Hardware implementation of associative memory characteristics with analogue-type resistive-switching device

Centimeter-Scale Tellurium Oxide Films for Artificial Optoelectronic Synapses with Broadband Responsiveness and Mechanical Flexibility

Prevailing over the bottleneck of von Neumann computing has been significant attention due to the inevitableness of proceeding through enormous data volumes in current digital technologies. Inspired by the human brain's operational principle, the artificial synapse of neuromorphic computing has been explored as an emerging solution. Especially, the optoelectronic synapse is of growing interest as vision is an essential source of information in which dealing with optical stimuli is vital. Herein, flexible optoelectronic synaptic devices composed of centimeter-scale tellurium dioxide (TeO2) films detecting and exhibiting synaptic characteristics to broadband wavelengths are presented. The TeO2-based flexible devices demonstrate a comprehensive set of emulating basic optoelectronic synaptic characteristics; i.e., excitatory postsynaptic current (EPSC), paired-pulse facilitation (PPF), conversion of short-term to long-term memory, and learning/forgetting. Furthermore, they feature linear and symmetric conductance synaptic weight updates at various wavelengths, which are applicable to broadband neuromorphic computations. Based on this large set of synaptic attributes, a variety of applications such as logistic functions or deep learning and image recognition as well as learning simulations are demonstrated. This work proposes a significant milestone of wafer-scale metal oxide semiconductor-based artificial synapses solely utilizing their optoelectronic features and mechanical flexibility, which is attractive toward scaled-up neuromorphic architectures.

Artificial Optoelectronic Synapse Based on Violet Phosphorus Microfiber Arrays

Memristor-based artificial synapses are regarded as the most promising candidate to develop brain-like neuromorphic network computers and overcome the bottleneck of Von-Neumann architecture. Violet phosphorus (VP) as a new allotrope of available phosphorus with outstanding electro-optical properties and stability has attracted more and more attention in the past several years. In this study, large-scale, high-yield VP microfiber vertical arrays have been successfully developed on a Sn-coated graphite paper and are used as the memristor functional layers to build reliable, low-power artificial synaptic devices. The VP devices can well mimic the major synaptic functions such as short-term memory (STM), long-term memory (LTM), paired-pulse facilitation (PPF), spike timing-dependent plasticity (STDP), and spike rate-dependent plasticity (SRDP) under both electrical and light stimulation conditions, even the dendritic synapse functions and simple logical operations. By virtue of the excellent performance, the VP artificial synapse devices can be conductive to building high-performance optic-neural synaptic devices simulating the human-like optic nerve system. On this basis, Pavlov's associative memory can be successfully implemented optically. This study provides a promising approach for the design and manufacture of VP-based artificial synaptic devices and outlines a direction with multifunctional neural devices.

Short-term synaptic plasticity in emerging devices for neuromorphic computing

Neuromorphic computing is a promising computing paradigm toward building next-generation artificial intelligence machines, in which diverse types of synaptic plasticity play an active role in information processing. Compared to long-term plasticity (LTP) forming the foundation of learning and memory, short-term plasticity (STP) is essential for critical computational functions. So far, the practical applications of LTP have been widely investigated, whereas the implementation of STP in hardware is still elusive. Here, we review the development of STP by bridging the physics in emerging devices and biological behaviors. We explore the computational functions of various STP in biology and review their recent progress. Finally, we discuss the main challenges of introducing STP into synaptic devices and offer the potential approaches to utilize STP to enrich systems' capabilities. This review is expected to provide prospective ideas for implementing STP in emerging devices and may promote the construction of high-level neuromorphic machines.

Emergence of associative learning in a neuromorphic inference network

OBJECTIVE

In the theoretical framework of predictive coding and active inference, the brain can be viewed as instantiating a rich generative model of the world that predicts incoming sensory data while continuously updating its parameters via minimization of prediction errors. While this theory has been successfully applied to cognitive processes - by modelling the activity of functional neural networks at a mesoscopic scale - the validity of the approach when modelling neurons as an ensemble of inferring agents, in a biologically plausible architecture, remained to be explored.

APPROACH

We modelled a simplified cerebellar circuit with individual neurons acting as Bayesian agents to simulate the classical delayed eyeblink conditioning protocol. Neurons and synapses adjusted their activity to minimize their prediction error, which was used as the network cost function. This cerebellar network was then implemented in hardware by replicating digital neuronal elements via a low-power microcontroller.

MAIN RESULTS

Persistent changes of synaptic strength - that mirrored neurophysiological observations - emerged via local (neurocentric) prediction error minimization, leading to the expression of associative learning. The same paradigm was effectively emulated in low-power hardware showing remarkably efficient performance compared to conventional neuromorphic architectures.

SIGNIFICANCE

These findings show that: i) an ensemble of free energy minimizing neurons - organized in a biological plausible architecture - can recapitulate functional self-organization observed in nature, such as associative plasticity, and ii) a neuromorphic network of inference units can learn unsupervised tasks without embedding predefined learning rules in the circuit, thus providing a potential avenue to a novel form of brain-inspired artificial intelligence.

A carbon-based memristor design for associative learning activities and neuromorphic computing

Carbon quantum dots (QDs) have attracted significant interest due to their excellent electronic properties and wide application prospects. However, the application of carbon QDs has been rarely reported in memristors. Here, a memristor model with carbon conductive filaments (CFs) is proposed for the first time based on carbon quantum dots. The CF-based devices exhibited excellent resistive switching performance, in particular a narrow range of SET and RESET voltages and good power efficiency and retention properties. These devices could also emulate important biological synapse performances, such as the transition from short-term plasticity (STP) to long-term potentiation (LTP) behaviors, long-term depression (LTD) behavior, and four types of spike-timing-dependent plasticity (STDP) learning rules. Interestingly, Pavlovian associative learning functions were also reliably demonstrated in the memristor device (MD). The digit recognition ability of the MDs was evaluated though a single-layer perceptron model, in which the recognition accuracy of digits reached 92.63% after 250 training iterations. The transmission electron microscopy (TEM) results evidenced that the carbon CF was found in the MD at the "ON" state. Thus, this new carbon CF-based mechanism for memristors provides a new idea for achieving better neuromorphic MDs and applications.

Pavlovian conditioning demonstrated with neuromorphic memristive devices

Pavlovian conditioning, a classical case of associative learning in a biological brain, is demonstrated using the Ni/Nb-SrTiO₃/Ti memristive device with intrinsic forgetting properties in the framework of the asymmetric spike-timing-dependent plasticity of synapses. Three basic features of the Pavlovian conditioning, namely, acquisition, extinction and recovery, are implemented in detail. The effects of the temporal relation between conditioned and unconditioned stimuli as well as the time interval between individual training trials on the Pavlovian conditioning are investigated. The resulting change of the response strength, the number of training trials necessary for acquisition and the number of extinction trials are illustrated. This work clearly demonstrates the hardware implementation of the brain function of the associative learning.

Nonassociative learning implementation by a single memristor-based multi-terminal synaptic device

Animals' survival is dependent on their abilities to adapt to the changing environment by adjusting their behaviours, which is related to the ubiquitous learning behaviour, nonassociative learning. Thus mimicking the indispensable learning behaviour in organisms based on electronic devices is vital to better achieve artificial neural networks and neuromorphic computing. Here a three terminal device consisting of an oxide-based memristor and a NMOS transistor is proposed. The memristor with gradual conductance tuning inherently functions as the synapse between sensor neurons and motor neurons and presents adjustable synaptic plasticity, while the NMOS transistor attached to the memristor is utilized to mimic the modulatory effect of the neuromodulator released by inter neurons. Such a memristor-based multi-terminal device allows the practical implementation of significant nonassociative learning based on a single electronic device. In this study, the experience-induced modification behaviour, both habituation and sensitization, was successfully achieved. The dependence of the nonassociative behavioural response on the strength and interval of presented stimuli was also discussed. The implementation of nonassociative learning offers feasible and experimental advantages for further study on neuromorphic systems based on electronic devices.