检索结果-南通市图书馆

Rts: learning robustly from time series data with noisy label

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第6期18卷 186332-186332页

作者： ZHOU Zhi JIN Yi-Xuan Li Yu-Feng national key laboratory for Novel Software technology Nanjing University

Significant progress has been made in machine learning with large amounts of clean labels and static data. However, in many real-world applications, the data often changes with time and it is difficult to obtain massive clean annotations, that is, noisy labels and time series are faced simultaneously. For example, in product-buyer evaluation, each sample records the daily time behavior of users, but the long transaction period brings difficulties to analysis, and salespeople often erroneously annotate the user’s purchase behavior. Such a novel setting, to our best knowledge, has not been thoroughly studied yet, and there is still a lack of effective machine learning methods. In this paper, we present a systematic approach RTS both theoretically and empirically, consisting of two components, Noise-Tolerant Time Series Representation and Purified Oversampling Learning. Specifically, we propose reducing label noise’s destructive impact to obtain robust feature representations and potential clean samples. Then, a novel learning method based on the purified data and time series oversampling is adopted to train an unbiased model. Theoretical analysis proves that our proposal can improve the quality of the noisy data set. Empirical experiments on diverse tasks, such as the house-buyer evaluation task from real-world applications and various benchmark tasks, clearly demonstrate that our new algorithm robustly outperforms many competitive methods.

关键词： weakly-supervised learning time-series classification class-imbalanced learning

Robust cooperative multi-agent reinforcement learning via multi-view message certification

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 131-145页

作者： Lei YUAN Tao JIANG Lihe LI Feng CHEN Zongzhang ZHANG Yang YU national key laboratory for Novel Software technology Nanjing University Polixir Technologies

Many multi-agent scenarios require message sharing among agents to promote coordination,hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment. Major relevant studies tackle this issue under specific assumptions, like a limited number of message channels would sustain perturbations, limiting the efficiency in complex scenarios. In this paper,we take a further step in addressing this issue by learning a robust cooperative multi-agent reinforcement learning via multi-view message certification, dubbed CroMAC. Agents trained under CroMAC can obtain guaranteed lower bounds on state-action values to identify and choose the optimal action under a worst-case deviation when the received messages are perturbed. Concretely, we first model multi-agent communication as a multi-view problem, where every message stands for a view of the state. Then we extract a certificated joint message representation by a multi-view variational autoencoder(MVAE) that uses a product-of-experts inference network. For the optimization phase, we do perturbations in the latent space of the state for a certificate guarantee. Then the learned joint message representation is used to approximate the certificated state representation during training. Extensive experiments in several cooperative multi-agent benchmarks validate the effectiveness of the proposed CroMAC.

关键词： multi-agent reinforcement learning robust communication adversarial training multi-view learning message certification

Highly sensitive CO_(2)-LITES sensor based on a self-designed low-frequency quartz tuning fork and fiber-coupled MPC

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第7期22卷 105-110页

作者： Jinfeng Hou Xiaonan Liu Yahui Liu Ying He Weijiang Zhao Yufei Ma national key laboratory of Science and technology on Tunable Laser Harbin Institute of TechnologyHarbin 150001China

A highly sensitive carbon dioxide(CO_(2))sensor based on light-induced thermoelastic spectroscopy(LITES)utilizing a selfdesigned low-frequency quartz tuning fork(QTF)and a fiber-coupled multipass cell(MPC)is reported in this *** QTF with a low resonant frequency of 8675 Hz and a high Q factor of 11,675.64 was used to improve its energy accumulation time and the sensor’s signal *** MPC with the fiber-coupled structure and optical length of 40 m was adopted to significantly increase the gas absorbance and reduce the optical alignment difficulty as well as improve the robustness of the sensor system.A distributed feedback(DFB),near-infrared diode laser with an emission wavelength of 1.57μm was used as an excitation *** experimental results showed that this CO_(2)-LITES sensor had an excellent linear response to CO_(2) *** minimum detection limitation(MDL)of this CO_(2)-LITES sensor was obtained to be 445.91 ppm,and it could be improved to 47.70 ppm(parts per million)when the integration time of the system reached 500 *** improvement methods for the detection performance of such sensors were also discussed.

关键词： carbon dioxide quartz tuning fork multipass cell light-induced thermoelastic spectroscopy

维普期刊数据库

GS-orthogonalization OMP method for space target detection via bistatic space-based radar

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第7期37卷 333-351页

作者： Shuyu ZHENG Libing JIANG Qingwei YANG Yingjian ZHAO Zhuang WANG national key laboratory of Science and technology on Automatic Target Recognition College of Electronic Science and TechnologyNational University of Defense TechnologyChangsha 410073China

A space-based bistatic radar system composed of two space-based radars as the transmitter and the receiver respectively has a wider surveillance region and a better early warning capability for high-speed targets,and it can detect focused space targets more flexibly than the monostatic radar system or the ground-based radar ***,the target echo signal is more difficult to process due to the high-speed motion of both space-based radars and space *** be specific,it will encounter the problems of Range Cell Migration(RCM)and Doppler Frequency Migration(DFM),which degrade the long-time coherent integration performance for target detection and localization *** solve this problem,a novel target detection method based on an improved Gram Schmidt(GS)-orthogonalization Orthogonal Matching Pursuit(OMP)algorithm is proposed in this ***,the echo model for bistatic space-based radar is constructed and the conditions for RCM and DFM are ***,the proposed GS-orthogonalization OMP method is applied to estimate the equivalent motion parameters of space ***,the RCM and DFM are corrected by the compensation function correlated with the estimated motion ***,coherent integration can be achieved by performing the Fast Fourier Transform(FFT)operation along the slow time direction on compensated echo *** simulations and real raw data results validate that the proposed GS-orthogonalization OMP algorithm achieves better motion parameter estimation performance and higher detection probability for space targets detection.

关键词： Bistatic space-based radar High-speed maneuvering space targets detection Range Cell Migration(RCM) Doppler Frequency Migration(DFM) Gram Schmidt(GS)-orthogonalization Orthogonal Matching Pursuit(OMP)algorithm

维普期刊数据库

LAMDA-SSL:a comprehensive semi-supervised learning toolkit

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第1期67卷 306-307页

作者： Lin-Han JIA Lan-Zhe GUO Zhi ZHOU Yu-Feng LI national key laboratory for Novel Software technology Nanjing University

Machine learning, particularly deep learning, has achieved remarkable success across a wide range of tasks. However,most of these tasks demand a substantial amount of labeled training data, which can be challenging to obtain in many real-world applications due to difficulties, costs, or time constraints associated with labeling. In this context,semi-supervised learning (SSL) has emerged as a promising paradigm to alleviate the dependency on large labeled datasets by harnessing the power of unlabeled data [1–3].

关键词：

Sub-Nyquist sampling-based wideband spectrum sensing:a compressed power spectrum estimation approach

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第2期18卷 139-145页

作者： Jilin WANG Yinsen HUANG Bin WANG national key laboratory of Science and technology on Communications University of Electronic Science and Technology of ChinaChengdu 611731China

In this paper,we introduce a sub-Nyquist sampling-based receiver architecture and method for wideband spectrum *** of recovering the original wideband analog signal,the proposed method aims to directly reconstruct the power spectrum of the wideband analog signal from sub-Nyquist *** that power spectrum alone is sufficient for wideband spectrum *** only the covariance matrix of the wideband signal is needed,the proposed method,unlike compressed sensing-based methods,does not need to impose any sparsity requirement on the frequency *** proposed method is based on a multi-coset sampling *** exploiting the inherent sampling structure,a fast compressed power spectrum estimation method whose primary computational task consists of fast Fourier transform(FFT)is *** results are presented to show the effectiveness of the proposed method.

关键词： wideband spectrum sensing sub-Nyquist multicoset sampling FCPSE

An internal ballistic model of electromagnetic railgun based on PFN coupled with multi-physical field and experimental validation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Defence technology（防务技术） 2024年第2期32卷 254-261页

作者： Benfeng Gu Haiyuan Li Baoming Li national key laboratory of Transient Physics Nanjing University of Science and TechnologyNanjing 210094China

To accelerate the practicality of electromagnetic railguns,it is necessary to use a combination of threedimensional numerical simulation and experiments to study the mechanism of bore *** this paper,a three-dimensional numerical model of the augmented railgun with four parallel unconventional rails is introduced to simulate the internal ballistic process and realize the multi-physics field coupling calculation of the rail gun,and a test experiment of a medium-caliber electromagnetic launcher powered by pulse formation network(PFN)is carried *** test methods such as spectrometer,fiber grating and high-speed camera are used to test several parameters such as muzzle initial velocity,transient magnetic field strength and stress-strain of *** the simulation results and experimental data,the damage condition of the contact surface is analyzed.

关键词： Internal ballistic modeling Electromagnetic rail gun Multi-physics field coupling Experimental validation PFN

维普期刊数据库

Communication-robust multi-agent learning by adaptable auxiliary multi-agent adversary generation

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第6期18卷 186331-186331页

作者： YUAN Lei CHEN Feng ZHANG Zongzhang YU Yang national key laboratory for Novel Software technology Nanjing University Polixir Technologies

Communication can promote coordination in cooperative Multi-Agent Reinforcement Learning (MARL). Nowadays, existing works mainly focus on improving the communication efficiency of agents, neglecting that real-world communication is much more challenging as there may exist noise or potential attackers. Thus the robustness of the communication-based policies becomes an emergent and severe issue that needs more exploration. In this paper, we posit that the ego system trained with auxiliary adversaries may handle this limitation and propose an adaptable method of Multi-Agent Auxiliary Adversaries Generation for robust Communication, dubbed MA3C, to obtain a robust communication-based policy. In specific, we introduce a novel message-attacking approach that models the learning of the auxiliary attacker as a cooperative problem under a shared goal to minimize the coordination ability of the ego system, with which every information channel may suffer from distinct message attacks. Furthermore, as naive adversarial training may impede the generalization ability of the ego system, we design an attacker population generation approach based on evolutionary learning. Finally, the ego system is paired with an attacker population and then alternatively trained against the continuously evolving attackers to improve its robustness, meaning that both the ego system and the attackers are adaptable. Extensive experiments on multiple benchmarks indicate that our proposed MA3C provides comparable or better robustness and generalization ability than other baselines.

关键词： multi-agent communication adversarial training robustness validation reinforcement learning

Learning in games:a systematic review

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 133-159页

作者： Rong-Jun QIN Yang YU national key laboratory for Novel Software technology Nanjing University Polixir Technologies

Game theory studies the mathematical models for self-interested individuals. Nash equilibrium is arguably the most central solution in game theory. While finding the Nash equilibrium in general is known as polynomial parity arguments on directed graphs(PPAD)-complete, learning in games provides an alternative to approximate Nash equilibrium, which iteratively updates the player's strategy through interactions with other players. Rules and models have been developed for learning in games, such as fictitious play and no-regret learning. Particularly, with recent advances in online learning and deep reinforcement learning,techniques from these fields greatly boost the breakthroughs in learning in games from theory to *** a result, we have witnessed many superhuman game AI systems. The techniques used in these systems evolve from conventional search and learning to purely reinforcement learning(RL)-style learning methods,gradually getting rid of the domain knowledge. In this article, we systematically review the above techniques,discuss the trend of basic learning rules towards a unified framework, and recap applications in large ***, we discuss some future directions and make the prospect of future game AI systems. We hope this article will give some insights into designing novel approaches.

关键词： non-cooperative games learning in games no-regret learning reinforcement learning superhuman AI