SPIN-ION | Hybrid Spintronic Synapses for Neuromorphic Computing

Summary
At Spin-Ion Technologies we develop a new manufacturing solution based on ion beam processes to precisely engineer magnetic materials at the atomic scale. This result enables the development of new neuromorphic chips based on low power synapses composed of magnetic devices that can overcome both catastrophic forgetting and reduce device variability, hence greatly advancing the development of highly efficient, robust hardware amenable to neural applications on the edge.

Our transition project involves both hardware & software developments to demonstrate implementation of an Artificial Neural Network on a magnetic chip, which will bridge computational neuroscience and deep learning while generating strong impact for future embedded and neuromorphic systems. This project also covers all necessary steps for full commercial readiness, including problem/solution validation, market research, competition analysis, establishing IP strategy, ensuring regulatory compliance, stakeholder engagements, dissemination activities, construction of a detailed business plan and securing future funding.
Results, demos, etc. Show all and search (0)
Unfold all
/
Fold all
More information & hyperlinks
Web resources: https://cordis.europa.eu/project/id/101112764
Start date: 01-05-2023
End date: 31-10-2025
Total budget - Public funding: 2 499 998,75 Euro - 2 499 998,00 Euro
Cordis data

Original description

At Spin-Ion Technologies we develop a new manufacturing solution based on ion beam processes to precisely engineer magnetic materials at the atomic scale. This result enables the development of new neuromorphic chips based on low power synapses composed of magnetic devices that can overcome both catastrophic forgetting and reduce device variability, hence greatly advancing the development of highly efficient, robust hardware amenable to neural applications on the edge.

Our transition project involves both hardware & software developments to demonstrate implementation of an Artificial Neural Network on a magnetic chip, which will bridge computational neuroscience and deep learning while generating strong impact for future embedded and neuromorphic systems. This project also covers all necessary steps for full commercial readiness, including problem/solution validation, market research, competition analysis, establishing IP strategy, ensuring regulatory compliance, stakeholder engagements, dissemination activities, construction of a detailed business plan and securing future funding.

Status

SIGNED

Call topic

HORIZON-EIC-2022-TRANSITIONCHALLENGES-01

Update Date

31-07-2023
Images
No images available.
Geographical location(s)