Search

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.

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.

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.

Integration of computer-science oriented artificial neural networks (ANNs) and neuroscience oriented spiking neural networks (SNNs) has emerged as a highly promising direction to achieve further breakthroughs in artificial intelligence through complementary advantages. This integration needs to support individual modeling of ANNs and SNNs as well as their hybrid modeling, which not only simultaneously calculates single-paradigm networks but also converts their different information representations. It remains challenging to realize effective calculation and signal conversion on the existing dedicated hardware platforms. To solve this problem, we propose an end-to-end mapping framework for implementing various hybrid neural networks on many-core neuromorphic architectures based on the cross-paradigm Tianjic chip. We construct hardware configuration schemes for four typical signal conversions and establish a global timing adjustment mechanism among different heterogeneous modules. Experimental results show that our framework can implement these hybrid models with low execution latency and low power consumption with nearly no accuracy degradation. This work provides a new approach of developing hybrid neural network models for brain-inspired computing chips and further tapping the potential of these models.

Object tracking based on the event-based camera or dynamic vision sensor (DVS) remains a challenging task due to the noise events, rapid change of event-stream shape, chaos of complex background textures, and occlusion. To address the challenges, this paper presents a robust event-stream object tracking method based on correlation filter mechanism and convolutional neural network (CNN) representation. In the proposed method, rate coding is used to encode the event-stream object. 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, the correlation filter-based method has the advantage of high speed. The proposed approach will promote the potential applications of these event-based vision sensors in autonomous driving, robots and many other high-speed scenes.

Using chips that mimic the human brain to perform cognitive tasks, namely neuromorphic computing, calls for low power and high efficiency hardware. Here, Yaoet al. show on-chip analogue weight storage by integrating non-volatile resistive memory into a CMOS platform and test it in facial recognition.

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.

Ca2+ is a pivotal signal in human pulmonary artery smooth muscle cells (PASMCs) proliferation. Capacitative Ca2+ entry (CCE) via the store-operated channel (SOC), which encoded by the transient receptor potential (TRP) gene, is an important mechanism for regulating intracellular Ca2+ concentration ([Ca2+]i) in PASMCs. Sildenafil, a potent type 5 nucleotide-dependent phosphodiesterase (PDE) inhibitor, has been proposed as a therapeutic tool to treat or prevent pulmonary arterial hypertension (PAH); however, the mechanism of its antiproliferative effect on PASMCs remains unclear. This study was designed to investigate the possible antiproliferative mechanism of sildenafil on human PASMCs, namely, its effect on the Ca2+-signal pathway. Cultured normal PASMCs were treated with endothelin-1 (ET-1) or ET-1 plus sildenafil separately. Cell number and viability were determined with a hemocytometer or MTT assay. [Ca2+]i was measured by loading PASMCs with fura 2-AM. Expression of the TRPC1 gene and protein was detected by RT-PCR and Western blot, respectively. The results show that sildenafil dose-dependently inhibited the proliferation of PASMCs, the enhancement of basal [Ca2+]i level, increase of CCE, and upregulation of TRPC expression induced by ET-1. These results suggest that sildenafil potently inhibits ET-1–induced PASMCs proliferation and downregulation of CCE and TRPC expression may be responsible for its antiproliferative effect. Keywords:: store-operated channel, capacitative Ca2+ entry, transient receptor potential channel, pulmonary artery smooth muscle cell

Finding the solution for driving a complex network at the minimum energy cost with a given number of controllers, known as the minimum-cost control problem, is critically important but remains largely open. We propose a projected gradient method to tackle this problem, which works efficiently in both synthetic and real-life networks. The study is then extended to the case where each controller can only be connected to a single network node to have the lowest connection complexity. We obtain the interesting insight that such connections basically avoid high-degree nodes of the network, which is in resonance with recent observations on controllability of complex networks. Our results provide the first technical path to enabling minimum-cost control of complex networks, and contribute new insights to locating the key nodes from a minimum-cost control perspective.