Bidirectional LSTM Convolutional Neural Network (BLSTM-CNN)
Jump to navigation
Jump to search
A Bidirectional LSTM Convolutional Neural Network (BLSTM-CNN) is a LSTM convolutional network that is a bi-LSTM network.
- Context:
- It can be trained by a Bidirectional LSTM Convolutional Neural Network Training System (that implements a Bidirectional LSTM Convolutional Neural Network Training Algorithm).
- Example(s):
- Counter-Example(s)
- See: LSTM, Artificial Neural Network, Bidirectional Recurrent Neural Network, Stacked Bidirectional and Unidirectional LSTM (SBU-LSTM) Neural Network.
References
2018
- (Kim, 2018) ⇒ Kyungna Kim (2018). "Arrhythmia Classification in Multi-Channel ECG Signals Using Deep Neural Networks".
- QUOTE:To utilize both the pattern recognition afforded by deep CNNs and the temporal learning ability of LSTMs, we also train an additional architecture that combines them into a single model. We begin with a stacked LSTM to extract temporal structures from the data, and instead of feeding the unrolled hidden state into another LSTM layer, we feed it as input into a (deep) CNN to extract localized features. In the combined model, we begin by feeding the data into a 2-layer LSTM. The output of the final LSTM layer is treated as a one-dimensional image of size (100 × 600), and fed into a CNN to extract localized features. We also train a similar architecture with a bidirectional 2-layer LSTM, where the image is of size (200×600). Full high-level architecture of our combined network is shown in figure 3.4.
- QUOTE:To utilize both the pattern recognition afforded by deep CNNs and the temporal learning ability of LSTMs, we also train an additional architecture that combines them into a single model. We begin with a stacked LSTM to extract temporal structures from the data, and instead of feeding the unrolled hidden state into another LSTM layer, we feed it as input into a (deep) CNN to extract localized features. In the combined model, we begin by feeding the data into a 2-layer LSTM. The output of the final LSTM layer is treated as a one-dimensional image of size (100 × 600), and fed into a CNN to extract localized features. We also train a similar architecture with a bidirectional 2-layer LSTM, where the image is of size (200×600). Full high-level architecture of our combined network is shown in figure 3.4.
