A biomimetic neural encoder for spiking neural network

Abstract

Spiking neural networks (SNNs) promise to bridge the gap between artificial neural networks (ANNs) and biological neural networks (BNNs) by exploiting biologically plausible neurons that offer faster inference, lower energy expenditure, and event-driven information processing capabilities. However, implementation of SNNs in future neuromorphic hardware requires hardware encoders analogous to the sensory neurons, which convert external/internal stimulus into spike trains based on specific neural algorithm along with inherent stochasticity. Unfortunately, conventional solid-state transducers are inadequate for this purpose necessitating the development of neural encoders to serve the growing need of neuromorphic computing. Here, we demonstrate a biomimetic device based on a dual gated MoS2 field effect transistor (FET) capable of encoding analog signals into stochastic spike trains following various neural encoding algorithms such as rate-based encoding, spike timing-based encoding, and spike count-based encoding. Two important aspects of neural encoding, namely, dynamic range and encoding precision are also captured in our demonstration. Furthermore, the encoding energy was found to be as frugal as ≈1–5 pJ/spike. Finally, we show fast (≈200 timesteps) encoding of the MNIST data set using our biomimetic device followed by more than 91% accurate inference using a trained SNN.

NaCl-Assisted CVD Growth of Large-Area High-Quality Trilayer MoS2 and the Role of the Concentration Boundary Layer

“…Particularly, molybdenum disulfide (MoS 2 ), a family member of TMDs, has a thickness-dependent band gap of 1.8 eV for monolayer and 1.2 eV for bulk, high electron mobility (40–480 cm 2 /V s), , and high Seebeck coefficient . These unique properties make MoS 2 a fitting material candidate for flexible devices, , photodetectors, − field-effect transistors, ,− space applications, , gas sensors, neuromorphic computing, − biomimetic sensing, , and so forth. Numerous approaches have been utilized to achieve a layered MoS 2 film, such as metal–organic chemical vapor deposition (MOCVD), , CVD, − atomic layer deposition (ALD), physical vapor deposition (PVD), and thermal deposition .…”

All-in-one, bio-inspired, and low-power crypto engines for near-sensor security based on two-dimensional memtransistors

“…Therefore, the sensing unit of our MoS 2 -based crypto engine is not limited to only optical stimuli. See Supplementary Table 1 for benchmarking of our work against earlier works on 2D materials [18][19][20][21][22][23][24][25][26][27][28][29][30] , memristors [31][32][33][34][35][36][37] , phase change materials 38 , and nano crystals 39 that combine either "sensing and storage" or "sensing and compute" or "security and storage" but not all aspects in a single hardware platform.…”

Demonstration of Stochastic Resonance, Population Coding, and Population Voting Using Artificial MoS2 Based Synapses

“…Note that atomically thin 2D semiconductors such as monolayer MoS 2 offer potential for aggressive device scaling and high dielectric constant of Al 2 O 3 compared to conventional SiO 2 allows for superior electrostatic gate control, essential for achieving low power device operation . The choice of MoS 2 is motivated by its technological maturity, which include high electrical performance, ease of fabrication, ease of growing over a large area (wafer-scale), high yield, low device-to-device variation, reliability, and demonstration of multifunctional sensors as well as biomimetic, neuromorphic, and hardware security devices. − MoS 2 used in this study was grown epitaxially on a sapphire substrate using a metal organic chemical vapor deposition (MOCVD) technique at 1000 °C and subsequently transferred from the growth substrate to the device fabrication substrate using a PMMA-assisted wet transfer process . The large-area MOCVD growth allows for the fabrication of high-performance monolayer MoS 2 FET arrays that serve as the neural population.…”