Learning the Chinese Sentence Representation with LSTM Autoencoder

Chen, Mu-Yen; Huang, Tien‐Chi; Shu, Yang; Chen, Chia-Chen; Hsieh, Tsung-Che; Yen, Neil Y.

doi:10.1145/3184558.3186355

Cited by 6 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motivated by [17] and [18], as well as our work in a different domain [19], we propose a novel LSTM denoising auto-encoder for modulation classification wherein the auto-encoder and classifier are trained simultaneously. Fig.…”

Section: An Lstm Denoising Auto-encodermentioning

confidence: 99%

Real-Time Radio Modulation Classification With An LSTM Auto-Encoder

Vikalo

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Identifying modulation type of a received radio signal is a challenging problem encountered in many applications including radio interference mitigation and spectrum allocation. This problem is rendered challenging by the existence of a large number of modulation schemes and numerous sources of interference. Existing methods for monitoring spectrum readily collect large amounts of radio signals. However, existing state-of-the-art approaches to modulation classification struggle to reach desired levels of accuracy with computational efficiency practically feasible for implementation on low-cost computational platforms. To this end, we propose a learning framework based on an LSTM denoising autoencoder designed to extract robust and stable features from the noisy received signals, and detect the underlying modulation scheme. The method uses a compact architecture that may be implemented on low-cost computational devices while achieving or exceeding state-of-the-art classification accuracy. Experimental results on realistic synthetic and over-the-air radio data show that the proposed framework reliably and efficiently classifies radio signals, and often significantly outperform state-of-the-art approaches.

show abstract

Section: An Lstm Denoising Auto-encodermentioning

confidence: 99%

Real-Time Radio Modulation Classification With An LSTM Auto-Encoder

Vikalo

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…where α is the weight parameter for the losses. Thanks to the reconstruction loss in the combined loss function, the LSTM parameters will be optimized so that the state vector encodes the necessary information to reconstruct the sequences and the features discriminating the anomalous inputs [34]. Although the RNNs were used as an unsupervised feature extracting stage in conjunction with regression and classification stages, thanks to the SVDD, our approach is able to remain fully unsupervised.…”

Section: Joint Optimization Of the Feature Extraction And The Outlier...mentioning

confidence: 99%

“…Randomly initialize the One-Class Classifier. while X arrives do H (33) Compute parameter update (34) end while Although Algorithm 1 requires the whole training set for the parameter optimization, we introduce an algorithm for the online setup where we update the model parameters with a single observed sequence. This procedure is given in Algorithm 2.…”

Section: Algorithm 2 Online Anomaly Detection Training Algorithmmentioning

confidence: 99%

Unsupervised Online Anomaly Detection On Irregularly Sampled Or Missing Valued Time-Series Data Using LSTM Networks

Karaahmetoglu,

Ilhan,

Balaban

et al. 2020

Preprint

View full text Add to dashboard Cite

We study anomaly detection and introduce an algorithm that processes variable length, irregularly sampled sequences or sequences with missing values. Our algorithm is fully unsupervised, however, can be readily extended to supervised or semi-supervised cases when the anomaly labels are present as remarked throughout the paper. Our approach uses the Long Short Term Memory (LSTM) networks in order to extract temporal features and find the most relevant feature vectors for anomaly detection. We incorporate the sampling time information to our model by modulating the standard LSTM model with time modulation gates. After obtaining the most relevant features from the LSTM, we label the sequences using a Support Vector Data Descriptor (SVDD) model. We introduce a loss function and then jointly optimize the feature extraction and sequence processing mechanisms in an end-to-end manner. Through this joint optimization, the LSTM extracts the most relevant features for anomaly detection later to be used in the SVDD, hence completely removes the need for feature selection by "expert" knowledge. Furthermore, we provide a training algorithm for the online setup, where we optimize our model parameters with individual sequences as the new data arrives. Finally, on real-life datasets, we show that our model significantly outperforms the standard approaches thanks to its combination of LSTM with SVDD and joint optimization.

show abstract