In recent years, the analysis of the dynamics of annular neural networks has received extensive attention and achieved some achievements. However, most of the current research merely focuses on the single-ring, low-dimension, two rings sharing one neuron cases, without considering the rich coupling modes between rings. In this article, a large-scale time-delay fractional-order dual-loop neural network model with cross-coupling structure is established, in which two rings complete information interaction through two shared neurons. Moreover, the Caputo fractional derivative is introduced in this article to describe the neural network more accurately. First, the transmission time delay between each neuron is selected as the key parameter leading to the bifurcation, and the characteristic equation of the network is creatively derived using the Coates flow graph method. Subsequently, through the holistic element method and magnitude angle formula, we simplify the analytical process. Then, we obtain the stability and Hopf bifurcation criterion of the network. Finally, the conclusions of the theoretical analysis are verified by a series of numerical simulations. The results show that the stability region of the network is closely related to the fractional order, the number of neurons, the distribution of neurons, and the self-feedback coefficients. Moreover, the time delays have a significant effect on the amplitude and period of the Hopf bifurcation.

Spatiotemporal dynamics in the brain have been recognized as strongly related to the formation of perceived and cognitive diseases, such as delusions and hallucinations in Alzheimer's disease. However, two practical considerations are rarely mentioned in related mechanism research: the connectomics networking and the anomalous diffusion generated by the complex medium between neurons and the complex topology of neural networks, respectively. Furthermore, how to optimize the corresponding dynamics behaviors has excellent implications for treating brain diseases. This article first realizes the networking under connectomics for an anomalous-diffusion single-neuron model and applies a nonlinear state feedback control to generate optimized dynamic behaviors, which provides a paradigm of nonequilibrium self-organization driven by anomalous diffusion. Then, by tracing the root distribution of the characteristic equation, some controlled conditions causing or inhibiting Turing instability and Hopf bifurcation are deduced, and the effects of self-diffusion and cross diffusion on Turing instability range are also revealed. At last, thorough numerical simulations are updated to illustrate the results. It is emphasized that delay, self-diffusion, cross diffusion, and fractional order occupy dominant positions in determining the network's spatiotemporal dynamics, and utilizing the control strategy can efficiently reduce Turing instability and delay Hopf bifurcation.

Abstract In this paper, a two-neuron reaction–diffusion neural network with discrete and distributed delays is proposed, and the state feedback control strategy is adopted to achieve control of its spatiotemporal dynamical behaviours. Adding two virtual neurons, the original system is transformed into a neural network only containing the discrete delay. The conditions under which Hopf bifurcation and Turing instability arise are determined through analysis of the characteristic equation. Additionally, the amplitude equations are derived with the aid of weakly nonlinear analysis, and the selection of the Turing patterns is determined. The simulation results demonstrate that the state feedback controller can delay the onset of Hopf bifurcation and suppress the generation of Turing patterns.

With the proliferation of information and rapid network development, network attacks and threats are on the rise, and identifying malicious traffic is crucial for network security. However, the distribution of malicious and benign traffic in real-world networks is unbalanced, and the identification of malicious traffic in a real-world environment with a large amount of unbalanced and less known labelled malicious traffic is still a pressing problem. To tackle this issue, the paper presents a self-paced and reweighting Positive-Unlabeled learning algorithm (SRPU) for detecting imbalanced distribution traffic. This approach includes a self-paced training strategy that flexibly identifies assured positive/negative instances while taking the regret data loss into account, and a double-loss reweighting strategy to classify imbalanced malevolent traffic. We present the performance of SRPU by performing real-world experiments on three widely available datasets. These datasets include both common network attacks and APT attacks. The experimental results show that SRPU achieves the highest F1 and MCC scores at different label frequencies. It significantly outperforms existing methods.

In this paper, we address the problem of simultaneous relighting and novel view synthesis of a complex scene from multi-view images with a limited number of light sources. We propose an analysis-synthesis approach called Relit-NeuLF. Following the recent neural 4D light field network (NeuLF)[22], Relit-NeuLF first leverages a two-plane light field representation to parameterize each ray in a 4D coordinate system, enabling efficient learning and inference. Then, we recover the spatially-varying bidirectional reflectance distribution function (SVBRDF) of a 3D scene in a self-supervised manner. A DecomposeNet learns to map each ray to its SVBRDF components: albedo, normal, and roughness. Based on the decomposed BRDF components and conditioning light directions, a RenderNet learns to synthesize the color of the ray. To self-supervise the SVBRDF decomposition, we encourage the predicted ray color to be close to the physically-based rendering result using the microfacet model. Comprehensive experiments demonstrate that the proposed method is efficient and effective on both synthetic data and real-world human face data, and outperforms the state-of-the-art results.

In this paper, a real-time method called PoP-Net is proposed to predict multi-person 3D poses from a depth image. PoP-Net learns to predict bottom-up part representations and top-down global poses in a single shot. Specifically, a new part-level representation, called Truncated Part Displacement Field (TPDF), is introduced which enables an explicit fusion process to unify the advantages of bottom-up part detection and global pose detection. Meanwhile, an effective mode selection scheme is introduced to automatically resolve the conflicting cases between global pose and part detections. Finally, due to the lack of high-quality depth datasets for developing multi-person 3D pose estimation, we introduce Multi-Person 3D Human Pose Dataset (MP-3DHP) as a new benchmark. MP-3DHP is designed to enable effective multi-person and background data augmentation in model training, and to evaluate 3D human pose estimators under uncontrolled multi-person scenarios. We show that PoP-Net achieves the state-of-the-art results both on MP-3DHP and on the widely used ITOP dataset, and has significant advantages in efficiency for multi-person processing. MP-3DHP Dataset and the evaluation code have been made available at: https://github.com/oppo-us-research/PoP-Net.

With the rapid development of the Internet, the number of cyber threats increases exponentially. More and more cyber threats come from new and unexpected sources, leading organizations and individuals to facing more security risks and vulnerabilities. Automatically obtaining and structuring security information from cybersecurity news can help security analysts to identify useful information more quickly. Most existing studies on extracting security events merely focused on the event detection task, aiming to discover and categorize cybersecurity events from the plain text. However, such event detection methods cannot capture useful information such as who performed the cyberattack, when the data breach event happened, who was the victim, etc. These arguments of a cybersecurity event are needed for analysts to get cybersecurity event details directly. Several studies have tried to extract rich semantic information of cybersecurity events, but they merely focused on extracting event arguments within the sentence scope. These studies still have limitations when the event arguments needed to recognize spread across multiple sentences. In this paper, we proposed a framework that effectively extracts cybersecurity events at the document-level from cybersecurity news, blogs and announcements. We model the document level event extraction task as a sequence tagging problem. The goal is to identify the related arguments of cybersecurity events from documents. Firstly, we get the characters embedding and incorporate the word information into the character representations. Then we design a sliding window mechanism to get the cross-sentence context information. Finally, we predict the label of each character. We build a Chinese cybersecurity dataset and use three methods to evaluate our method, and the experimental results demonstrate the effectiveness of the proposed model.