Supervised Sequence Labelling

By Alex Graves. 2012

585 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Financial Time Series Prediction Using Deep Learning (2017, methodology): “…techniques were successfully applied to a gamut of problems such as computer vision [16, 17], automatic speech recognition [18, 19], natural language processing [20, 21, 22], hand-writing recognition [23], and bio-informatics [24], to name a few, outperforming contemporary state-of-the-art schemes.”
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, positive): “The negative log-likelihood loss function [70] is adopted to measure the difference between the true class label y and the prediction result ŷ.”
Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station (2020, background): “This implies that there is a nonlinear interrelationship among parameters (Graves 2012; Jozefowicz et al. 2015; Kavitha et al. 2016) and the selected parameter does not follow a linear path within selected sequential timeslots (Bishop 2006; McCREA et al. 2005).”
Interacting with Soli: Exploring Fine-Grained Dynamic Gesture Recognition in the Radio-Frequency Spectrum (2016, background): “Recently they have been outperformed by recurrent neural networks (RNNs) [9], augmented with Long short-term memory (LSTM) [10] cells.”
End-to-end Feedback Loss in Speech Chain Framework via Straight-through Estimator (2018, methodology): “To reduce the memory consumption and processing time, we used hierarchical sub-sampling [17, 18] on all three Bi-LSTM layers and reduced the sequence length by a factor of eight.”
Learning Text Similarity with Siamese Recurrent Networks (2016, background): “…and below the logistic function is denoted by σ The Long Short-Term Memory (Hochreiter and Schmidhuber, 1997) variant of RNNs in particular has had success in tasks related to natural language processing, such as text classiﬁcation (Graves, 2012) and language translation (Sutskever et al., 2014).”
EA-LSTM: Evolutionary Attention-based LSTM for Time Series Prediction (2018, methodology): “Furthermore, we can learn the nonliner mapping function by these formulations [ Graves, 2012 ] of the calculating process in LSTMs cells as follows: where σ ( · ) represents the activation function of sigmoid and W matrices with double subscript the connection weights be-tween the two cells.”
Granger Causality: A Review and Recent Advances (2021, methodology): “:( t K ) , for some lag K , or a recurrent network, like an LSTM, that does not require specifying the lag order.”
EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks (2017, methodology): “…neural networks (RNNs), a type of networks suitable for handling time-series data like speech (Graves et al., 2013) or handwriting recognition (Graves, 2012; Graves and Schmidhuber, 2009), have also been used successfully for sentiment analysis (Ren et al., 2016; Liu et al., 2015; Tai et al.,…”
Neural Granger Causality (2021, methodology): “Due to their effectiveness at modeling complex time dependencies, we choose to model the recurrent function f using an LSTM [26].”
Meta-learning of Sequential Strategies (2019, methodology): “…we use a memory-based architecture, such as a recurrent neural network [Elman, 1990, Jordan, 1997, Hochreiter et al., 2001, Kolen and Kremer, 2001, Graves, 2012], then the function f conforms to the interface where π t ∈ ∆( X ) is the current prediction vector, m t and m t − 1 ∈ M are the…”
Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling (2018, methodology): “The sequence-to-sequence (seq2seq) model proposed in [1, 2, 3] is a neural architecture for performing sequence classiﬁcation and later adopted to perform speech recognition in [4, 5, 6].”
DeepNano: Deep recurrent neural networks for base calling in MinION nanopore reads (2016, methodology): “g using deep recurrent neural networks In this section, we describe the design of our basecaller, which is based on deep recurrent neural networks. A recurrent neural network (Lee Giles et al., 1994; Graves, 2012) is a type of articial neural network used for sequence labeling. Given a sequence of i”
Global Context-Aware Attention LSTM Networks for 3D Action Recognition (2017, methodology): “(9) The negative log-likelihood loss function [13] is used to measure the difference between the true label y and the predicted result ŷ.”