The recently developed Dynamic Vision Sensors (DVS) sense dynamic visual information asynchronously and code it into trains of events with sub-micro second temporal resolution. This high temporal precision makes the output of these sensors especially suited for dynamic 3D visual reconstruction, by matching corresponding events generated by two different sensors in a stereo setup. This paper explores the use of Gabor filters to extract information about the orientation of the object edges that produce the events, applying the matching algorithm to the events generated by the Gabor filters and not to those produced by the DVS. This strategy provides more reliably matched pairs of events, improving the final 3D reconstruction. ; European Union PRI-PIMCHI-2011-0768 ; Ministerio de Economía y Competitividad TEC2009-10639-C04-01 ; Ministerio de Economía y Competitividad TEC2012-37868-C04-01 ; Junta de Andalucía TIC-6091
Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network ; European Union 644096, 687299 ; Gobierno de España TEC2016-77785- P, TEC2015-63884-C2-1-P ; Junta de Andalucía TIC-6091, TICP1200
This paper describes a convolution chip for event-driven vision sensing and processing systems. As opposed to conventional frame-constraint vision systems, in event-driven vision there is no need for frames. In frame-free event-based vision, information is represented by a continuous flow of self-timed asynchronous events. Such events can be processed on the fly by event-based convolution chips, providing at their output a continuous event flow representing the 2-D filtered version of the input flow. In this paper we present a 32 × 32 pixel 2-D convolution event processor whose kernel can have arbitrary shape and size up to 32 × 32. Arrays of such chips can be assembled to process larger pixel arrays. Event latency between input and output event flows can be as low as 155 ns. Input event throughput can reach 20 Meps (mega events per second), and output peak event rate can reach 45 Meps. The chip can be configured to discriminate between two simulated propeller-like shapes rotating simultaneously in the field of view at a speed as high as 9400 rps (revolutions per second). Achieving this with a frame-constraint system would require a sensing and processing capability of about 100 K frames per second. The prototype chip has been built in 0.35 CMOS technology, occupies 4.3 × 5.4 and consumes a peak power of 200 mW at maximum kernel size at maximum input event rate. ; European Union 216777 ; Gobierno de España TEC2006-11730-C03-01, TEC2009-10639-C04-01 ; Junta de Andalucía P06TIC01417
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 nely 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 4 4 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 4 4 1T1R synapse crossbarwas 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 ampli ers. 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. ; International Consortium of Nanotechnologies (ICON) Grant G0086 ; European Union H2020 grant 824164 (HERMES) ; European Union H2020 grant 871371 (MeM-Scales) ; European Union H2020 grant 871501 (NeurONN) ; European Union H2020 grant 899559 (SpinAge) ; European Union H2020 grant PCI2019-111826-2 (APPROVIS3D) ; Spanish Ministry of Science and Innovation Grant PID2019-105556GB-C31 (NANOMIND) ; Spanish Ministry of Science and Innovation / FEDER Grant PID2019-103876RB-I00 (CORDION) ; Junta de Andalucía (Spain) Grant US-1260118 (Neuro-Radio) ; Universidad de Sevilla ( Spain) VI PPIT
In this paper we present a very exciting overlap between emergent nanotechnology and neuroscience, which has been discovered by neuromorphic engineers. Specifically, we are linking one type of memristor nanotechnology devices to the biological synaptic update rule known as spike-time-dependent-plasticity (STDP) found in real biological synapses. Understanding this link allows neuromorphic engineers to develop circuit architectures that use this type of memristors to artificially emulate parts of the visual cortex. We focus on the type of memristors referred to as voltage or flux driven memristors and focus our discussions on a behavioral macro-model for such devices. The implementations result in fully asynchronous architectures with neurons sending their action potentials not only forward but also backward. One critical aspect is to use neurons that generate spikes of specific shapes. We will see how by changing the shapes of the neuron action potential spikes we can tune and manipulate the STDP learning rules for both excitatory and inhibitory synapses. We will see how neurons and memristors can be interconnected to achieve large scale spiking learning systems, that follow a type of multiplicative STDP learning rule. We will briefly extend the architectures to use three-terminal transistors with similar memristive behavior. We will illustrate how a V1 visual cortex layer can assembled and how it is capable of learning to extract orientations from visual data coming from a real artificialCMOS spiking retina observing real life scenes. Finally, we will discuss limitations of currently available memristors. The results presented are based on behavioral simulations and do not take into account non-idealities of devices and interconnects. The aim of this paper is to present, in a tutorial manner, an initial framework for the possible development of fully asynchronous STDP learning neuromorphic architectures exploiting two or three-terminal memristive type devices. All files used for the simulations are made available through the journal web site. ; European Union 216777 ; Gobierno de España TEC2006-11730-C03-01, TEC2009-10639-C04-01 ; Junta de Andalucía P06TIC01417
Address-event representation (AER) is an emergent hardware technology which shows a high potential for providing in the near future a solid technological substrate for emulating brain-like processing structures. When used for vision, AER sensors and processors are not restricted to capturing and processing still image frames, as in commercial frame-based video technology, but sense and process visual information in a pixel-level event-based frameless manner. As a result, vision processing is practically simultaneous to vision sensing, since there is no need to wait for sensing full frames. Also, only meaningful information is sensed, communicated, and processed. Of special interest for brain-like vision processing are some already reported AER convolutional chips, which have revealed a very high computational throughput as well as the possibility of assembling large convolutional neural networks in a modular fashion. It is expected that in a near future we may witness the appearance of large scale convolutional neural networks with hundreds or thousands of individual modules. In the meantime, some research is needed to investigate how to assemble and configure such large scale convolutional networks for specific applications. In this paper, we analyze AER spiking convolutional neural networks for texture recognition hardware applications. Based on the performance figures of already available individual AER convolution chips, we emulate large scale networks using a custom made event-based behavioral simulator. We have developed a new event-based processing architecture that emulates with AER hardware Manjunath's frame-based feature recognition software algorithm, and have analyzed its performance using our behavioral simulator. Recognition rate performance is not degraded. However, regarding speed, we show that recognition can be achieved before an equivalent frame is fully sensed and transmitted. ; Ministerio de Educación y Ciencia TEC-2006-11730-C03-01 ; Junta de Andalucía P06-TIC-01417 ; European Union IST-2001-34124, 216777
This paper describes CAVIAR, a massively parallel hardware implementation of a spike-based sensing-processing-learning-actuating system inspired by the physiology of the nervous system. CAVIAR uses the asychronous address-event representation (AER) communication framework and was developed in the context of a European Union funded project. It has four custom mixed-signal AER chips, five custom digital AER interface components, 45k neurons (spiking cells), up to 5M synapses, performs 12G synaptic operations per second, and achieves millisecond object recognition and tracking latencies. ; European Commission IST-2001-34124