NeuroP Project (European Union)
Проект NeuroP (Европейский союз)
Neuromorphic processors: event-based VLSI models of cortical circuits for brain-inspired computation (FP7). Neuroinformatics researchers (Principal Investigator Dr. Giacomo Indiveri, Institute of Neuroinformatics) from the University of Zurich and ETH Zurich together with colleagues from the EU and USA have demonstrated how complex cognitive abilities can be incorporated into electronic systems made with “neuromorphic” chips. Image Source
Краткое описание проекта - Project Description
Хроника проекта - Project Timeline
Структура проекта - Project Research Areas
Участники проекта - Project Participants
Взаимосвязанные проекты - Related Projects
Ссылки на источники информации - References
Brains are remarkable computing devices which clearly outperform conventional architectures in real-world tasks. Computational neuroscience has made tremendous progress in uncovering the key principles by which neural systems carry out computation, and ICTs have advanced to a point where it is possible to integrate almost as many transistors in a VLSI system as neurons in a brain. Yet, we are still unable to develop artificial neural systems with basic computing abilities able to parallel even simple insect brains.
We have recently demonstrated how it is possible to implement large-scale artificial neural networks and real-time sensory motor systems in VLSI technology, exploiting the physics of silicon to reproduce the biophysics of neural systems. But the main bottleneck is in the understanding of how to use these systems to perform general purpose computation.
Progress in this domain can be achieved only by pursuing a fully integrated multi-disciplinary approach. We propose to combine neuroscience, mathematics, computer-science, and engineering to develop a theoretical formalism and its supporting technology for designing spike-based general purpose "neuromorphic processors", as distributed multi-chip neuromorphic VLSI systems, and for programming them to learn to produce desired computations autonomously. We will study the properties of neural circuits in the neocortex, model their coding strategies and spike-driven learning mechanisms using biophysically realistic spiking neural networks, and implement them using hybrid analogue digital VLSI circuits.
By interfacing these systems to silicon retinas, cochleas and autonomous robotic platforms we will build embodied neuromorphic processors able to carry out event-based computations in real-world behavioural tasks.
Neuromorphic Cognitive Systems
What is a neuromorphic cognitive system and what is neuromorphic cognition?
We don't have a comprehensive answer to these questions yet. But our work is aimed at bridging the gap from simple reactive neuromorphic sensory-motor systems to ones that are cognitive in quality: e.g. neuromorphic architectures that can reason about the actions to take, in response to the combinations of external stimuli, internal states, and behavioral objectives.
We focus on analog/digital VLSI architectures that use the physics of silicon to reproduce the biophysics of biological neural systems, and multi-chip systems that communicate using asynchronous event-based signals (spikes).
Our main contributions to neuromorphic VLSI technology consist of novel low-power silicon neuron circuits, dynamic silicon synapses, hybrid analog/digital spike-based learning mechanisms, soft Winner-take-all networks, and asynchronous digital communication circuits and systems.
2009. The NCS group was established in early 2009 at the Institute of Neuroinformatics to study and develop computational models, hybrid analog/digital VLSI circuits, and multi-chip event-based systems for implementing Neuromorphic Cognitive Systems.
2011-03-01 Начало проекта NeuroP.
2016-02-29 Окончание проекта NeuroP.
NeuroP Project. ERC FP7 Grant 257219 “Neuromorphic processors: event-based VLSI models of cortical circuits for brain-inspired computation” , 2011-2016.
From 2011-03-01 to 2016-02-29 | NEUROP website
Project reference: 257219 Status: Execution
Total cost: EUR 1 494 023 EU contribution: EUR 1 494 023
Programme acronym: FP7-IDEAS-ERC Subprogramme area: ERC-SG-PE7 Contract type: ERC Starting Grant
Основной проект: Neuromorphic Cognitive Systems
- Plasticity in NEUral Memristive Architectures
- Real neurons-nanoelectronics Architecture with Memristive Plasticity
- Spike-based computation and learning in distributed neuromorphic systems
- Towards new Brain-Machine Interfaces: state-dependent information coding
Neuromorphic Cognitive Systems group (NCS)
Institute of Neuroinformatics, Zurich, SCHWEIZ/SUISSE/SVIZZERA
University of Zurich / ETH Zurich
The NCS group was established in early 2009 at the Institute of Neuroinformatics to study and develop computational models, hybrid analog/digital VLSI circuits, and multi-chip event-based systems for implementing Neuromorphic Cognitive Systems.
Участник проекта: University of Zurich, Zurich, SCHWEIZ/SUISSE/SVIZZERA
Координатор проекта: Dr. Giacomo Indiveri
Узнать больше о проектах: http://erc.europa.eu/
RAMP. EU ICT FP7 Grant ICT-612058-RAMP “Real neurons-nanoelectronics Architecture with Memristive Plasticity” (STREP project, co-investigator; coordinator: S. Vassanelli, Univ. of Padova, Italy), 2013-2016, 298952 EUR
SpikeComp. Swiss National Science Foundation Grant #138798: “Spike-based computation and learning in distributed neuromorphic systems” (National research project, principal investigator), 2013-2016, 335800 CHF.
SI-CODE. EU ICT FP7 Grant ICT-284553-SI-CODE: “Towards new Brain-Machine Interfaces: state-dependent information coding” (STREP project, co-investigator; coordinator: S. Panzeri, Italian Institute of Technology, Italy), 2012-2015, 440574 EUR.
PNEUMA. Swiss National Science Foundation Grant #138798: “Plasticity in NEUral Memristive Architectures”, (ERA-Net CHIST-ERA call, co-investigator; coordinator: T. Prodromakis, Imperial College London, UK), 2011-2013, 310000 EUR.
CSN-II. EU ICT FP7 Grant ICT-601167-CSNII: “Convergent Science Network of Biomimetics and NeuroTechnology, (Coordination and Support Action, co-investigator; coordinator: P. Verschure, Universitat Pompeu Fabra), 2010-2013, 950000 EUR
- The 2013 CapoCaccia Cognitive Neuromorphic Engineering Workshop
- The Annual Telluride Workshop.
Azghadi, MR and Moradi, Saber and Indiveri, Giacomo Programmable Neuromorphic Circuits for Spike-Based Neural Dynamics, 11th IEEE International new Circuits and Systems, 2013
Moradi, Saber and Imam, Nabil and Manohar, Rajit and Indiveri, Giacomo A Memory-Efficient Routing Method for Large-Scale Spiking Neural Networks, 21st European Conference on Circuit Theory and Design 1-4, 2013
Moradi, Saber and Indiveri, Giacomo An event-based neural network architecture with asynchronous programmable synaptic memory, IEEE Transaction on Biomedical Circuits and Systems, 2013
Mostafa, H. and Corradi, F. and Osswald, M. and Indiveri, G. Automated synthesis of asynchronous event-based interfaces for neuromorphic systems, Circuit Theory and Design (ECCTD), 2013 European Conference on, 1-4, 2013
Neftci, Emre and Binas, Jonathan and Rutishauser, Ueli and Chicca, Elisabetta and Indiveri, Giacomo and Douglas, Rodney J. Synthesizing Cognition in Neuromorphic Electronic Systems, PNAS, 110:(37) E3468–E3476, 2013
(New PNAS paper on "Synthesizing cognition in neuromorphic electronic systems" Jul 23, 2013)
New chapter in book published. May 27, 2013
New article on neuromorphic memristors posted Mar 01, 2013
Neuro-Inspired Accelerators for Computing (NIAC) workshop slides Feb 28, 2013
ESSDERC 2012 tutorial slides Sep 21, 2012
Indiveri, G. and Horiuchi, T.K. Frontiers in neuromorphic engineering, Frontiers in Neuroscience, 5:, 2011