“新词的不断涌现是语言的自然规律, 如在专业领域中新概念和实体名称代表了专业领域中某些共同特征集合的抽象概括, 经常作为关键词在句子中承担一定的角色。新词发现问题直接影响中文分词结果和后继文本语义理解任务的性能, 是自然语言处理研究领域的重要任务。本文提出了融合自编码器和对抗训练的中文新词发现模型, 采用字符级别的自编码器和无监督自学习的方式进行预训练, 可以有效提取语义信息, 不受分词结果影响, 适用于不同领域的文本;同时为了引入通用语言学知识, 添加了先验句法分析结果, 借助领域共享编码器融合语义和语法信息, 以提升划分歧义词的准确性;采用对抗训练机制, 以提取领域无关特征, 减少对于人工标注语料的依赖。实验选择六个不同的专业领域数据集评估新词发现任务, 结果显示本文模型优于其他现有方法;结合模型析构实验, 详细验证了各个模块的有效性。同时通过选择不同类型的源域数据和不同数量的目标域数据进行对比实验, 验证了模型的鲁棒性。最后以可视化的方式对比了自编码器和共享编码器对不同领域数据的编码结果, 显示了对抗训练方法能够有效地提取两者之间的相关性和差异性信息。”
We apply the proposed method to the MNIST dataset and the MIT-BIH dataset with a convolutional auto-encoder.
We here propose a novel cost-effective millimeter-level resolution photonic multiband radar system using a single MZM driven by a 1-GHz-bandwidth LFM signal.
A data-driven method is developed to approximate an nonlinear time-varying system (NTVS) by a linear time-varying system (LTVS), based on Koopman Operator and deep neural networks.
Then the self-coherent detection, as a simple and low-cost means, is accordingly facilitated for both de-chirping of MMW radar and frequency down-conversion reception of MMW communication, which circumvents the costly high-speed mixers along with MMW local oscillators and more significantly achieves the real-time decomposition of radar and communication information.
Discovering governing equations from data is critical for diverse scientific disciplines as they can provide insights into the underlying phenomenon of dynamic systems.
no code implementations • 11 Mar 2022 • Jin Hao, Jiaxiang Liu, Jin Li, Wei Pan, Ruizhe Chen, Huimin Xiong, Kaiwei Sun, Hangzheng Lin, Wanlu Liu, Wanghui Ding, Jianfei Yang, Haoji Hu, Yueling Zhang, Yang Feng, Zeyu Zhao, Huikai Wu, Youyi Zheng, Bing Fang, Zuozhu Liu, Zhihe Zhao
Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information.
As a popular representation of 3D data, point cloud may contain noise and need to be filtered before use.
In this article, we develop a multistage recommender system utilizing a two-level monotonic property characterizing a monotonic chain of events for personalized prediction.
The finite data-driven approximation of Koopman operators results in a class of linear predictors, useful for formulating linear model predictive control (MPC) of nonlinear dynamical systems with reduced computational complexity.
Furthermore, a practical calculation approach based on the Monte-Carlo integration method is derived to quantify the uncertainty of the parameters and predictions.
However, grasping distinguishable skills for some tasks with non-unique optima can be essential for further improving its learning efficiency and performance, which may lead to a multimodal policy represented as a mixture-of-experts (MOE).
This paper presents a deep reinforcement learning (DRL) algorithm for orientation estimation using inertial sensors combined with magnetometer.
In this article, we derive one-split and two-split tests relaxing the assumptions and computational complexity of existing black-box tests and extending to examine the significance of a collection of features of interest in a dataset of possibly a complex type such as an image.
Reinforcement learning is promising to control dynamical systems for which the traditional control methods are hardly applicable.
Built on the recent advances on risk analysis for ER, the proposed approach first trains a deep model on labeled training data, and then fine-tunes it by minimizing its estimated misprediction risk on unlabeled target data.
In comparison with the existing RL algorithms, the proposed method can achieve superior performance in terms of maintaining safety.
An actor-critic reinforcement learning algorithm is proposed to learn the state estimator approximated by a deep neural network.
To this end, we propose a random covariance clustering model (RCCM) to concurrently cluster subjects based on their FC networks, estimate the unique FC networks of each subject, and to infer shared network features.
More importantly, the existing multi-agent reinforcement learning (MARL) algorithms cannot ensure the closed-loop stability of a multi-agent system from a control-theoretic perspective, so the learned control polices are highly possible to generate abnormal or dangerous behaviors in real applications.
This paper presents a novel model-reference reinforcement learning algorithm for the intelligent tracking control of uncertain autonomous surface vehicles with collision avoidance.
Binary Convolutional Neural Networks (CNNs) can significantly reduce the number of arithmetic operations and the size of memory storage, which makes the deployment of CNNs on mobile or embedded systems more promising.
Asymptotic expansion of the TRSW model equations in these three small parameters leads to the deterministic thermal versions of the Salmon's L1 (TL1) model and the thermal quasi-geostrophic (TQG) model, upon expanding in the neighbourhood of thermal quasi-geostrophic balance among the flow velocity and the gradients of free surface elevation and buoyancy.
Fluid Dynamics Geophysics
Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation.
With the conventional control, we can ensure the learning-based control law provides closed-loop stability for the overall system, and potentially increase the sample efficiency of the deep reinforcement learning.
In this paper, we introduce and extend the idea of robust stability and $H_\infty$ control to design policies with both stability and robustness guarantee.
In this paper, we combine variational learning and constrained reinforcement learning to simultaneously learn a Conditional Representation Model (CRM) to encode the states into safe and unsafe distributions respectively as well as to learn the corresponding safe policy.
Reinforcement learning (RL) offers a principled way to achieve the optimal cumulative performance index in discrete-time nonlinear stochastic systems, which are modeled as Markov decision processes.
One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training.
This paper presents a simple yet effective method for feature-preserving surface smoothing.
Computational Geometry Graphics
Our methods are tested on both the matrix game and the differential game, which have a non-trivial equilibrium where common gradient-based methods fail to converge.
Collision avoidance is a critical task in many applications, such as ADAS (advanced driver-assistance systems), industrial automation and robotics.
Herein, we present a system for hyperspectral image segmentation that utilizes multiple class--based denoising autoencoders which are efficiently trained.
Use of this recording configuration with neural network deconvolution promises to make clinically indicated home sleep studies practical.
To address this gap, we introduce a new analytical framework: We propose that groups arrive at accurate shared beliefs via distributed Bayesian inference.