Modeling temporal dependencies in data using a DBN-LSTM

By Raunaq Vohra, Kratarth Goel, Jajati Keshari Sahoo. 2015

34 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

Citations in the corpus

• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling (2018, neutral): “Note however that other models such as the Deep Belief Net LSTM perform better still (Vohra et al., 2015); we believe this is likely due to the fact that the datasets are relatively small, and thus the right regularization method or generative modeling procedure can improve performance significantly.”
• Convolutional Sequence Modeling Revisited (2018, unknown): “Note however that other models such as the Deep Belief Net LSTM (Vohra et al., 2015) perform substantially better on this task; we believe this is likely due to the fact that the datasets involved in polyphonic music are relatively small, and thus the right regularization method or generative modeli”