ABSTRACT
Neural networks are increasingly used to solve optimization problems in various fields, including operations research, design automation, and gene sequencing. However, these networks face challenges due to the nondeterministic polynomial time (NP)-hard issue, which results in exponentially increasing computational complexity as the problem size grows. Conventional digital hardware struggles with the von Neumann bottleneck, the slowdown of Moore's law, and the complexity arising from heterogeneous system design. Two-dimensional (2D) memristors offer a potential solution to these hardware challenges, with their in-memory computing, decent scalability, and rich dynamic behaviors. In this study, we explore the use of nonvolatile 2D memristors to emulate synapses in a discrete-time Hopfield neural network, enabling the network to solve continuous optimization problems, like finding the minimum value of a quadratic polynomial, and tackle combinatorial optimization problems like Max-Cut. Additionally, we coupled volatile memristor-based oscillators with nonvolatile memristor synapses to create an oscillatory neural network-based Ising machine, a continuous-time analog dynamic system capable of solving combinatorial optimization problems including Max-Cut and map coloring through phase synchronization. Our findings demonstrate that 2D memristors have the potential to significantly enhance the efficiency, compactness, and homogeneity of integrated Ising machines, which is useful for future advances in neural networks for optimization problems.
ABSTRACT
Intrinsic plasticity of neurons, such as spontaneous threshold lowering (STL) to modulate neuronal excitability, is key to spatial attention of biological neural systems. In-memory computing with emerging memristors is expected to solve the memory bottleneck of the von Neumann architecture commonly used in conventional digital computers and is deemed a promising solution to this bioinspired computing paradigm. Nonetheless, conventional memristors are incapable of implementing the STL plasticity of neurons due to their first-order dynamics. Here, a second-order memristor is experimentally demonstrated using yttria-stabilized zirconia with Ag doping (YSZ:Ag) that exhibits STL functionality. The physical origin of the second-order dynamics, i.e., the size evolution of Ag nanoclusters, is uncovered through transmission electron microscopy (TEM), which is leveraged to model the STL neuron. STL-based spatial attention in a spiking convolutional neural network (SCNN) is demonstrated, improving the accuracy of a multiobject detection task from 70% (20%) to 90% (80%) for the object within (outside) the area receiving attention. This second-order memristor with intrinsic STL dynamics paves the way for future machine intelligence, enabling high-efficiency, compact footprint, and hardware-encoded plasticity.
ABSTRACT
To overcome the energy efficiency bottleneck of the von Neumann architecture and scaling limit of silicon transistors, an emerging but promising solution is neuromorphic computing, a new computing paradigm inspired by how biological neural networks handle the massive amount of information in a parallel and efficient way. Recently, there is a surge of interest in the nematode worm Caenorhabditis elegans (C. elegans), an ideal model organism to probe the mechanisms of biological neural networks. In this article, we propose a neuron model for C. elegans with leaky integrate-and-fire (LIF) dynamics and adjustable integration time. We utilize these neurons to build the C. elegans neural network according to their neural physiology, which comprises: 1) sensory modules; 2) interneuron modules; and 3) motoneuron modules. Leveraging these block designs, we develop a serpentine robot system, which mimics the locomotion behavior of C. elegans upon external stimulus. Moreover, experimental results of C. elegans neurons presented in this article reveals the robustness (1% error w.r.t. 10% random noise) and flexibility of our design in term of parameter setting. The work paves the way for future intelligent systems by mimicking the C. elegans neural system.
ABSTRACT
A large number of studies have shown that astrocytes can be combined with the presynaptic terminals and postsynaptic spines of neurons to constitute a triple synapse via an endocannabinoid retrograde messenger to achieve a self-repair ability in the human brain. Inspired by the biological self-repair mechanism of astrocytes, this work proposes a self-repairing neuron network circuit that utilizes a memristor to simulate changes in neurotransmitters when a set threshold is reached. The proposed circuit simulates an astrocyte-neuron network and comprises the following: 1) a single-astrocyte-neuron circuit module; 2) an astrocyte-neuron network circuit; 3) a module to detect malfunctions; and 4) a neuron PR (release probability of synaptic transmission) enhancement module. When faults occur in a synapse, the neuron module becomes silent or near silent because of the low PR of the synapses. The circuit can detect faults automatically. The damaged neuron can be repaired by enhancing the PR of other healthy neurons, analogous to the biological repair mechanism of astrocytes. This mechanism helps to repair the damaged circuit. A simulation of the circuit revealed the following: 1) as the number of neurons in the circuit increases, the self-repair ability strengthens and 2) as the number of damaged neurons in the astrocyte-neuron network increases, the self-repair ability weakens, and there is a significant degradation in the performance of the circuit. The self-repairing circuit was used for a robot, and it effectively improved the robots' performance and reliability.