Improved pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines

32 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.

Deep Learning: Methods and Applications (2014, methodology): “The use of SESM in pre-training DNNs for speech recognition can be found in [284].”
Hierarchical Convolutional Deep Learning in Computer Vision (2013, background): “This challenge continues to motivate researchers to design better unsupervised algorithms [95, 107] and better optimization methods for training deep neural nets [29,63].”
Context-Dependent MLPs for LVCSR: TANDEM, Hybrid or Both? (2012, background): “In order to remedy the convergence difficulties arising from the deep structure, different MLP pre-training algorithms [5, 6, 7] have been proposed.”
On rectified linear units for speech processing (2013, background): “This challenge continued to motivate researchers to design better unsupervised algorithms [3, 4] and better optimization methods for training deep neural nets [5, 6].”
Deep Neural Networks for Acoustic Modeling in Speech Recognition (2012, methodology): “For speech recognition, improved performance was achieved on both TIMIT and Broadcast News tasks by pretraining with a type of autoencoder that tries to find sparse codes [56].”
Phone recognition with hierarchical convolutional deep maxout networks (2015, unknown): “DNN with BMMI features (CD) [50] 19.”