fundamental goal of global sustainability. NEMERFEC aims to create novel ANNs by developing hardware based on memristive and ferroelectric material systems. These thin films of binary and complex oxides must be deposited by physical ablation methods, such as PLD and sputtering, with a high degree of control during deposition. Advanced device characterisation, microfabrication and nanofabrication techniques will be carried out in the clean room facilities of the Aragon Institute of Nanoscience and Materials (INMA-CSIC) to obtain RNAs at nanometre scales and with ultra-fast turnaround time. The final ANNs will be implemented in thermal imaging analysis in hyperthermia processes with magnetic nanoparticles at NANO Scale Biomagnetics during the non-academic internship period. These potential results will be completely novel in this type of application.

More info here