Pasar al contenido principal

COGNICION NANO-MEMRISTIVA NEUROMORFICA (NANO-MEM)

PID2019-105556GB-C31

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Neuromorphic Low-power Inference on Memristive Crossbars with On-chip Offset Calibration

  • Rosa, José M. de la
  • Charanraj Mohan
  • Camuñas-Mesa, Luis A.
  • Vianello, Elisa
  • Serrano-Gotarredona, Teresa
  • Linares-Barranco, Bernabé
Monolithic integration of silicon with nano-sized Redox-based resistive Random-Access Memory (ReRAM) devices opened the door to the creation of dense synaptic connections for bio-inspired neuromorphic circuits. One drawback of OxRAM based neuromorphic systems is the relatively low ON resistance of OxRAM synapses (in the range of just a few kilo-ohms). This requires relatively large currents (many micro amperes per synapse), and therefore imposes strong driving capability demands on peripheral circuitry, limiting scalability and low power operation. After learning, however, a read inference can be made low-power by applying very small amplitude read pulses, which require much smaller driving currents per synapse. Here we propose and experimentally demonstrate a technique to reduce the amplitude of read inference pulses in monolithic neuromorphic CMOS OxRAM-synaptic crossbar systems. Unfortunately, applying tiny read pulses is non-trivial due to the presence of random DC offset voltages. To overcome this, we propose finely calibrating DC offset voltages using a bulk-based three-stage on-chip calibration technique. In this work, we demonstrate spiking pattern recognition using STDP learning on a small 4x4 proof-of-concept memristive crossbar, where on-chip offset calibration is implemented and inference pulse amplitude could be made as small as 2mV. A chip with pre-synaptic calibrated input neuron drivers and a 4x4 1T1R synapse crossbar was designed and fabricated in the CEA-LETI MAD200 technology, which uses monolithic integration of OxRAMs above ST130nm CMOS. Custom-made PCBs hosting the post- synaptic circuits and control FPGAs were used to test the chip in different experiments, including synapse characterization, template matching, and pattern recognition using STDP learning, and to demonstrate the use of on-chip offset-calibrated low-power amplifiers. According to our experiments, the minimum possible inference pulse amplitude is limited by offset voltage drifts and noise. We conclude the paper with some suggestions for future work in this direction.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A CMOL-Like Memristor-CMOS Neuromorphic Chip-Core Demonstrating Stochastic Binary STDP

  • Camuñas-Mesa, Luis A.
  • Vianello, Elisa
  • Reita, Carlo
  • Serrano-Gotarredona, Teresa
  • Linares-Barranco, Bernabé
The advent of nanoscale memristors raised hopes of being able to build CMOL (CMOS/nanowire/molecular) type ultra-dense in-memory-computing circuit architectures. In CMOL, nanoscale memristors would be fabricated at the intersection of nanowires. The CMOL concept can be exploited in neuromorphic hardware by fabricating lower density neurons on CMOS and placing massive analog synaptic connectivity with nanowire and nanoscale-memristor fabric post-fabricated on top. However, technical problems have hindered such developments for presently available reliable commercial monolithic CMOS-memristor technologies. On one hand, each memristor needs a MOS selector transistor in series to guarantee forming and programming operations in large arrays. This results in compound MOS-memristor synapses (called 1T1R) which are no longer synapses at the crossing of nanowires. On the other hand, memristors do not yet constitute highly reliable, stable analog memories for massive analog-weight synapses with gradual learning. Here we demonstrate a pseudo-CMOL monolithic chip core that circumvents the two technical problems mentioned above by: (a) exploiting a CMOL-like geometrical chip layout technique to improve density despite the 1T1R limitation, and (b) exploiting a binary weight stochastic Spike-Timing-Dependent-Plasticity (STDP) learning rule that takes advantage of the more reliable binary memory capability of the memristors used. Experimental results are provided for a spiking neural network (SNN) CMOL-core with 64 input neurons, 64 output neurons and 4096 1T1R synapses, fabricated in 130nm CMOS with 200nm-sized Ti/HfOx/TiN memristors on top. The CMOL-core uses query-driven event read-out, which allows for memristor variability insensitive computations. Experimental system-level demonstrations are provided for plain template matching tasks, as well as regularized stochastic binary STDP feature-extraction learning, obtaining perfect recognition in hardware for a 4-letter recognition experiment., This work was supported in part by EU H2020 under Grant 687299 “NeuRAM3” and Grant 871371 “MeM-Scales;” and in part by the Spain’s Ministry of Science and Innovation, with support from the European Regional Development Fund, under Grant PID2019-105556GB-C31 (NANOMIND). The work of Luis A. Camuñas-Mesa was supported by the VI PPIT through the Universidad de Sevilla., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A CMOS-memristor hybrid system for implementing stochastic binary spike timing-dependent plasticity

  • Ahmadi-Farsani, Javad
  • Ricci, Saverio
  • Hashemkhani, Shahin
  • Ielmini, Daniele
  • Linares-Barranco, Bernabé
  • Serrano-Gotarredona, Teresa
This article is part of the theme issue ‘Advanced neurotechnologies: translating innovation for health and well-being’., This paper describes a fully experimental hybrid system in which a 4×4 memristive crossbar spiking neural network (SNN) was assembled using custom high-resistance state memristors with analogue CMOS neurons fabricated in 180 nm CMOS technology. The custom memristors used NMOS selector transistors, made available on a second 180 nm CMOS chip. One drawback is that memristors operate with currents in the micro-amperes range, while analogue CMOS neurons may need to operate with currents in the pico-amperes range. One possible solution was to use a compact circuit to scale the memristor-domain currents down to the analogue CMOS neuron domain currents by at least 5–6 orders of magnitude. Here, we proposed using an on-chip compact current splitter circuit based on MOS ladders to aggressively attenuate the currents by over 5 orders of magnitude. This circuit was added before each neuron. This paper describes the proper experimental operation of an SNN circuit using a 4×4 1T1R synaptic crossbar together with four post-synaptic CMOS circuits, each with a 5-decade current attenuator and an integrate-and-fire neuron. It also demonstrates one-shot winner-takes-all training and stochastic binary spike-timing-dependent-plasticity learning using this small system., This work was funded by EU H2020 grant nos. 824164 HERMES and 871371 MEM-SCALES, and by Spanish grants from the Ministry of Economy and Competitivity TEC2015- 63884-C2-1-P (COGNET) and PID2019-105556GB-C31 (NANOMIND) (with support from the European Regional Development Fund)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A neuromorphic CMOS circuit with self-repairing capability

  • Rahiminejad, Ehsan
  • Azad, Fatemez
  • Parvizi-Fard, Adel
  • Amiri, Mahmood
  • Linares-Barranco, Bernabé
Neurophysiological observations confirm that the brain not only is able to detect the impaired synapses (in brain damage) but also it is relatively capable of repairing faulty synapses. It has been shown that retrograde signaling by astrocytes leads to the modulation of synaptic transmission and thus bidirectional collaboration of astrocyte with nearby neurons is an important aspect of self-repairing mechanism. Specifically, the retrograde signaling via astrocyte can increase the transmission probability of the healthy synapses linked to the neuron. Motivated by these findings, in the present research, a CMOS neuromorphic circuit with self-repairing capabilities is proposed based on astrocyte signaling. In this way, the computational model of self-repairing process is hired as a basis for designing a novel analog integrated circuit in the 180-nm CMOS technology. It is illustrated that the proposed analog circuit is able to successfully recompense the damaged synapses by appropriately modifying the voltage signals of the remaining healthy synapses in the wide range of frequency. The proposed circuit occupies 7500- μm2 silicon area and its power consumption is about 65.4 μW . This neuromorphic fault-tolerant circuit can be considered as a key candidate for future silicon neuronal systems and implementation of neurorobotic and neuro-inspired circuits., 10.13039/501100004837-Ministerio de Ciencia e Innovación (Grant Number: PID2019-105556GB-C31). 10.13039/501100005317-Kermanshah University of Medical Sciences, Kermanshah, Iran, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Liquid state machine on SpiNNaker for spatio-temporal classification tasks

  • Patiño-Saucedo, Alberto
  • Rostro-Gonzalez, Horacio
  • Serrano-Gotarredona, Teresa
  • Linares-Barranco, Bernabé
Liquid State Machines (LSMs) are computing reservoirs composed of recurrently connected Spiking Neural Networks which have attracted research interest for their modeling capacity of biological structures and as promising pattern recognition tools suitable for their implementation in neuromorphic processors, benefited from the modest use of computing resources in their training process. However, it has been difficult to optimize LSMs for solving complex tasks such as event-based computer vision and few implementations in large-scale neuromorphic processors have been attempted. In this work, we show that offline-trained LSMs implemented in the SpiNNaker neuromorphic processor are able to classify visual events, achieving state-of-the-art performance in the event-based N-MNIST dataset. The training of the readout layer is performed using a recent adaptation of back-propagation-through-time (BPTT) for SNNs, while the internal weights of the reservoir are kept static. Results show that mapping our LSM from a Deep Learning framework to SpiNNaker does not affect the performance of the classification task. Additionally, we show that weight quantization, which substantially reduces the memory footprint of the LSM, has a small impact on its performance., This work was supported by EU H2020 grant 871371 (MeM-Scales), by Spanish grant from the Ministry of Science and Innovation PID2019-105556GB-C31 (NANOMIND) with support from the European Regional Development Fund), and by CONACYT scholarship number 688116/578600., We also acknowledge support of the publication fee by the CSIC Open Access Publication Support Initiative through its Unit of Information Resources for Research (URICI)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

SL-Animals-DVS: event-driven sign language animals dataset

  • Vasudevan, Ajay
  • Negri, Pablo
  • Di Ielsi, Camila
  • Linares-Barranco, Bernabé
  • Serrano-Gotarredona, Teresa
Non-intrusive visual-based applications supporting the communication of people employing sign language for communication are always an open and attractive research field for the human action recognition community. Automatic sign language interpretation is a complex visual recognition task where motion across time distinguishes the sign being performed. In recent years, the development of robust and successful deep-learning techniques has been accompanied by the creation of a large number of databases. The availability of challenging datasets of Sign Language (SL) terms and phrases helps to push the research to develop new algorithms and methods to tackle their automatic recognition. This paper presents ‘SL-Animals-DVS’, an event-based action dataset captured by a Dynamic Vision Sensor (DVS). The DVS records non-fluent signers performing a small set of isolated words derived from SL signs of various animals as a continuous spike flow at very low latency. This is especially suited for SL signs which are usually made at very high speeds. We benchmark the recognition performance on this data using three state-of-the-art Spiking Neural Networks (SNN) recognition systems. SNNs are naturally compatible to make use of the temporal information that is provided by the DVS where the information is encoded in the spike times. The dataset has about 1100 samples of 59 subjects performing 19 sign language signs in isolation at different scenarios, providing a challenging evaluation platform for this emerging technology., This work was funded by EU H2020 grants 824164 “HERMES”, 871371 “Memscales” and 871501 “NeuroNN”, Spanish grant from the Ministry of Economy and Competitivity NANOMIND-PID2019-105556GB-C31, with support from the European Regional Development Fund. P. Negri was partially supported by the Scholarship Program Mobility of the Postgraduate Iberoamerican University Association (AUIP). C. Di Ielsi was supported by a scholarship of the Computer Department of the University of Buenos Aires. A. Vasudevan was supported by the MINECO FPI scholarship BES-2016-077757., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Effect of device mismatches in differential oscillatory neural networks

  • Shamsi, Jafar
  • Avedillo, María J.
  • Linares-Barranco, Bernabé
  • Serrano-Gotarredona, Teresa
Analog implementation of Oscillatory Neural Networks (ONNs) has the potential to implement fast and ultra-low-power computing capabilities. One of the drawbacks of analog implementation is component mismatches which cause desynchronization and instability in ONNs. Emerging devices like memristors and VO2are particularly prone to variations. In this paper, we study the effect of component mismatches on the performance of differential ONNs (DONNs). Mismatches were considered in two main blocks: differential oscillatory neurons and synaptic circuits. To measure DONN tolerance to mismatches in each block, performance was evaluated with mismatches being present separately in each block. Memristor-bridge circuits with four memristors were used as the synaptic circuits. The differential oscillatory neurons were based on VO2-devices. The simulation results showed that DONN performance was more vulnerable to mismatches in the components of the differential oscillatory neurons than to mismatches in the synaptic circuits. DONNs were found to tolerate up to 20% mismatches in the memristance of the synaptic circuits. However, mismatches in the differential oscillatory neurons resulted in non-uniformity of the natural frequencies, causing desynchronization and instability. Simulations showed that 0.5% relative standard deviation (RSD) in natural frequencies can reduce DONN performance dramatically. In addition, sensitivity analyses showed that the high threshold voltage of VO2-devices is the most sensitive parameter for frequency non-uniformity and desynchronization., This work was supported in part by EU H2020 “NeurONN” under Grant 871501 and in part by the Spanish Ministry of Economy and Competitivity (NANOMIND) (with support from the European Regional Development Fund) under Grant PID2019-105556GB-C31., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A Fully Digital Relaxation-Aware Analog Programming Technique for HfOx RRAM Arrays

  • Erfanijazi, Hamidreza
  • Camuñas-Mesa, Luis A.
  • Vianello, Elisa
  • Serrano-Gotarredona, Teresa
  • Linares-Barranco, Bernabé
For neuromorphic engineering to emulate the human brain, improving memory density with low power consumption is an indispensable but challenging goal. In this regard, emerging RRAMs have attracted considerable interest for their unique qualities like low power consumption, high integration potential, durability, and CMOS compatibility. Using RRAMs to imitate the more analog storage behavior of brain synapses is also a promising strategy for further improving memory density and power efficiency. However, RRAM devices display strong stochastic behavior, together with relaxation effects, making it more challenging to precisely control their multi-level storage capability. To address this, researchers have reported different multi-level programming strategies, mostly involving the precise control of analog parameters like compliance current during write operations and/or programming voltage amplitudes. Here, we present a new fully digital relaxation-aware method for tuning the conductance of analog RRAMs. The method is based on modulating digital pulse widths during erase operations while keeping other parameters fixed, and therefore requires no precise alterations to analog parameters like compliance currents or programming voltage amplitudes. Experimental results, with and without relaxation effect awareness, on a 64 RRAM 1T1R HfOx memory array of cells, fabricated in 130nm CMOS technology, indicate that it is possible to obtain 2-bit memory per cell multi-value storage at the array level, verified 1000 seconds after programming., This work was partly funded by EU grants 871501, 824164, 899559, 101070908, and National grant PID2019-105556GB-C31 (with support from the European Regional Development Fund)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

A Fully Digital Relaxation-Aware Analog Programming Technique for HfOx RRAM Arrays

  • Erfanijazi, Hamidreza
  • Camuñas-Mesa, Luis A.
  • Vianello, Elisa
  • Serrano-Gotarredona, Teresa
  • Linares-Barranco, Bernabé
For neuromorphic engineering to emulate the human brain, improving memory density with low power consumption is an indispensable but challenging goal. In this regard, emerging RRAMs have attracted considerable interest for their unique qualities like low power consumption, high integration potential, durability, and CMOS compatibility. Using RRAMs to imitate the more analog storage behavior of brain synapses is also a promising strategy for further improving memory density and power efficiency. However, RRAM devices display strong stochastic behavior, together with relaxation effects, making it more challenging to precisely control their multi-level storage capability. To address this, researchers have reported different multi-level programming strategies, mostly involving the precise control of analog parameters like compliance current during write operations and/or programming voltage amplitudes. Here, we present a new fully digital relaxation-aware method for tuning the conductance of analog RRAMs. The method is based on modulating digital pulse widths during erase operations while keeping other parameters fixed, and therefore requires no precise alterations to analog parameters like compliance currents or programming voltage amplitudes. Experimental results, with and without relaxation effect awareness, on a 64 RRAM 1T1R HfOx memory array of cells, fabricated in 130nm CMOS technology, indicate that it is possible to obtain 2-bit memory per cell multi-value storage at the array level, verified 1000 seconds after programming., This work was partly funded by EU grants 871501, 824164, 899559, 101070908, and National grant PID2019-105556GB-C31 (with support from the European Regional Development Fund)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A 128×128 Electronically Multi-Foveated Dynamic Vision Sensor With Real-Time Resolution Reconfiguration

  • Faramarzi, Farnaz
  • Linares-Barranco, Bernabé
  • Serrano-Gotarredona, Teresa
This paper presents the design and implementation of a 128× 128 electronically foveated dynamic vision sensor (EF-DVS) fabricated using 350 nm CMOS technology. The EF-DVS integrates a novel pixel grouping approach that permits real-time dynamic resolution adjustments via external digital signals. Previous approaches rely on physically crafting high- and low-resolution regions, which require a mechanical setup for tracking moving objects within the fovea. Here, our innovation supports flexible and fast operation modes, acting on amplified photocurrents, allowing the sensor to operate in both high-resolution and low-resolution settings, and to configure multiple high-resolution regions of interest (ROIs) with arbitrary shapes and sizes within the pixel array in real-time. Although the pixel circuitry is more complex than its un-foveated predecessor, we have kept the same pixel area, sacrificing slightly fixed pattern noise (FPN). The sensor achieves a latency of 3.66μs and demonstrates a contrast sensitivity down to 1.03%. It maintains a dynamic range exceeding 120 dB and an intra-scene dynamic range above 60 dB. Notably, the power consumption is reduced with respect to its predecessor, down to 0.7 mW at 100 Keps when configured in low-resolution mode with a 2× 2 pixel grouping. The ability to dynamically adjust spatial resolution reduces noise event rates, enhances sensitivity, and lowers both data bandwidth and processing requirements. These features make the EF-DVS a suitable candidate for applications in robotics, surveillance, and real-time monitoring systems where efficient data processing and low latency are critical., This work was supported in part by EU CHIST-ERA Grants APROVIS3D under Project PCI2019-111826-2; in part by EU HE NIMBLEAI under Grant 101070679; in part by the Andalusian Regional Grant BIOVEO under Project PROYEXCEL_00060; in part by Spanish Grants from the Ministry of Science, Innovation and Universities MULTI-SENS under Grant PDC2023-145841-C31; and in part by the NANOMIND through European Regional Development Fund under Grant PID2019-105556GB-C31. The work of Farnaz Faramarzi was supported by the FPI Scholarship from the Spanish Ministry of Science, Innovation, and Universities., Peer reviewed