In this paper, a two-neuron reaction-diffusion neuralnetwork with discrete and distributed delays is proposed, and the state feedback control strategy is adopted to achieve control of its spatiotemporal dynamical beh...
详细信息
In this paper, a two-neuron reaction-diffusion neuralnetwork 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 neuralnetwork 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.
In this paper, an approach for ground-moving target classification with an FMCW radar is proposed. In particular, data are collected using a low-cost 24 GHz off-the-shelf FMCW radar, combined with an embedded Raspberr...
详细信息
In this paper, an approach for ground-moving target classification with an FMCW radar is proposed. In particular, data are collected using a low-cost 24 GHz off-the-shelf FMCW radar, combined with an embedded Raspberry Pi device for data acquisition and processing. An FFT-based processing scheme is then applied to obtain a sequence of range-Doppler maps, which are provided in input to different convolutional neuralnetwork (CNN) architectures for classifying the targets (cars, motorcycles, or pedestrians) eventually passing in front of the radar. Specifically, two approaches have been followed and compared. In the first one, single range-Doppler maps are processed alone using a convolutional neuralnetwork, and then a voting mechanism is applied to select the target classes. In the second approach, a sequence of range-Doppler maps is processed using a time-distributed layer feeding a recurrent neuralnetwork. The CNNs are deployed on the Raspberry Pi providing the target classification on a low-cost embedded device. The obtained results show that the proposed approaches allow for effectively detecting the different types of targets running on an embedded device in less than one second.
Text classification is a crucial domain within natural language processing (NLP), with applications ranging from document categorization to sentiment analysis. In this context, the use of attention mechanisms in neura...
详细信息
Artificial neuralnetwork is considered to be one of the effective ways to enable soft robots to achieve high-performance control due to their significant advantages, such as massively parallel processing and distribu...
详细信息
Artificial neuralnetwork is considered to be one of the effective ways to enable soft robots to achieve high-performance control due to their significant advantages, such as massively parallel processing and distributed storage of information, adaptivity, and fault tolerance. Artificial neuralnetworks are composed of microelectronic components connected together, of which the most basic units are artificial neural synaptic units, such as atomic switches, memristors, and synaptic transistors. This paper first introduces the research status of soft robots and artificial neural synapses, predicts the demand of soft robots for artificial neural synapses, summarizes the difficulties and problems that may be encountered in the application of artificial neural synapses to soft robots, and finally points out the importance and feasibility of artificial neural synapses in the research and development of soft robots.
The traditional association theory maintains that associations between cues can change only in trials where the cue is actually presented. However, the retrospective revaluation (RR) studies the phenomenon that respon...
详细信息
The traditional association theory maintains that associations between cues can change only in trials where the cue is actually presented. However, the retrospective revaluation (RR) studies the phenomenon that responses to a cue can change even when the cue is not actually presented. A hardware memristor-based neuralnetwork circuit with an RR effect is proposed in this article. The neuralnetwork circuit successfully demonstrates various phenomena of RR, including the impact of deflation and inflation of companion cue associations on target cue, higher order RR, and context dependence. The correctness of the circuit design is verified by Pspice simulation. The key feature of this design lies in its ability to learn cue associations even in training trials, where the target cues are absent. This distinctive attribute offers a fresh perspective for the creation of more intricate, brain-inspired information processing systems with enhanced integration capabilities.
An unmanned aerial vehicle (UAV) swarm has emerged as a powerful tool for mission execution in a variety of applications supported by deep neuralnetworks (DNNs). In the context of UAV swarms, conventional methods for...
详细信息
An unmanned aerial vehicle (UAV) swarm has emerged as a powerful tool for mission execution in a variety of applications supported by deep neuralnetworks (DNNs). In the context of UAV swarms, conventional methods for efficient data processing involve transmitting data to cloud and edge servers. However, these methods often face limitations in adapting to real-time applications due to the low latency of cloud-based approaches and weak mobility of edge-based approaches. In this paper, a new system called deep reinforcement learning-based resilient layer distribution (DRL-RLD) for distributed inference is designed to minimize end-to-end latency in UAV swarm, considering the resource constraints of UAVs. The proposed system dynamically allocates CNN layers based on UAV-to-UAV and UAV-to-ground communication links to minimize end-to-end latency. It can also enhance resilience to maintain mission continuity by reallocating layers when inoperable UAVs occur. The performance of the proposed system was verified through simulations in terms of latency compared to the comparison baselines, and its robustness was demonstrated in the presence of inoperable UAVs.
Within the Beyond 6th Generation (B6G) network, this research presents an efficient Convolutional neuralnetwork (CNN) architecture specifically tailored for image processing in intelligent city applications. The sugg...
详细信息
Within the Beyond 6th Generation (B6G) network, this research presents an efficient Convolutional neuralnetwork (CNN) architecture specifically tailored for image processing in intelligent city applications. The suggested CNN model takes advantage of the very low-latency, high-speed nature of B6G networks to enable crowd-monitoring-based public-safety image analysis in real-time. By catering to the distributed nature of data processing and the reduced load on central servers, our architecture is well-suited to the B6G infrastructures' edge computing environment. The CNN model accomplishes great accuracy in picture identification tasks with minimum processing overhead by utilising lightweight Convolutional layers and advanced optimisation techniques. We prove the model's efficacy in real-time processing and analysis of high-resolution images from security cameras and drones in trials conducted in virtual smart city environments. The findings show that B6G networks and sophisticated image processing methods can work together to make smart city apps more efficient and responsive.
Modern dynamical systems are rapidly incorporating artificial intelligence to improve the efficiency and quality of complex predictive analytics. To efficiently operate on increasingly large datasets and intrinsically...
详细信息
Modern dynamical systems are rapidly incorporating artificial intelligence to improve the efficiency and quality of complex predictive analytics. To efficiently operate on increasingly large datasets and intrinsically dynamic non-euclidean data structures, the computing community has turned to Graph neuralnetworks (GNNs). We make a key observation that existing GNN processing frameworks do not efficiently handle the intrinsic dynamics in modern GNNs. The dynamic processing of GNN operates on the complete static graph at each time step, leading to repetitive redundant computations that introduce tremendous under-utilization of system resources. We propose a novel dynamic graph neuralnetwork (DGNN) processing framework that captures the dynamically evolving dataflow of the GNN semantics, i.e., graph embeddings and sparse connections between graph nodes. The framework identifies intrinsic redundancies in node-connections and captures representative node-sparse graph information that is readily ingested for processing by the system. Our evaluation on an NVIDIA GPU shows up to 3.5x speedup over the baseline setup that processes all nodes at each time step.
With the advent of the intelligent information processing era, more and more private sensitive data are being collected and analyzed for intelligent decision making tasks. Such information processing also brings many ...
详细信息
With the advent of the intelligent information processing era, more and more private sensitive data are being collected and analyzed for intelligent decision making tasks. Such information processing also brings many challenges with existing privacy protection algorithms. On the one hand, the algorithms based on data encryption compromise the integrity of the original data or incur high computational and communication costs to some extent. On the other hand, algorithms based on distributed learning require frequent sharing of parameters between different computing nodes, which poses risks of leaking local model information and reducing global learning efficiency. To mitigate the impact of these issues, a quantum fuzzy federated learning (QFFL) algorithm is proposed. In the QFFL algorithm, a quantum fuzzy neuralnetwork is designed at the local computing nodes, which enhances data generalization while preserving data integrity. In global model, QFFL makes predictions through the quantum federated inference (QFI). QFI leads to a general framework for quantum federated learning on non-independent and identically distributed (IID) data with one-shot communication complexity, achieving privacy protection of local data and accelerating the global learning efficiency of the algorithm. The experiments are conducted on the COVID-19 and MNIST datasets, and the results indicate that QFFL demonstrates superior performance compared to the baselines, manifesting in faster training efficiency, higher accuracy, and enhanced security. In addition, based on the fidelity experiments and related analysis under four common quantum noise channels, the results demonstrated that it has good robustness against quantum noises, proving its applicability and practicality.
Graph neuralnetworks (GNNs) have delivered remarkable results in various fields. However, the rapid increase in the scale of graph data has introduced significant performance bottlenecks for GNN inference. Both compu...
详细信息
暂无评论