Social media is a platform for people to share their lives and interact with others. image sharing is an integral component. Privacy information will inevitably be compromised during the process of sharing whole photo...
详细信息
In this work, we propose a multisensory mutual associative memory networks framework and memristive circuit to mimic the ability of the biological brain to make associations of information received simultaneously. The...
详细信息
In this work, we propose a multisensory mutual associative memory networks framework and memristive circuit to mimic the ability of the biological brain to make associations of information received simultaneously. The circuit inspired by neural mechanisms of associative memory cells mainly consists of three modules: 1) the storage neurons module, which encodes external multimodal information into the firing rate of spikes;2) the synapse module, which uses the nonvolatility memristor to achieve weight adjustment and associative learning;and 3) the retrieval neuron module, which feeds the retrieval signal output from each sensory pathway to other sensory pathways, so that achieve mutual association and retrieval between multiple modalities. Different from other one-to-one or many-to-one unidirectional associative memory work, this circuit achieves bidirectional association from multiple modalities to multiple modalities. In addition, we simulate the acquisition, extinction, recovery, transmission, and consolidation properties of associative memory. The circuit is applied to cross-modal association of image and audio recognition results, and episodic memory is simulated, where multiple images in a scene are intramodal associated. With power and area analysis, the circuit is validated as hardware-friendly. Further research to extend this work into large-scale associative memory networks, combined with visual-auditory-tactile-gustatory sensory sensors, is promising for application in intelligent robotic platforms to facilitate the development of neuromorphic systems and brain-like intelligence.
Compared to traditional area coverage algorithms, this paper proposes a re-plannable multi-agent coverage path planning algorithm to address issues such as low coverage rate of multiple agents in large-scale scenarios...
详细信息
Driver fatigue is a critical factor that lead to traffic accidents with a high fatality rate. Electroencephalogram (EEG) is one of the most reliable indicators to objectively assess fatigue status, but recognizing fat...
详细信息
Driver fatigue is a critical factor that lead to traffic accidents with a high fatality rate. Electroencephalogram (EEG) is one of the most reliable indicators to objectively assess fatigue status, but recognizing fatigue driving status from it is still an essential and challenging problem. In this paper, we propose a multiscale global prompt Transformer (MsGPT) deep learning model, which can automatically recognize driver fatigue end-to-end. First, we construct an intra-inter-scale cascade framework based on Transformer with a multiscale convolutional patch embedding (MC-PatchEmbed), and guide global-local feature interaction by adding a global prompt token throughout. Second, to efficiently integrate intra-scale and inter-scale feature information, we design a mixed token by aggregating the output from the intra-scale, which includes rich low-level feature information for multiscale. Moreover, a novel learnable query is introduced into multi-head self-attention (MSA) to reduce the computational complexity to linear level. Experiments are conducted on the SEED-VIG dataset and the SADT dataset with both intra-subject and inter-subject settings to evaluate the performance of MsGPT, and the results show that MsGPT greatly outperforms various methods in terms of the classification evaluation metrics of EEG-based fatigue driving. Note to Practitioners-This paper considers the use of raw EEG data to recognize the driver fatigue state. Existing methods mainly rely on manually extracted EEG features and convolutional neural network (CNN) based inference. However, the large intra-individual and inter-individual differences greatly limit the extraction of EEG fatigue features. This paper suggests a multiscale global prompt Transformer (MsGPT) deep learning model. This model leverages a shared weighting mechanism to construct an inter- to intra-scale multiscale framework that can capture refined fatigue features not achievable at a single scale, we incorporate a new Transform
作者:
Huang, XiangZhang, Hai-TaoSchool of Artificial Intelligence and Automation
Huazhong University of Science and Technology Engineering Research Center of Autonomous Intelligent Unmanned Systems The Key Laboratory of Image Processing and Intelligent Control The State Key Laboratory of Digital Manufacturing Equipment and Technology Wuhan430074 China
The piezoelectric actuator is one kind of device that can drive nanoscale motion. However, the nonlinear hysteresis effect induced by its natural material greatly degrades its positioning accuracy. To handle this chal...
详细信息
Almost all event-triggered control (ETC) strategies were designed for discrete-time or continuous-time systems. In order to unify these existing theoretical results of ETC and develop ETC strategies for nonlinear syst...
详细信息
Almost all event-triggered control (ETC) strategies were designed for discrete-time or continuous-time systems. In order to unify these existing theoretical results of ETC and develop ETC strategies for nonlinear systems, whose state variables evolve steadily at one time and change intermittently at another time, this article investigates quasisynchronization of delayed neural networks (NNs) on time scales with discontinuous activation functions via ETC approaches. First, the existence of the Filippov solutions is proved for discontinuous NNs with finite discontinuities. Second, two static event-triggered conditions and two dynamic event-triggered conditions are established to avoid continuous communication between the master-slave systems under algebraic/matrix inequality criteria. Third, under static/dynamic event-triggered conditions, a positive lower bound of event-triggered intervals is demonstrated to be greater than a positive number for each event-based controller, which shows that the Zeno behavior will not occur. Finally, two numerical simulations are carried out to show the effectiveness of the presented theoretical results in this article.
Continual learning aims to learn on a sequence of new tasks while maintaining the performance on previous tasks. Source-free domain adaptation (SFDA), which adapts a pre-trained source model to a target domain, is use...
详细信息
ISBN:
(纸本)9781665488679
Continual learning aims to learn on a sequence of new tasks while maintaining the performance on previous tasks. Source-free domain adaptation (SFDA), which adapts a pre-trained source model to a target domain, is useful in protecting the source domain data privacy. Generalized SFDA (G-SFDA) combines continual learning and SFDA to achieve outstanding performance on both the source and the target domains. This paper proposes semi-supervised G-SFDA (SSG-SFDA) for domain incremental learning, where a pre-trained source model (instead of the source data), few labeled target data, and plenty of unlabeled target data, are available. The goal is to achieve good performance on all domains. To cope with domain-ID agnostic, SSG-SFDA trains a conditional variational auto-encoder (CVAE) for each domain to learn its feature distribution, and a domain discriminator using virtual shallow features generated by CVAE to estimate the domain ID. To cope with catastrophic forgetting, SSG-SFDA uses soft domain attention to improve the sparse domain attention in G-SFDA. To cope with insufficient labeled target data, SSG-SFDA uses MixMatch to augment the unlabeled target data and better exploit the few labeled target data. Experiments on three datasets demonstrated the effectiveness of SSG-SFDA.
DNA nanotubes with controllable geometries hold a wide range of interdisciplinary applications. When preparing DNA nanotubes of varying widths or distinct chirality, existing methods require repeatedly designing and s...
详细信息
DNA nanotubes with controllable geometries hold a wide range of interdisciplinary applications. When preparing DNA nanotubes of varying widths or distinct chirality, existing methods require repeatedly designing and synthesizing specific DNA sequences, which can be costly and laborious. Here, we proposed an intercalator-assisted DNA tile assembly method which enables the production of DNA nanotubes of diverse widths and chirality using identical DNA strands. Through adjusting the concentration of intercalators during assembly, the twisting direction and extent of DNA tiles could be modulated, leading to the formation of DNA nanotubes featuring controllable widths and chirality. Moreover, through introducing additional intercalators and secondary annealing, right-handed nanotubes could be reconfigured into distinct left-handed nanotubes. We expect that this method could be universally applied to modulating the self-assembly pathways of various DNA tiles and other chiral materials, advancing the landscape of DNA tile assembly.
The multimodal optimisation problem challenges the balance between diversity and convergence, which poses a great degree of challenge to traditional population-based intelligence optimisers. The whale optimisation alg...
详细信息
Multimodal Emotion Recognition is challenging because of the heterogeneity gap among different modalities. Due to the powerful ability of feature abstraction, Deep Neural Networks (DNNs) have exhibited significant suc...
详细信息
Multimodal Emotion Recognition is challenging because of the heterogeneity gap among different modalities. Due to the powerful ability of feature abstraction, Deep Neural Networks (DNNs) have exhibited significant success in bridging the heterogeneity gap in cross-modal retrieval and generation tasks. In this work, a DNNs-based Multi-channel Weight-sharing Autoencoder with Cascade Multi-head Attention (MCWSA-CMHA) is proposed to generically address the affective heterogeneity gap in MER. Specifically, multimodal heterogeneity features are extracted by multiple independent encoders, and then a scalable heterogeneous feature fusion module (CMHA) is realized by connecting multiple multi-head attention modules in series. The core of the proposed algorithm is to reduce the heterogeneity between the output features of different encoders through the unsupervised training of MCWSA, and then to model the affective interactions between different modal features through the supervised training of CMHA. Experimental results demonstrate that the proposed MCWSA-CMHA achieves outperformance on two publicly available datasets compared with the state-of-the-art techniques. In addition, visualization experiments and approximation experiments are used to verify the effectiveness of each module in the proposed algorithm, and the experimental results show that the proposed MCWSA-CMHA can mine more emotion-related information among multimodal features compared with other fusion methods.
暂无评论