Memristor-based Neural Networks Research Articles

A memristive all-inclusive hypernetwork for parallel analog deployment of full search space architectures

In recent years, there has been a significant advancement in memristor-based neural networks, positioning them as a pivotal processing-in-memory deployment architecture for a wide array of deep learning applications. Within this realm of progress, the emerging parallel analog memristive platforms are prominent for their ability to generate multiple feature maps in a single processing cycle. However, a notable limitation is that they are specifically tailored for neural networks with fixed structures. As an orthogonal direction, recent research reveals that neural architecture should be specialized for tasks and deployment platforms. Building upon this, the neural architecture search (NAS) methods effectively explore promising architectures in a large design space. However, these NAS-based architectures are generally heterogeneous and diversified, making it challenging for deployment on current single-prototype, customized, parallel analog memristive hardware circuits. Therefore, investigating memristive analog deployment that overrides the full search space is a promising and challenging problem. Inspired by this, and beginning with the DARTS search space, we study the memristive hardware design of primitive operations and propose the memristive all-inclusive hypernetwork that covers 2×1025 network architectures. Our computational simulation results on 3 representative architectures (DARTS-V1, DARTS-V2, PDARTS) show that our memristive all-inclusive hypernetwork achieves promising results on the CIFAR10 dataset (89.2% of PDARTS with 8-bit quantization precision), and is compatible with all architectures in the DARTS full-space. The hardware performance simulation indicates that the memristive all-inclusive hypernetwork costs slightly more resource consumption (nearly the same in power, 22%∼25% increase in Latency, 1.5× in Area) relative to the individual deployment, which is reasonable and may reach a tolerable trade-off deployment scheme for industrial scenarios.

Memristor-Based Conditioned Inhibition Neural Network Circuit With Blocking Generalization and Differentiation

Memristor-Based Conditioned Inhibition Neural Network Circuit With Blocking Generalization and Differentiation

Observer-based resilient dissipativity control for discrete-time memristor-based neural networks with unbounded or bounded time-varying delays

This work focuses on the issue of observer-based resilient dissipativity control of discrete-time memristor-based neural networks (DTMBNNs) with unbounded or bounded time-varying delays. Firstly, the Luenberger observer is designed, and additionally based on the observed states, the observer-based resilient controller is proposed. An augmented system is presented by considering both the error system and the DTMBNNs with the controller. Secondly, a novel sufficient extended exponential dissipativity condition is obtained for the augmented system with unbounded time-varying delays by proposing a system solutions-based estimation approach. This method is based on system solutions and without constructing any Lyapunov–Krasovskii functionals (LKF), thereby reducing the complexity of theoretical derivation and computational workload. In addition, an algorithm is proposed to solve the nonlinear inequalities in the sufficient condition. Thirdly, the sufficient extended exponential dissipativity condition for the augmented system with bounded time-varying delays is also obtained. Finally, the effectiveness of the theoretical results is illustrated through two simulation examples.

New results on synchronization control of memristor-based quaternion-valued fuzzy neural networks with delayed impulses

A model of memristor-based quaternion-valued fuzzy neural networks (MQVFNNs) with delayed impulses and time-varying delays is established, and the synchronization issue is investigated in this paper. Firstly, to avoid non-commutativity, the MQVFNNs are decomposed into real-valued delayed impulsive neural networks. Secondly, a novel lemma for delayed impulsive system is introduced based on Halanay differential inequality. Then, by employing the theory of differential inclusion and the proposed lemma, some sufficient conditions are deduced to guarantee the global exponential synchronization of memristive quaternion-valued fuzzy neural networks under a simple delayed nonlinear control scheme. Finally, a numerical simulation is given to demonstrate the effectiveness of our theoretical results.

A Memristor Neural Network Based on Simple Logarithmic-Sigmoidal Transfer Function with MOS Transistors

Memristors are state-of-the-art, nano-sized, two-terminal, passive electronic elements with very good switching and memory characteristics. Owing to their very low power usage and a good compatibility to the existing CMOS ultra-high-density integrated circuits and chips, they are potentially applicable in artificial and spiking neural networks, memory arrays, and many other devices and circuits for artificial intelligence. In this paper, a complete electronic realization of an analog circuit model of the modified neural net with memristor-based synapses and transfer function with memristors and MOS transistors in LTSPICE is offered. Each synaptic weight is realized by only one memristor, providing enormously reduced circuit complexity. The summing and scaling implementation is founded on op-amps and memristors. The logarithmic-sigmoidal activation function is based on a simple scheme with MOS transistors and memristors. The functioning of the suggested memristor-based neural network for pulse input signals is evaluated both analytically in MATLAB-SIMULINK and in the LTSPICE environment. The obtained results are compared one to another and are successfully verified. The realized memristor-based neural network is an important step towards the forthcoming design of complex memristor-based neural networks for artificial intelligence, for implementation in very high-density integrated circuits and chips.

Powering AI at the edge: A robust, memristor-based binarized neural network with near-memory computing and miniaturized solar cell

Memristor-based neural networks provide an exceptional energy-efficient platform for artificial intelligence (AI), presenting the possibility of self-powered operation when paired with energy harvesters. However, most memristor-based networks rely on analog in-memory computing, necessitating a stable and precise power supply, which is incompatible with the inherently unstable and unreliable energy harvesters. In this work, we fabricated a robust binarized neural network comprising 32,768 memristors, powered by a miniature wide-bandgap solar cell optimized for edge applications. Our circuit employs a resilient digital near-memory computing approach, featuring complementarily programmed memristors and logic-in-sense-amplifier. This design eliminates the need for compensation or calibration, operating effectively under diverse conditions. Under high illumination, the circuit achieves inference performance comparable to that of a lab bench power supply. In low illumination scenarios, it remains functional with slightly reduced accuracy, seamlessly transitioning to an approximate computing mode. Through image classification neural network simulations, we demonstrate that misclassified images under low illumination are primarily difficult-to-classify cases. Our approach lays the groundwork for self-powered AI and the creation of intelligent sensors for various applications in health, safety, and environment monitoring.

Delay-independent control for synchronization of memristor-based BAM neural networks with parameter perturbation and strong mismatch via finite-time technology

This paper mainly studies the synchronization problem of memristor-based bidirectional associative memory neural networks (MBAMNNs) via finite-time technology. Different from the existing neural network dynamic models, the given model in this paper is focused on the impact of parameter perturbation and strong mismatch, where strong mismatch includes parameter mismatch and time-varying delay mismatch. These characteristics can make the model be closer to the actual situation. A delay-independent feedback control scheme, which can stabilize the error system within finite-time regardless of whether the past state is known or not, is designed. It is worth noting that the constant is replaced by a function with the exponential term in the delay-independent controller, which can save the control cost to a certain extent. Based on the integral inequality technique, some sufficient conditions for MBAMNNs to converge to the equilibrium point within finite-time are provided. The validity and correctness of the theoretical results are finally confirmed by numerical simulation.

Quantized dynamic event-triggered control for fixed/preset-time bipartite synchronization of memristor-based discontinuous multi-layer signed networks

This study addresses the fixed/preset-time bipartite synchronization (FTBS/PTBS) of memristor-based discontinuous multi-layer signed networks via quantized dynamic event-triggered control (ETC). Firstly, a memristor-based neural network model incorporating multi-layer coupling structures, signed networks and discontinuous activations is built. Subsequently, by designing two quantized dynamic ETC strategies without the linear feedback term, the FTBS and PTBS of the considered networks are discussed, and it is proved that Zeno behavior can be ruled out. In contrast to the previous static ETC mechanism, the introduced internal dynamic variable can significantly decrease the triggering times and further save communication resources. Lastly, three numerical examples are offered to verify the correctness and practicability of the theoretical analysis.

Dynamics analysis, synchronization and FPGA implementation of multiscroll Hopfield neural networks with non-polynomial memristor

The number of attractors in a memristor-based multiscroll Hopfield Neural Network (HNN) is typically coupled with the number of polynomials, which leads to a coupling between the computational complexity and resource utilization in circuit implementation. To decouple this relationship, we propose a non-polynomial memristor that satisfies the Lipschitz condition. Regardless of whether it is used to simulate synaptic behavior, simulate the impact of electromagnetic radiation, or a combination of both scenarios, it can conveniently control the generation of single-direction or multiple-direction multiscroll attractors without adding or reducing any terms. By constructing Lyapunov functions, the sufficient condition for these multiscroll memristor HNNs to be bounded is obtained. After improving the feasibility of linear matrix inequalities, a strongly adaptive observer is proposed. After uniting an adaptive sliding mode control method, we propose a new adaptive synchronization scheme to simulate neural network synchronization. Finally, the digital circuit implementation and functional verification of these memristor-based multiscroll HNNs are completed using a field-programmable gate array (FPGA). Based on this, an image encryption circuit is designed so that the FPGA can directly encrypt images and transmit them to the IO device.

Synchronization of Delayed Memristor-Based Neural Networks via Pinning Control With Local Information.

In this article, a novel pinning control method, only requiring information from partial nodes, is developed to synchronize drive-response memristor-based neural networks (MNNs) with time delay. An improved mathematical model of MNNs is established to describe the dynamic behaviors of MNNs accurately. In the existing literature, pinning controllers for synchronization of drive-response systems were designed based on information of all nodes, but in some specific situations, the control gains may be very large and challenging to realize in practice. To overcome this problem, a novel pinning control policy is developed to achieve synchronization of delayed MNNs, which depends only on local information of MNNs, for reducing communication and calculation burdens. Furthermore, sufficient conditions for synchronization of delayed MNNs are provided. Finally, numerical simulation and comparative experiments are conducted to verify the effectiveness and superiority of the proposed pinning control method.

Exponential Synchronization of Memristor-Based Competitive Neural Networks With Reaction-Diffusions and Infinite Distributed Delays.

Taking into account the infinite distributed delays and reaction-diffusions, this article investigates the global exponential synchronization problem of a class of memristor-based competitive neural networks (MCNNs) with different time scales. Based on the Lyapunov-Krasovskii functional and inequality approach, an adaptive control approach is proposed to ensure the exponential synchronization of the addressed drive-response networks. The closed-loop system is a discontinuous and delayed partial differential system in a cascade form, involving the spatial diffusion, the infinite distributed delays, the parametric adaptive law, the state-dependent switching parameters, and the variable structure controllers. By combining the theories of nonsmooth analysis, partial differential equation (PDE) and adaptive control, we present a new analytical method for rigorously deriving the synchronization of the states of the complex system. The derived m-norm (m ≥ 2)-based synchronization criteria are easily verified and the theoretical results are easily extended to memristor-based neural networks (NNs) without different time scales and reaction-diffusions. Finally, numerical simulations are presented to verify the effectiveness of the theoretical results.

Reliable and Energy-efficient Diabetic Retinopathy Screening using Memristor-based Neural Networks

Reliable and Energy-efficient Diabetic Retinopathy Screening using Memristor-based Neural Networks

Memristor-Based Neural Network Circuit of Associative Memory With Occasion Setting

Memristor-Based Neural Network Circuit of Associative Memory With Occasion Setting

Synchronization of inertial complex-valued memristor-based neural networks with time-varying delays.

The synchronization of inertial complex-valued memristor-based neural networks (ICVMNNs) with time-varying delays was explored in the paper with the non-separation and non-reduced approach. Sufficient conditions required for the exponential synchronization of the ICVMNNs were identified with the construction of comprehensive Lyapunov functions and the design of a novel control scheme. The adaptive synchronization was also investigated based on the derived results, which is easier to implement in practice. What's more, a numerical example that verifies the obtained results was presented.

Memristor-Based Neural Network Circuit of Operant Conditioning With Bridging and Conditional Reinforcement

Memristor-Based Neural Network Circuit of Operant Conditioning With Bridging and Conditional Reinforcement

Memristor-Based Neural Network Circuit of Associative Memory With Overshadowing and Emotion Congruent Effect.

Most memristor-based neural network circuits consider only a single pattern of overshadowing or emotion, but the relationship between overshadowing and emotion is ignored. In this article, a memristor-based neural network circuit of associative memory with overshadowing and emotion congruent effect is designed, and overshadowing under multiple emotions is taken into account. The designed circuit mainly consists of an emotion module, a memory module, an inhibition module, and a feedback module. The generation and recovery of different emotions are realized by the emotion module. The functions of overshadowing under different emotions and recovery from overshadowing are achieved by the inhibition module and the memory module. Finally, the blocking caused by long-term overshadowing is implemented by the feedback module. The proposed circuit can be applied to bionic emotional robots and offers some references for brain-like systems.

Circuit Implementation and Quasi-Stabilization of Delayed Inertial Memristor-Based Neural Networks.

In this brief, we consider the stability of inertial memristor-based neural networks with time-varying delays. First, delayed inertial memristor-based neural networks are modeled as continuous systems in the flux-current-voltage-time domain via the mathematical model of Hewlett-Packard (HP) memristor. Then, they are reduced to delayed inertial neural networks with interval parameters uncertainties. Quasi-equilibrium points and quasi-stability are proposed. Quasi-stability criteria of delayed inertial memristor-based neural networks are obtained by matrix measure method, the Halanay inequality, and uncertainty technologies. In the end, a numerical example is provided to show the validity of our results.

Scroll-growing/controlling chaotic attractors in cyclic Hopfield neural networks via memristive bridging

In this paper, a memristor-based neural network is proposed, which is implemented by two tri-neuron resistive-cyclic Hopfield neural networks (RC-HNNs) via memristive bridging. The memristor-bridged network has a line equilibrium set composed of infinitely many index-2 saddle-foci, but it can produce multi-scroll chaotic attractors contrary to Shil’nikov’s criterion. Complex bifurcation behaviors, scroll-growing chaotic attractors over time, and homogeneous coexisting attractors are revealed by numerical methods. Further, a scroll-control scheme is designed and scroll-controlling chaotic attractors are demonstrated numerically. The results show that the memristor-bridged network can not only generate scroll-growing chaotic attractors over time, but also produce scroll-controlling chaotic attractors by limiting the dynamic range of the internal state of the bridging memristor. Finally, an analog electronic circuit is designed for the memristor-bridged network, and PSIM circuit simulations are used to verify the numerical simulations.

Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks

Safety-critical sensory applications, like medical diagnosis, demand accurate decisions from limited, noisy data. Bayesian neural networks excel at such tasks, offering predictive uncertainty assessment. However, because of their probabilistic nature, they are computationally intensive. An innovative solution utilizes memristors’ inherent probabilistic nature to implement Bayesian neural networks. However, when using memristors, statistical effects follow the laws of device physics, whereas in Bayesian neural networks, those effects can take arbitrary shapes. This work overcome this difficulty by adopting a variational inference training augmented by a “technological loss”, incorporating memristor physics. This technique enabled programming a Bayesian neural network on 75 crossbar arrays of 1,024 memristors, incorporating CMOS periphery for in-memory computing. The experimental neural network classified heartbeats with high accuracy, and estimated the certainty of its predictions. The results reveal orders-of-magnitude improvement in inference energy efficiency compared to a microcontroller or an embedded graphics processing unit performing the same task.

Memristor-Based Neural Network Circuit of Duple-Reward and Duple-Punishment Operant Conditioning With Time Delay

Memristor-Based Neural Network Circuit of Duple-Reward and Duple-Punishment Operant Conditioning With Time Delay