检索结果-内蒙古大学图书馆

Evolving Constrained Reinforcement Learning Policy

学校读者我要写书评

暂无评论

Evolving Constrained Reinforcement Learning Policy

International Joint Conference on Neural Networks (IJCNN)

作者： Chengpeng Hu Jiyuan Pei Jialin Liu Xin Yao Research Institute of Trustworthy Autonomous Systems (RITAS) Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improves the exploration efficiency. However, when adapting this approach to address constrained problems, balancing the trade-off between the reward and constraint violation is hard. In this paper, we propose a novel evolutionary constrained reinforcement learning (ECRL) algorithm, which adaptively balances the reward and constraint violation with stochastic ranking, and at the same time, restricts the policy's behaviour by maintaining a set of Lagrange relaxation coefficients with a constraint buffer. Extensive experiments on robotic control benchmarks show that our ECRL achieves outstanding performance compared to state-of-the-art algorithms. Ablation analysis shows the benefits of introducing stochastic ranking and constraint buffer.

关键词：

Multi-view LSTM Language Model with Word-synchronized Auxiliary Feature for LVCSR

学校读者我要写书评

暂无评论

Multi-view LSTM Language Model with Word-synchronized Auxili...

第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

作者： Yue Wu Tianxing He Zhehuai Chen Yanmin Qian Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong UniversityShanghaiChina

ISBN: (纸本)9783319690049

Recently long short-term memory language model(LSTMLM)has received tremendous interests from both language and speech communities,due to its superiorty on modelling long-term ***,integrating auxiliary information,such as context feature,into the LSTM LM has shown improved performance in perplexity(PPL).However,improper feed of auxiliary information won't give consistent gain on word error rate(WER)in a large vocabulary continuous speech recognition(LVCSR)*** solve this problem,a multi-view LSTM LM architecture combining a tagging model is proposed in this *** an on-line unidirectional LSTM-RNN is built as a tagging model,which can generate word-synchronized auxiliary *** the auxiliary feature from the tagging model is combined with the word sequence to train a multi-view unidirectional LSTM *** training modes for the tagging model and language model are explored and *** new architecture is evaluated on PTB,Fisher English and SMS Chinese data sets,and the results show that not only LM PPL promotion is observed,but also the improvements can be well transferred to WER reduction in ASR-rescore task.

关键词： LSTM language model speech recognition multi-view aux-iliary feature tagging model

Robust Spoken Language Understanding with Unsupervised ASR-Error Adaptation

学校读者我要写书评

暂无评论

Robust Spoken Language Understanding with Unsupervised ASR-E...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Su Zhu Ouyu Lan Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781538646595

Robustness to errors produced by automatic speech recognition (ASR) is essential for Spoken Language Understanding (SLU). Traditional robust SLU typically needs ASR hypotheses with semantic annotations for training. However, semantic annotation is very expensive, and the corresponding ASR system may change frequently. Here, we propose a novel unsupervised ASR-error adaptation method, obviating the need of annotated ASR hypotheses. It only requires semantically annotated transcripts for the slot-tagging task and the transcripts paired with hypotheses for an input sentence reconstruction task. In this method, feature encoders which share part of the parameters are exploited to enforce the tasks in a similar feature space. Therefore, the transcript side slot-tagging model can be transferred to ASR hypotheses side easily. Experiments show that the proposed approach can yield significant improvement over strong baselines, and achieve performance very close to the oracle system.

关键词： Spoken Language understanding ASR-error robustness adversarial adaptation spoken language understanding Speech recognition aquifer storage and recovery spoken language Eigenvector transcript Religious Missions ANNOTATIONS

Short-length SSVEP data extension by a novel generative adversarial networks based framework

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Yudong Li, Ning Zhang, Yangsong Xu, Peng Yao, Dezhong School of Computer Science and Technology Laboratory for Brain Science and Medical Artificial Intelligence Southwest University of Science and Technology Mianyang621010 China Key Laboratory of Testing Technology for Manufacturing Process Ministry of Education Southwest University of Science and Technology Mianyang621010 China MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China Chengdu610059 China

Steady-state visual evoked potentials (SSVEPs) based brain-computer interface (BCI) has received considerable attention due to its high information transfer rate (ITR) and available quantity of targets. However, the performance of frequency identification methods heavily hinges on the amount of user calibration data and data length, which hinders the deployment in real-world applications. Recently, generative adversarial networks (GANs)-based data generation methods have been widely adopted to create synthetic electroencephalography (EEG) data, holds promise to address these issues. In this paper, we proposed a GAN-based end-to-end signal transformation network for Time-window length Extension, termed as TEGAN. TEGAN transforms short-length SSVEP signals into long-length artificial SSVEP signals. By incorporating a novel U-Net generator architecture and an auxiliary classifier into the network architecture, the TEGAN could produce conditioned features in the synthetic data. Additionally, we introduced a two-stage training strategy and the LeCam-divergence regularization term to regularize the training process of GAN during the network implementation. The proposed TEGAN was evaluated on two public SSVEP datasets (a 4-class dataset and a 12-class dataset). With the assistance of TEGAN, the performance of traditional frequency recognition methods and deep learning-based methods have been significantly improved under limited calibration data. And the classification performance gap of various frequency recognition methods has been narrowed. This study substantiates the feasibility of the proposed method to extend the data length for short-time SSVEP signals for developing a high-performance BCI system. The proposed GAN-based methods have the great potential of shortening the calibration time and cutting down the budget for various real-world BCI-based applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

Concept transfer learning for adaptive language understanding

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhu, Su Yu, Kai Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

Semantic transfer is an important problem of the language understanding (LU), which is about how the recognition pattern of a semantic concept benefits other associated concepts. In this paper, we propose a new semantic representation based on combinatory concepts. Semantic slot is represented as a composition of different atomic concepts in different semantic dimensions. Specifically, we propose the concept transfer learning methods for extending combinatory concepts in LU. The concept transfer learning makes use of the common ground of combinatory concepts shown in the literal description. Our methods are applied to two adaptive LU problems: semantic slot refinement and domain adaptation, and respectively evaluated on two benchmark LU datasets: ATIS and DSTC 2&3. The experiment results show that the concept transfer learning is very efficient for semantic slot refinement and domain adaptation in the LU. Copyright © 2017, The Authors. All rights reserved.

关键词： Semantics

FOCAL KL-DIVERGENCE BASED DILATED CONVOLUTIONAL NEURAL NETWORKS FOR CO-CHANNEL SPEAKER IDENTIFICATION

学校读者我要写书评

暂无评论

FOCAL KL-DIVERGENCE BASED DILATED CONVOLUTIONAL NEURAL NETWO...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Shuai Wang Yanmin Qian Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781538646595

Recognizing the identities of multiple talkers via their overlapped speech is a challenging task, it is also one main difficulty for the "cocktail party problem". In this paper, a novel dilated convolutional neural network with a focal KL-divergence loss function is proposed to tackle this problem. During training, relative loss for the well-classified samples is automatically reduced and consequently more attention is paid to the hard samples. The use of the focal KL-divergence loss function leads to more stable training and improved testing performance. Furthermore, a post processing of assigning different frames with different weights is also adopted and leads to further improvement. The proposed framework can be easily extended from 2-talker to 3-talker speaker identification scenario. Experiments on the artificially generated RSR2015 multi-talker mixed corpus show that the proposed approach can improve multi-talker speaker identification significantly.

关键词： co-channel speaker identification convolutional neural networks focal loss dilated convolution Loudspeakers Neural network speaker recognition personal identity

SEMI-SUPERVISED TRAINING USING ADVERSARIAL MULTI-TASK LEARNING FOR SPOKEN LANGUAGE UNDERSTANDING

学校读者我要写书评

暂无评论

SEMI-SUPERVISED TRAINING USING ADVERSARIAL MULTI-TASK LEARNI...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Ouyu Lan Su Zhu Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781538646595

Spoken language understanding (SLU) usually requires human semantic annotation on collected data, but the process is expensive. In order to make better use of unlabeled data for robust SLU, we propose an adversarial multi-task learning method by merging a bidirectional language model (BLM) and a slot tagging model (STM). As a secondary objective, the BLM is used to learn generalized and unsupervised knowledge with abundant unlabeled data and improve the performance of STM on unseen data samples. We construct a shared space for both tasks and independent private spaces for each task respectively. Additional adversarial task discriminator is also used to obtain more task-independent sharing information. Experiments show that the proposed approaches achieve the state-of-the-art performance on the small scale ATIS benchmark and significantly improve the semi-supervised performance on a large-scale dataset.

关键词： Spoken language understanding Multitask learning Semi-supervised learning Adversarial task discriminator spoken language understanding Semi-supervised Learning STACK TRITIUM MONITOR Scanning Tunneling Microscope Data sampling BLM gene Data Collection Methods

An investigation on deep learning with Beta stabilizer

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Qi Tan, Tian Yu, Kai Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

Artificial neural networks (ANN) have been used in many applications such like handwriting recognition and speech recognition. It is well-known that learning rate is a crucial value in the training procedure for artificial neural networks. It is shown that the initial value of learning rate can confoundedly affect the final result and this value is always set manually in practice. A new parameter called beta stabilizer has been introduced to reduce the sensitivity of the initial learning rate. But this method has only been proposed for deep neural network (DNN) with sigmoid activation function. In this paper we extended beta stabilizer to long short-term memory (LSTM) and investigated the effects of beta stabilizer parameters on different models, including LSTM and DNN with relu activation function. It is concluded that beta stabilizer parameters can reduce the sensitivity of learning rate with almost the same performance on DNN with relu activation function and LSTM. However, it is shown that the effects of beta stabilizer on DNN with relu activation function and LSTM are fewer than the effects on DNN with sigmoid activation function. Copyright © 2020, The Authors. All rights reserved.

关键词： Long short-term memory

GaitSet: Regarding gait as a set for cross-view gait recognition

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Chao, Hanqing He, Yiwei Zhang, Junping Feng, JianFeng Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China

As a unique biometric feature that can be recognized at a distance, gait has broad applications in crime prevention, forensic identification and social security. To portray a gait, existing gait recognition methods utilize either a gait template, where temporal information is hard to preserve, or a gait sequence, which must keep unnecessary sequential constraints and thus loses the flexibility of gait recognition. In this paper we present a novel perspective, where a gait is regarded as a set consisting of independent frames. We propose a new network named GaitSet to learn identity information from the set. Based on the set perspective, our method is immune to permutation of frames, and can naturally integrate frames from different videos which have been filmed under different scenarios, such as diverse viewing angles, different clothes/carrying conditions. Experiments show that under normal walking conditions, our single-model method achieves an average rank-1 accuracy of 95.0% on the CASIA-B gait dataset and an 87.1% accuracy on the OU-MVLP gait dataset. These results represent new state-of-the-art recognition accuracy. On various complex scenarios, our model exhibits a significant level of robustness. It achieves accuracies of 87.2% and 70.4% on CASIA-B under bag-carrying and coat-wearing walking conditions, respectively. These outperform the existing best methods by a large margin. The method presented can also achieve a satisfactory accuracy with a small number of frames in a test sample, e.g., 82.5% on CASIA-B with only 7 frames. The source code has been released at https://***/AbnerHqC/GaitSet. Copyright © 2018, The Authors. All rights reserved.

关键词： Gait analysis