For the manipulator which is used to execute maintenance tasks in the Tokamak reactor, solving the problem of collision-free path planning is the premise. This paper introduced the Single-RRT and Bi-RRT algorithms then used Bi-RRT algorithm to make the path planning for the motion of a redundant manipulator in the vacuum chamber, finally made a Matlab simulation analysis. The result shows that RRT algorithm can effectively achieve the purpose of collision-free path planning, and using Bi-RRT can reduce the number of searches and invalid search points compared with Single-RRT. The better path can be obtained and used in the actual control by means of multiple searches and replacements.

Deep neural networks, while generalize well, are known to be sensitive to small adversarial perturbations. This phenomenon poses severe security threat and calls for in-depth investigation of the robustness of deep learning models. With the emergence of neural networks for graph structured data, similar investigations are urged to understand their robustness. It has been found that adversarially perturbing the graph structure and/or node features may result in a significant degradation of the model performance. In this work, we show from a different angle that such fragility similarly occurs if the graph contains a few bad-actor nodes, which compromise a trained graph neural network through flipping the connections to any targeted victim. Worse, the bad actors found for one graph model severely compromise other models as well. We call the bad actors ``anchor nodes'' and propose an algorithm, named GUA, to identify them. Thorough empirical investigations suggest an interesting finding that the anchor nodes often belong to the same class; and they also corroborate the intuitive trade-off between the number of anchor nodes and the attack success rate. For the dataset Cora which contains 2708 nodes, as few as six anchor nodes will result in an attack success rate higher than 80% for GCN and other three models.

No abstract

Model compression is very important for the efficient deployment of deep neural network (DNN) models on resource-constrained devices. Among various model compression approaches, high-order tensor decomposition is particularly attractive and useful because the decomposed model is very small and fully structured. For this category of approaches, tensor ranks are the most important hyper-parameters that directly determine the architecture and task performance of the compressed DNN models. However, as an NP-hard problem, selecting optimal tensor ranks under the desired budget is very challenging and the state-of-the-art studies suffer from unsatisfied compression performance and timing-consuming search procedures. To systematically address this fundamental problem, in this paper we propose BATUDE, a Budget-Aware TUcker DEcomposition-based compression approach that can efficiently calculate optimal tensor ranks via one-shot training. By integrating the rank selecting procedure to the DNN training process with a specified compression budget, the tensor ranks of the DNN models are learned from the data and thereby bringing very significant improvement on both compression ratio and classification accuracy for the compressed models. The experimental results on ImageNet dataset show that our method enjoys 0.33% top-5 higher accuracy with 2.52X less computational cost as compared to the uncompressed ResNet-18 model. For ResNet-50, the proposed approach enables 0.37% and 0.55% top-5 accuracy increase with 2.97X and 2.04X computational cost reduction, respectively, over the uncompressed model.

No abstract

No abstract

No abstract

This paper addresses the problem of automatically labeling focus word pairs in spontaneous spoken English, where a focus word pair refers to salient part of text or speech and the word motivating it. The prediction of focus word pairs is important for speech applications such as expressive text-tospeech (TTS) synthesis and speech recognition. It can also help in better textual and intention understanding for spoken dialog systems. Traditional approaches such as support vector machines (SVMs) prediction neglect the dependency between words and meet the obstacle of the imbalanced distribution of positive and negative samples of dataset. This paper introduces conditional random fields (CRFs) to the task of automatically predicting focus word pair from lexical, syntactic and semantic features.Furthermore, several new features related to syntactic and semantic information are proposed to achieve better performance. Experiments on the publicly available Switchboard corpus demonstrate that CRF model outperforms the baseline and SVM model for focus word pair prediction, and newly proposed features can further improve performance for CRF based predictor. Specifically, compared to the low recall rate of 11.31% achieved by the SVM model, the proposed CRF based predictor can yield a high recall rate of 70.88% with little impact on precision.