Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data
February 18, 2016 Β· Entered Twilight Β· π IEEE International Joint Conference on Neural Network
"Last commit was 8.0 years ago (β₯5 year threshold)"
Evidence collected by the PWNC Scanner
Repo contents: CRNN.py, README.md, license.txt
Authors
Gil Keren, BjΓΆrn Schuller
arXiv ID
1602.05875
Category
stat.ML: Machine Learning (Stat)
Cross-listed
cs.CL
Citations
154
Venue
IEEE International Joint Conference on Neural Network
Repository
https://github.com/cruvadom/Convolutional-RNN
β 32
Last Checked
1 month ago
Abstract
Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by feeding patches of the data into a recurrent neural network and using the outputs or hidden states of the recurrent units to compute the extracted features. By doing so, we exploit the fact that a window containing a few frames of the sequential data is a sequence itself and this additional structure might encapsulate valuable information. In addition, we allow for more steps of computation in the feature extraction process, which is potentially beneficial as an affine function followed by a non-linearity can result in too simple features. Using our convolutional recurrent layers we obtain an improvement in performance in two audio classification tasks, compared to traditional convolutional layers. Tensorflow code for the convolutional recurrent layers is publicly available in https://github.com/cruvadom/Convolutional-RNN.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Machine Learning (Stat)
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Distilling the Knowledge in a Neural Network
R.I.P.
π»
Ghosted
Layer Normalization
R.I.P.
π»
Ghosted
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
R.I.P.
π»
Ghosted
Domain-Adversarial Training of Neural Networks
R.I.P.
π»
Ghosted