An official website of the United States government
Analog neuromorphic computing systems emulate the parallelism and connectivity of the human brain, promising greater expressivity and energy efficiency compared to those of digital systems. Though many devices have emerged as candidates for artificial neurons and artificial synapses, there have been few device candidates for artificial dendrites. In this work, we report on biocompatible graphene-based artificial dendrites (GrADs) that can implement dendritic processing. By using a dual side-gate configuration, current applied through a Nafion membrane can be used to control device conductance across a trilayer graphene channel, showing spatiotemporal responses of leaky recurrent, alpha, and Gaussian dendritic potentials. The devices can be variably connected to enable higher-order neuronal responses, and we show through data-driven spiking neural network simulations that spiking activity is reduced by ≤15% without accuracy loss while low-frequency operation is stabilized. This positions the GrADs as strong candidates for energy efficient bio-interfaced spiking neural networks.
more »
« less
Hybrid spin-CMOS stochastic spiking neuron for high-speed emulation of In vivo neuron dynamics
The spintronic stochastic spiking neuron (S3N) developed herein realizes biologically mimetic stochastic spiking characteristics observed within in vivo cortical neurons, while operating several orders of magnitude more rapidly and exhibiting a favorable energy profile. This work leverages a novel probabilistic spintronic switching element device that provides thermally-driven and current-controlled tunable stochasticity in a compact, low-energy, and high-speed package. Simulation program with integrated circuit emphasis (SPICE) simulation results indicate that the equivalent of 1 second of in vivo neuronal spiking characteristics can be generated on the order of nanoseconds, enabling the feasibility of extremely rapid emulation of in vivo neuronal behaviors for future statistical models of cortical information processing. Their results also indicate that the S3N can generate spikes on the order of ten picoseconds while dissipating only 0.6–9.6 μW, depending on the spiking rate. Additionally, they demonstrate that an S3N can implement perceptron functionality, such as AND-gate- and OR-gate-based logic processing, and provide future extensions of the work to more advanced stochastic neuromorphic architectures.
more »
« less
- Award ID(s):
- 1739635
- PAR ID:
- 10057855
- Date Published:
- Journal Name:
- IET Computers & Digital Techniques
- ISSN:
- 1751-8601
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
State-of-the-art machine learning models have achieved impressive feats of narrow intelligence, but have yet to realize the computational generality, adaptability, and power efficiency of biological brains. Thus, this work aims to improve current neural network models by leveraging the principle that the cortex consists of noisy and imprecise components in order to realize an ultra-low-power stochastic spiking neural circuit that resembles biological neuronal behavior. By utilizing probabilistic spintronics to provide true stochasticity in a compact CMOS-compatible device, an Adaptive Ring Oscillator for as-needed discrete sampling, and a homeostasis mechanism to reduce power consumption, provide additional biological characteristics, and improve process variation resilience, this subthreshold circuit is able to generate sub-nanosecond spiking behavior with biological characteristics at 200mV, using less than 80nW, along with behavioral robustness to process variation.more » « less
-
Cortical neurons are characterized by their variable spiking patterns. Here, we examine the specific hypothesis that cortical synchrony drives spiking variability in vivo. Using dynamic clamps, we demonstrate that intrinsic neuronal properties do not contribute substantially to spiking variability, but rather spiking variability emerges from weakly synchronous network drive. With large-scale electrophysiology, we quantify the degree of synchrony and its timescale in cortical networks in vivo. The timescale of synchrony shifts in a range from 25 to 200 ms, depending on the presence of external sensory input. In particular, when the network moves from spontaneous to driven modes, the synchrony timescales shift from slow to fast, leading to a natural reduction in response variability across cortical areas. Finally, while an individual neuron exhibits reliable responses to physiological drive, different neurons respond in a distinct fashion according to their intrinsic properties, contributing to stable synchrony across the neural network.more » « less
-
Promising for digital signal processing applications, approximate computing has been extensively considered to tradeoff limited accuracy for improvements in other circuit metrics such as area, power, and performance. In this paper, approximate arithmetic circuits are proposed by using emerging nanoscale spintronic devices. Leveraging the intrinsic current-mode thresholding operation of spintronic devices, we initially present a hybrid spin-CMOS majority gate design based on a composite spintronic device structure consisting of a magnetic domain wall motion stripe and a magnetic tunnel junction. We further propose a compact and energy-efficient accuracy-configurable adder design based on the majority gate. Unlike most previous approximate circuit designs that hardwire a constant degree of approximation, this design is adaptive to the inherent resilience in various applications to different degrees of accuracy. Subsequently, we propose two new approximate compressors for utilization in fast multiplier designs. The device-circuit SPICE simulation shows 34.58% and 66% improvement in power consumption, respectively, for the accurate and approximate modes of the accuracy-configurable adder, compared to the recently reported domain wall motion-based full adder design. In addition, the proposed accuracy-configurable adder and approximate compressors can be efficiently utilized in the discrete cosine transform (DCT) as a widely-used digital image processing algorithm. The results indicate that the DCT and inverse DCT (IDCT) using the approximate multiplier achieve ~2x energy saving and 3x speed-up compared to an exactly-designed circuit, while achieving comparable quality in its output result.more » « less
-
Jolivet, Renaud Blaise (Ed.)Even when driven by the same stimulus, neuronal responses are well-known to exhibit a striking level of spiking variability. In-vivo electrophysiological recordings also reveal a surprisingly large degree of variability at the subthreshold level. In prior work, we considered biophysically relevant neuronal models to account for the observed magnitude of membrane voltage fluctuations. We found that accounting for these fluctuations requires weak but nonzero synchrony in the spiking activity, in amount that are consistent with experimentally measured spiking correlations. Here we investigate whether such synchrony can explain additional statistical features of the measured neural activity, including neuronal voltage covariability and voltage skewness. Addressing this question involves conducting a generalized moment analysis of conductance-based neurons in response to input drives modeled as correlated jump processes. Technically, we perform such an analysis using fixed-point techniques from queuing theory that are applicable in the stationary regime of activity. We found that weak but nonzero synchrony can consistently explain the experimentally reported voltage covariance and skewness. This confirms the role of synchrony as a primary driver of cortical variability and supports that physiological neural activity emerges as a population-level phenomenon, especially in the spontaneous regime.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1049/iet-cdt.2017.0145
