Explore the vast range of titles available.

Spiking neural networks (SNNs) are promising in ascertaining brain-like behaviors since spikes are capable of encoding spatio-temporal information. Recent schemes, e.g., pre-training from artificial neural networks (ANNs) or direct training based on backpropagation (BP), make the high-performance supervised training of SNNs possible. However, these methods primarily fasten more attention on its spatial domain information, and the dynamics in temporal domain are attached less significance. Consequently, this might lead to the performance bottleneck, and scores of training techniques shall be additionally required. Another underlying problem is that the spike activity is naturally non-differentiable, raising more difficulties in supervised training of SNNs. In this paper, we propose a spatio-temporal backpropagation (STBP) algorithm for training high-performance SNNs. In order to solve the non-differentiable problem of SNNs, an approximated derivative for spike activity is proposed, being appropriate for gradient descent training. The STBP algorithm combines the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD), and does not require any additional complicated skill. We evaluate this method through adopting both the fully connected and convolutional architecture on the static MNIST dataset, a custom object detection dataset, and the dynamic N-MNIST dataset. Results bespeak that our approach achieves the best accuracy compared with existing state-of-the-art algorithms on spiking networks. This work provides a new perspective to investigate the high-performance SNNs for future brain-like computing paradigm with rich spatio-temporal dynamics.

Neuromorphic vision research requires high-quality and appropriately challenging event-stream datasets to support continuous improvement of algorithms and methods. However, creating event-stream datasets is a time-consuming task, which needs to be recorded using the neuromorphic cameras. Currently, there are limited event-stream datasets available. In this work, by utilizing the popular computer vision dataset CIFAR-10, we converted 10,000 frame-based images into 10,000 event streams using a dynamic vision sensor (DVS), providing an event-stream dataset of intermediate difficulty in 10 different classes, named as \"CIFAR10-DVS.\" The conversion of event-stream dataset was implemented by a repeated closed-loop smooth (RCLS) movement of frame-based images. Unlike the conversion of frame-based images by moving the camera, the image movement is more realistic in respect of its practical applications. The repeated closed-loop image movement generates rich local intensity changes in continuous time which are quantized by each pixel of the DVS camera to generate events. Furthermore, a performance benchmark in event-driven object classification is provided based on state-of-the-art classification algorithms. This work provides a large event-stream dataset and an initial benchmark for comparison, which may boost algorithm developments in even-driven pattern recognition and object classification.

There are two principle approaches for learning in artificial intelligence: error-driven global learning and neuroscience-oriented local learning. Integrating them into one network may provide complementary learning capabilities for versatile learning scenarios. At the same time, neuromorphic computing holds great promise, but still needs plenty of useful algorithms and algorithm-hardware co-designs to fully exploit its advantages. Here, we present a neuromorphic global-local synergic learning model by introducing a brain-inspired meta-learning paradigm and a differentiable spiking model incorporating neuronal dynamics and synaptic plasticity. It can meta-learn local plasticity and receive top-down supervision information for multiscale learning. We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors. It achieves significantly higher performance than single-learning methods. We further implement the model in the Tianjic neuromorphic platform by exploiting algorithm-hardware co-designs and prove that the model can fully utilize neuromorphic many-core architecture to develop hybrid computation paradigm. Global and local learning represent two distinct approaches to artificial intelligence. In this manuscript, Wu et al present a hybrid learning strategy, drawing from elements of both approaches, and implement it on a co-designed neuromorphic platform.

Neural networks trained by backpropagation have achieved tremendous successes on numerous intelligent tasks. However, naïve gradient-based training and updating methods on memristors impede applications due to intrinsic material properties. Here, we built a 39 nm 1 Gb phase change memory (PCM) memristor array and quantified the unique resistance drift effect. On this basis, spontaneous sparse learning (SSL) scheme that leverages the resistance drift to improve PCM-based memristor network training is developed. During training, SSL regards the drift effect as spontaneous consistency-based distillation process that reinforces the array weights at the high-resistance state continuously unless the gradient-based method switches them to low resistance. Experiments show that the SSL not only helps the convergence of network with better performance and sparsity controllability without additional computation in handwritten digit classification. This work promotes the learning algorithms with the intrinsic properties of memristor devices, opening a new direction for development of neuromorphic computing chips. Designing energy efficient and scalable artificial networks for neuromorphic computing remains a challenge. Here, the authors present 1 Gb phase change memory memristor array with a spontaneous sparse learning scheme able to leverage the resistance drift issue improving the classification accuracy on MNIST handwritten digit dataset.

Conventional hardware platforms consume huge amount of energy for cognitive learning due to the data movement between the processor and the off-chip memory. Brain-inspired device technologies using analogue weight storage allow to complete cognitive tasks more efficiently. Here we present an analogue non-volatile resistive memory (an electronic synapse) with foundry friendly materials. The device shows bidirectional continuous weight modulation behaviour. Grey-scale face classification is experimentally demonstrated using an integrated 1024-cell array with parallel online training. The energy consumption within the analogue synapses for each iteration is 1,000 × (20 ×) lower compared to an implementation using Intel Xeon Phi processor with off-chip memory (with hypothetical on-chip digital resistive random access memory). The accuracy on test sets is close to the result using a central processing unit. These experimental results consolidate the feasibility of analogue synaptic array and pave the way toward building an energy efficient and large-scale neuromorphic system. Using chips that mimic the human brain to perform cognitive tasks, namely neuromorphic computing, calls for low power and high efficiency hardware. Here, Yao et al . show on-chip analogue weight storage by integrating non-volatile resistive memory into a CMOS platform and test it in facial recognition.

Current artificial systems suffer from catastrophic forgetting during continual learning, a limitation absent in biological systems. Biological mechanisms leverage the dual representation of specific and generalized memories within corticohippocampal circuits to facilitate lifelong learning. Inspired by this, we develop a corticohippocampal circuits-based hybrid neural network (CH-HNN) that emulates these dual representations, significantly mitigating catastrophic forgetting in both task-incremental and class-incremental learning scenarios. Our CH-HNNs incorporate artificial neural networks and spiking neural networks, leveraging prior knowledge to facilitate new concept learning through episode inference, and offering insights into the neural functions of both feedforward and feedback loops within corticohippocampal circuits. Crucially, CH-HNN operates as a task-agnostic system without increasing memory demands, demonstrating adaptability and robustness in real-world applications. Coupled with the low power consumption inherent to SNNs, our model represents the potential for energy-efficient, continual learning in dynamic environments. Energy-efficient, task-agnostic continual learning is a key challenge in Artificial Intelligence frameworks. Here, authors propose a hybrid neural network that emulates dual representations in corticohippocampal circuits, reducing the effect of catastrophic forgetting.

Recently many ideas have been proposed for the use of a longitudinal field for particle acceleration, fluorescent imaging, second-harmonic generation and Raman spectroscopy. A few methods to enhance the longitudinal field component have been suggested, but all have insufficient optical efficiency and non-uniform axial field strength. Here we report a new method that permits the combination of very unusual properties of light in the focal region, permitting the creation of a ‘pure’ longitudinal light beam with subdiffraction beam size (0.43λ). This beam is non-diffracting; that is, it propagates without divergence over a long distance (of about 4λ) in free space. This is achieved by focusing a radially polarized Bessel–Gaussian beam with a combination of a binary-phase optical element and a high-numerical-aperture lens. This binary optics works as a special polarization filter enhancing the longitudinal component. Light is often thought of in terms of radial polarization, but longitudinal polarization is also possible, and it has some intriguing possibilities for particle acceleration. Binary optics, combined with a high-numerical-aperture lens, is a potential route to achieving light with this unusual property.

Object tracking based on an event-based dynamic vision sensor (DVS) is challenging for the noise events, rapid change of event-stream shape, chaos of complex background textures, and occlusion. To address these challenges, this paper presents a robust event-stream object tracking method based on correlative filter mechanism and convolutional neural network (CNN) representation. In the proposed method, rate coding is used to encode the event-stream object in each segment. Feature representations from hierarchical convolutional layers of a pre-trained CNN are used to represent the appearance of the rate encoded event-stream object. Results prove that the proposed method not only achieves good tracking performance in many complicated scenes with noise events, complex background textures, occlusion, and intersected trajectories, but also is robust to variable scale, variable pose, and non-rigid deformations. In addition, this correlative filter based event-stream tracking has the advantage of high speed. The proposed approach will promote the potential applications of these event-based vision sensors in self-driving, robots and many other high-speed scenes.

There is a growing trend to design hybrid neural networks (HNNs) by combining spiking neural networks and artificial neural networks to leverage the strengths of both. Here, we propose a framework for general design and computation of HNNs by introducing hybrid units (HUs) as a linkage interface. The framework not only integrates key features of these computing paradigms but also decouples them to improve flexibility and efficiency. HUs are designable and learnable to promote transmission and modulation of hybrid information flows in HNNs. Through three cases, we demonstrate that the framework can facilitate hybrid model design. The hybrid sensing network implements multi-pathway sensing, achieving high tracking accuracy and energy efficiency. The hybrid modulation network implements hierarchical information abstraction, enabling meta-continual learning of multiple tasks. The hybrid reasoning network performs multimodal reasoning in an interpretable, robust and parallel manner. This study advances cross-paradigm modeling for a broad range of intelligent tasks. Hybrid neural networks combine advantages of spiking and artificial neural networks in the context of computing and biological motivation. The authors propose a design framework with hybrid units for improved flexibility and efficiency of hybrid neural networks, and modulation of hybrid information flows.

Bi 2 O 2 Se is an emerging semiconducting, air-stable layered material (Nat. Nanotechnol. 2017, 1 2 , 530 ; Nano Lett. 2017, 17, 3021 ), potentially exceeding MoS 2 and phosphorene in electron mobility and rivalling typical Van der Waals stacked layered materials in the next-generation high-speed and low-power electronics. Holding the promise of functional versatility, it is arousing rapidly growing interest from various disciplines, including optoelectronics, thermoelectronics and piezoelectronics. In this work, we comprehensively study the electrical properties of the native point defects in Bi 2 O 2 Se, as an essential step toward understanding the fundamentals of this material. The defect landscapes dependent on both Fermi energy and the chemical potentials of atomic constituents are investigated. Along with the bulk defect analysis, a complementary inspection of the surface properties, within the simple context of charge neutrality level model, elucidates the observed n-type characteristics of Bi 2 O 2 Se based FETs. This work provides important guide to engineer the defects of Bi 2 O 2 Se for desired properties, which is key to the successful application of this emerging layered material 27 .