Ultra low power analog design and technology for artificial neurons

Danneville, F.; Sourikopoulos, Ilias; Hedayat, Sara; Loyez, Christophe; Hoel, Virginie; Cappy, A.

doi:10.1109/bctm.2017.8112899

Cited by 8 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sourikopoulos et al have first demonstrated the fast-spiking behavior of biomimetic neuron with relatively constant period in [18]. Later, Sourikopoulos et al have demonstrated the stochastic resonance behavior of such a neuron [30]. According to [14], both characteristics are presented only for FS neurons, and thus Sourikopoulos' work was named as FS eNeuron in [13].…”

Section: Fs Eneuron Analysismentioning

confidence: 99%

“…The silicon area is dominated by the total capacitance value, depending on the capacitance density in the technology node (i.e. 0:2 fF=lm 2 ) [30]. The 55 nm technology node, used in this paper, is only a shrink down node of 65 nm technology using a 0.9 optical-lens reduction factor with similar capacitance density.…”

Section: Nasp Physical Designmentioning

confidence: 99%

“…The 55 nm technology node, used in this paper, is only a shrink down node of 65 nm technology using a 0.9 optical-lens reduction factor with similar capacitance density. In previous paper [13], eNeuron physical design only considers metal-insulator-metal (MIM) capacitors as proposed in [30]. In this paper, a varicap-based version is also considered for silicon area minimization, while the capacitance value (C m ; C K ; C K 0 ) is kept unchanged.…”

Section: Nasp Physical Designmentioning

confidence: 99%

See 2 more Smart Citations

Neuromorphic analog spiking-modulator for audio signal processing

Ferreira

Nebhen

Klisnick

et al. 2020

Analog Integr Circ Sig Process

View full text Add to dashboard Cite

While CMOS scaling is currently reaching its limits in power dissipation and circuit density, the analogy between biology and silicon is emerging as a solution to ultra-low-power signal processing. Urgent applications involving artificial vision and audition, including intelligent sensing, appeal original energy efficient and ultra-miniaturized silicon-based solutions. While state-of-the-art is focusing on digital-oriented solutions, this paper proposes a neuromorphic analog signal processor using Izhikevich-based artificial neurons in an analog spiking modulator. A varicap-based artificial neuron is explored reducing the silicon area to 98:6 lm 2 and the substrate leakage to a 1:95 fJ=spike efficiency. Post-layout simulation results are presented to investigate the high-resolution, high-speed, and full-scale dynamic range for audio signal processing applications. The proposal demonstrates a 9 bits spiking-modulator resolution, a maximum of 8 fJ=conv efficiency, and a root-mean-square error of 0:63 mV RMS .

show abstract

Section: Fs Eneuron Analysismentioning

confidence: 99%

Section: Nasp Physical Designmentioning

confidence: 99%

Section: Nasp Physical Designmentioning

confidence: 99%

See 1 more Smart Citation

Neuromorphic analog spiking-modulator for audio signal processing

Ferreira

Nebhen

Klisnick

et al. 2020

Analog Integr Circ Sig Process

View full text Add to dashboard Cite

show abstract

“…Sourikopoulos et al have first demonstrated the fast spiking beof biomimetic neuron with relatively constant period in [12]. Later, I. Sourikopoulos et al have demonstrated the stochastic resonance behavior of such a neuron [2]. This phenomenon is observed under a decreased I ex (below a certain critical value), where the neuron fires irregular spikes, switching randomly between resting and spiking states.…”

Section: Fs E-neuron Analysismentioning

confidence: 99%

Energy efficient fJ/spike LTS e-Neuron using 55-nm node

Ferreira

Carvalho

Klisnick

et al. 2019

Proceedings of the 32nd Symposium on Integrated Circuits and Systems Design

View full text Add to dashboard Cite

While CMOS technology is currently reaching its limits in power consumption and circuit density, a challenger is emerging from the analogy between biology and silicon. Hardware-based neural networks may drive a new generation of bio-inspired computers by the urge of a hardware solution for real-time applications. This paper redesigns a previous proposed electronic neuron (e-Neuron) in a higher firing rate to reduce the silicon area and highlight a better energy efficiency trade-off. Besides, an innovative schematic is proposed to state an e-Neuron library based on Izhikevichs model of neural firing patterns. Both e-Neuron circuits are designed using 55 nm technology node. Physical design of transistors in weak inversion are discussed to a minimal leakage. Neural firing pattern behaviors are validated by post-layout simulations, demonstrating the spike frequency adaptation and the rebound spikes due to postinhibitory effect in LTS e-Neuron. Presented results suggest that the time to rebound spikes is dependent of the excitation current amplitude. Both e-Neurons have presented a fF/spike energy efficiency and a smaller silicon area in comparison to Izhikevichs library propositions in the literature. CCS CONCEPTS• Hardware → Analog and mixed-signal circuit synthesis; Standard cell libraries; Emerging architectures.

show abstract

“…5c correspond to "tonic spiking", but biology features a variety of spike waveforms. For instance, in order to emulate a "bursting mode" with the synapses prior described, a basic neural circuit is to associate using a close loop a "fast" excitatory neuron connected to a "slow" inhibitory neuron; it turns out that when the "fast" excitatory neuron is excited by a current step, the "bursting" mode can be emulated [6].…”

Section: A Basic Synapsesmentioning

confidence: 99%

Sub-0.3V CMOS neuromorphic technology and its potential application

Danneville

Carpentier

Sourikopoulos

et al. 2021

2021 International Conference on Content-Based Multimedia Indexing (CBMI)

Self Cite

View full text Add to dashboard Cite

The aim of this paper is to present a sub-0.3 V neuromorphic technology developed for spiking neural network design and its potential application. The main properties of the developed ultra low power (ULP) artificial neuron are first recalled. A description of ULP synapses follows that includes the plasticity scheme. The neuromorphic toolbox is then used to design a basic circuit allowing oriented edges classification. The circuit is made of 40 neurons and 108 plastic synapses, its consumed silicon core area is 0.025 mm 2 and the overall power consumption of 5 nW. Finally, the deployment of the technology within an industrial context to fabricate highly energy efficient Spike-based visual sensor is discussed.

show abstract

Ultra low power analog design and technology for artificial neurons

Cited by 8 publications

References 19 publications

Neuromorphic analog spiking-modulator for audio signal processing

Neuromorphic analog spiking-modulator for audio signal processing

Energy efficient fJ/spike LTS e-Neuron using 55-nm node

Sub-0.3V CMOS neuromorphic technology and its potential application

Contact Info

Product

Resources

About