Printed Computing: Enabling Extremely Low Cost Pervasive Near Sensor Computing
PRICOM aims to develop innovative mixed-signal classifier computing using additive manufacturing to enable cost-effective, accurate, and energy-efficient processing for consumer goods and personalized medicine.
Projectdetails
Introduction
A large number of important domains - such as fast-moving consumer goods and personalized medicine - have still not seen the benefits of computing, mainly due to high production costs of rigid silicon technologies. Printed electronics based on additive manufacturing processes hold promise of meeting cost and conformity needs of such applications.
Challenges of Traditional Architectures
However, the realization of traditional digital processor architectures is infeasible due to constraints of low-cost manufacturing, such as:
- Form factor
- Low device count
- Large feature sizes
- High variations
The fundamental research question, hence, is how to perform accurate, reliable, and energy-efficient classification computing to meet target applications’ requirements within the constraints of additive printed manufacturing.
Aim of PRICOM
The aim of PRICOM is to make breakthroughs by developing unconventional mixed-signal classifier computing paradigms together with their hardware realization and mapping based on additive printing technologies. This enables:
- Significant reduction of the hardware footprint
- Direct processing of analog sensory inputs
- Achievement of high classification accuracy
Challenges in Analog Computing
Nevertheless, it is a major challenge as analog computing is very sensitive to variations, and at the same time, additive manufacturing is inherently prone to printing variations.
Proposed Solutions
I aim at closing this gap by:
- Utilizing the inherent tolerance of neuromorphic computing to variations with special hardware primitive design and training algorithms
- Designing novel variation-aware physical design algorithms
- Developing an iterative tuning flow exploiting unique features of additive manufacturing
Feasibility and Impact
The feasibility of multi-disciplinary research of PRICOM is underpinned by my unique cross-layer expertise and will be tested by fabrication-based demonstration of printed computing systems.
PRICOM can enable the proliferation of computing in the consumer market and personalized medicine, bringing economical gains and improving quality of life.
Financiële details & Tijdlijn
Financiële details
Subsidiebedrag | € 2.499.286 |
Totale projectbegroting | € 2.499.286 |
Tijdlijn
Startdatum | 1-10-2022 |
Einddatum | 30-9-2027 |
Subsidiejaar | 2022 |
Partners & Locaties
Projectpartners
- KARLSRUHER INSTITUT FUER TECHNOLOGIEpenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Neuromorphic computing system for real-time signal monitoring and classification with ultra-low-power 2D devicesThis project aims to develop a neuromorphic computing system using 2D semiconductor-based charge trap memory for efficient, low-power detection and classification of electrophysiological signals. | ERC Proof of... | € 150.000 | 2024 | Details |
ANalogue In-Memory computing with Advanced device TEchnologyThe project aims to develop closed-loop in-memory computing (CL-IMC) technology to significantly reduce energy consumption in data processing while maintaining high computational efficiency. | ERC Advanced... | € 2.498.868 | 2023 | Details |
Printing Electro-TomographyThe project aims to enhance 3D printing by integrating real-time electrical impedance measurements for improved speed and precision, boosting quality and efficiency in both professional and consumer markets. | ERC Proof of... | € 150.000 | 2022 | Details |
Neuromorphic Flexible Electro/chemical Interface for in-Memory Bio-Sensing and Computing.Develop a miniaturized, self-contained biosensing technology using neuromorphic devices for real-time monitoring and classification of neurodegenerative biomarkers in individualized healthcare. | ERC Starting... | € 1.500.000 | 2025 | Details |
Heterogeneous integration of imprecise memory devices to enable learning from a very small volume of noisy dataThe DIVERSE project aims to develop energy-efficient cognitive computing inspired by insect nervous systems, utilizing low-endurance resistive memories for real-time decision-making in noisy environments. | ERC Consolid... | € 2.874.335 | 2022 | Details |
Neuromorphic computing system for real-time signal monitoring and classification with ultra-low-power 2D devices
This project aims to develop a neuromorphic computing system using 2D semiconductor-based charge trap memory for efficient, low-power detection and classification of electrophysiological signals.
ANalogue In-Memory computing with Advanced device TEchnology
The project aims to develop closed-loop in-memory computing (CL-IMC) technology to significantly reduce energy consumption in data processing while maintaining high computational efficiency.
Printing Electro-Tomography
The project aims to enhance 3D printing by integrating real-time electrical impedance measurements for improved speed and precision, boosting quality and efficiency in both professional and consumer markets.
Neuromorphic Flexible Electro/chemical Interface for in-Memory Bio-Sensing and Computing.
Develop a miniaturized, self-contained biosensing technology using neuromorphic devices for real-time monitoring and classification of neurodegenerative biomarkers in individualized healthcare.
Heterogeneous integration of imprecise memory devices to enable learning from a very small volume of noisy data
The DIVERSE project aims to develop energy-efficient cognitive computing inspired by insect nervous systems, utilizing low-endurance resistive memories for real-time decision-making in noisy environments.
Vergelijkbare projecten uit andere regelingen
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Green SELf-Powered NEuromorphic Processing EnGines with Integrated VisuAl and FuNCtional SEnsingELEGANCE aims to develop eco-friendly, light-operated processing technology for energy-efficient IoT applications, utilizing sustainable materials to minimize electronic waste and environmental impact. | EIC Pathfinder | € 3.100.934 | 2024 | Details |
Hybrid electronic-photonic architectures for brain-inspired computingHYBRAIN aims to develop a brain-inspired hybrid architecture combining integrated photonics and unconventional electronics for ultrafast, energy-efficient edge AI inference. | EIC Pathfinder | € 1.672.528 | 2022 | Details |
High mobilitY Printed nEtwoRks of 2D Semiconductors for advanced electrONICsHYPERSONIC aims to enhance the mobility of printed electronic devices by minimizing junction resistance in nanosheet networks, enabling ultra-cheap, high-performance wearable sensors. | EIC Pathfinder | € 2.966.790 | 2024 | Details |
RECONFIGURABLE SUPERCONDUTING AND PHOTONIC TECHNOLOGIES OF THE FUTURERESPITE aims to develop a compact, scalable neuromorphic computing platform integrating vision and cognition on a single chip using superconducting technologies for ultra-low power and high performance. | EIC Pathfinder | € 2.455.823 | 2023 | Details |
Smart Paper & PrintingHet project ontwikkelt innovatieve materialen en machines voor geprinte elektronica, inclusief nieuwe producten en diensten, gericht op het verbeteren van test- en karakteriseringstechnieken. | Mkb-innovati... | € 198.800 | 2020 | Details |
Green SELf-Powered NEuromorphic Processing EnGines with Integrated VisuAl and FuNCtional SEnsing
ELEGANCE aims to develop eco-friendly, light-operated processing technology for energy-efficient IoT applications, utilizing sustainable materials to minimize electronic waste and environmental impact.
Hybrid electronic-photonic architectures for brain-inspired computing
HYBRAIN aims to develop a brain-inspired hybrid architecture combining integrated photonics and unconventional electronics for ultrafast, energy-efficient edge AI inference.
High mobilitY Printed nEtwoRks of 2D Semiconductors for advanced electrONICs
HYPERSONIC aims to enhance the mobility of printed electronic devices by minimizing junction resistance in nanosheet networks, enabling ultra-cheap, high-performance wearable sensors.
RECONFIGURABLE SUPERCONDUTING AND PHOTONIC TECHNOLOGIES OF THE FUTURE
RESPITE aims to develop a compact, scalable neuromorphic computing platform integrating vision and cognition on a single chip using superconducting technologies for ultra-low power and high performance.
Smart Paper & Printing
Het project ontwikkelt innovatieve materialen en machines voor geprinte elektronica, inclusief nieuwe producten en diensten, gericht op het verbeteren van test- en karakteriseringstechnieken.