Spanish National Research Council · University of Seville
 HOME
INTRANET
sp    en

Funding for the research activities carried out at IMSE-CNM comes primarily from the participation in competitive tender processes. The research is then conducted out via agreements, projects and contracts with national and international public organizations and private companies and organizations.



APPROVIS3D
Analog PROcessing of bioinspired VIsion Sensors for 3D reconstruction
PI: Teresa Serrano Gotarredona
[+]
Type: Research project
Reference: CHIST-ERA 2018-ACAI, Ref: PCI2019-111826-2
Funding Body: European Union
Start date: 01/04/2020
End date: 31/03/2023
Funding: 149.772,00 €
Abstract: APROVIS3D project targets analog computing for artificial intelligence in the form of Spiking Neural Networks (SNNs) on a mixed analog and digital architecture. The project includes including field programmable analog array (FPAA) and SpiNNaker applied to a stereopsis system dedicated to coastal surveillance using an aerial robot. Computer vision systems widely rely on artificial intelligence and especially neural network based machine learning, which recently gained huge visibility. The training stage for deep convolutional neural networks is both time and energy consuming. In contrast, the human brain has the ability to perform visual tasks with unrivalled computational and energy efficiency. It is believed that one major factor of this efficiency is the fact that information is vastly represented by short pulses (spikes) at analog -not discrete-times. However, computer vision algorithms using such representation still lack in practice, and its high potential is largely underexploited. Inspired from biology, the project addresses the scientific question of developing a lowpower, end-to-end analog sensing and processing architecture of 3D visual scenes, running on analog devices, without a central clock and aims to validate them in real-life situations. More specifically, the project will develop new paradigms for biologically inspired vision, from sensing to processing, in order to help machines such as Unmanned Autonomous Vehicles (UAV), autonomous vehicles, or robots gain high-level understanding from visual scenes. The ambitious long-term vision of the project is to develop the next generation AI paradigm that will eventually compete with deep learning. We believe that neuromorphic computing, mainly studied in EU countries, will be a key technology in the next decade. It is therefore both a scientific and strategic challenge for the EU to foster this technological breakthrough. The consortium from four EU countries offers a unique combination of expertise that the project requires. SNNs specialists from various fields, such as visual sensors (IMSE, Spain), neural network architecture and computer vision (Uni. of Lille, France) and computational neuroscience (INT, France) will team up with robotics and automatic control specialists (NTUA, Greece), and low power integrated systems designers (ETHZ, Switzerland) to help geoinformatics researchers (UNIWA, Greece) build a demonstrator UAV for coastal surveillance (TRL5). Adding up to the shared interest regarding analog based computing and computer vision, all team members have a lot to offer given their different and complementary points of view and expertise. Key challenges of this project will be end-to-end analog system design (from sensing to AIbased control of the UAV and 3D coastal volumetric reconstruction), energy efficiency, and practical usability in real conditions. We aim to show that such a bioinspired analog design will bring large benefits in terms of power efficiency, adaptability and efficiency needed to make coastal surveillance with UAVs practical and more efficient than digital approaches.

SPINAGE
Weighted Spintronic-Nano-Oscillator-based Neuromorphic Computing System Assisted by laser for Cognitive Computing
PI: Teresa Serrano Gotarredona
[+]
Type: Research project
Reference: H2020-FETOPEN-2018-2020, Ref: 899559
Funding Body: European Union
Start date: 01/09/2020
End date: 31/08/2024
Funding: 437.577,00 €
Abstract: The brain is a highly complex, high performance and low energy computing system due to its massive parallelism and intertwined network, which outperforms the current computers by orders of magnitudes, especially for cognitive computing applications. A large effort has been made into understanding the computing and mimicking the brain into an artificial implementation, so-called neuromorphic computing that has received much attention thanks to the advances in novel nanoscale technologies. The current implementation of the neuromorphic computing systems (NCS) using Complementary Metal-Oxide-Semiconductor (CMOS) technologies has 5-6 orders of magnitude lower performance (operation/sec/Watt/cm3) compared to the brain. Spintronic devices, using the spin of the electron instead of its charge, have been considered one of the most promising approaches for implementing not only memories but also NCSs leading to a high density, high speed, and energy-efficiency. The main goal of SpinAge is to realize a novel NCS enabling large-scale development of braininspired devices outclassing the performance of current computing machines. This will be achieved by the novel structures using spintronics and memristors, on-chip laser technology, nano electronics and finally advanced integration of all these technologies. We expect this unprecedented combination of emerging technologies will lead to at least 4-5 orders of magnitude better performance than the state-of-the-art CMOS-based NCSs. The approach taken in SpinAge is to implement synaptic neurons using novel nanoscale weighted spin-based nanooscillators, assisted by a low-energy laser pulse irradiation from an integrated plasmonic laser chip, integrated all with the CMOS interfacing electronics for a proof-of-concept of a 16x16 NCS for cognitive computing applications. Our breakthrough platform technology will demonstrate EU leadership of advanced neuromorphic computing.

HERMES
Hybrid Enhanced Regenerative Medicine Systems
PI: Teresa Serrano Gotarredona
[+]
Type: Research project
Reference: 824164
Funding Body: European Union
Start date: 2019
End date: 2023
Funding: 438.511,25 €
Abstract: Brain disorders are the most invalidating condition, exceeding HIV, cancer and heart ischemia, with significant impact on society and public health. Regenerative medicine is a promising branch of health science that aims at restoring brain function by rebuilding brain tissue. However, repairing the brain is one of the hardest challenges and we are still unable to effectively rebuild brain matter. Epilepsy is particularly challenging due to its dynamic nature caused by the relentless brain damage and aberrant rearrangements of brain rewiring. To overcome the biological uncertainty of canonical regenerative approaches, we propose an innovative solution based on intelligent biohybrids, made by the symbiotic integration of bioengineered brain tissue, neuromorphic microelectronics and artificial intelligence, to effectively drive self-repair of dysfunctional brain circuits and we validate it against animal models of epilepsy. HERMES fosters the emergence of a novel biomedical paradigm, rooted in the use of biohybrid neuronics (neural electronics), which we name enhanced regenerative medicine. To this end, HERMES will promote interdisciplinary cross-fertilization within and outside the consortium; it will extend the concepts of enhanced brain regeneration to philosophy, ethics, policy and society to foster the emergence of a new innovation eco-system. Intelligent biohybrids will represent a major breakthrough to advance brain repair research beyond regenerative medicine and neurotechnology alone; it will bring new knowledge in neurobiology, cognitive neuroscience and philosophy, and new neuromorphic technology and AI algorithms. HERMES will bring a giant conceptual leap that will shift the concept of biomedical interventions from treating to healing. In turn, it will potentially generate major returns on health care and society at large by bringing previously unimaginable possibilities to defeat disorders that represent today a global major burden of disease.

COGNET
Event-based cognitive vision system. Extension to audio with sensory fusion
PI: Teresa Serrano Gotarredona
[+]
Type: Research project
Reference: TEC2015-63884-C2-1-P
Funding Body: Ministerio de Economía y Competitividad
Start date: 01/01/2016
End date: 30/06/2020
Funding: 197.956,00 €
Abstract: The global goal of the COGNET project is to advance in the theoretical and technological development of event-based sensing and processing systems and demonstrate its potential to solve practical problems in a more efficient way than conventional technologies do. In particular, in the COGNET project we will address event-based vision and audition sensing, event-based vision and audition recognition systems and their off-line and on-line training, and the fusion of visual and auditive information to perform multisensory recognition tasks in real time. In COGNET, we are trying to demonstrate the superior performance of the event-based technology in two practical problems. The first one is binocular-based high-speed vehicle obstacle detection with few milliseconds response time, and the second one is visually guided speech recognition in a noisy environment.

NEURAM3
NEUral computing aRchitectures in Advanced Monolithic 3D-VLSI nano-technologies
PI: Teresa Serrano Gotarredona web
[+]
Type: Research project
Reference: 687299
Funding Body: European Union
Start date: 01/01/2016
End date: 30/06/2019
Funding: 483.220,00 €
Abstract: We propose to fabricate a chip implementing a neuromorphic architecture that supports state-of-the-art machine learning algorithms and spike-based learning mechanisms. With respect to its physical architecture this chip will feature an ultra low power, scalable and highly configurable neural architecture that will deliver a gain of a factor 50x in power consumption on selected applications compared to conventional digital solutions; and a monolithically integrated 3D technology in Fully-Depleted Silicon on Insulator (FDSOI) at 28nm design rules with integrated Resistive Random Access Memory (RRAM) synaptic elements;
We will complete this vision and develop complementary technologies that will allow to address the full spectrum of applications from mobile/autonomous objects to high performance computing coprocessing, by realising (1) a technology to implement on-chip learning, using native adaptive characteristics of electronic synaptic elements; and (2) a scalable platform to interconnect multiple neuromorphic processor chips to build large neural processing systems. The neuromorphic computing system will be developed jointly with advanced neural algorithms and computational architectures for online adaptation, learning, and high throughput on-line signal processing, delivering:
1. An ultra-low power massively parallel non von Neumann computing platform with non-volatile nano-scale devices that support on-line learning mechanisms.
2. A programming toolbox of algorithms and data structures tailored to the specific constraints and opportunities of the physical architecture.
3. An array of fundamental application demonstrations instantiating the basic classes of signal processing tasks.
The neural chip will validate the concept and be a first step to develop a European technology platform addressing from ultra-low power data processing in autonomous systems (Internet of Things) to energy efficient large data processing in servers and networks.