Accelerated Parallelizable Neural Network Learning Algorithm for Speech Recognition

21 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 stacking networks for information retrieval (2013, unknown): “The weight matrices of the DSN in each module can be further learned using batch-mode gradient descent [16].”
A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition (2012, methodology): “The lower-layer weight matrix W can be optimized using an accelerated gradient descent [7, 8] algorithm to minimize the squared error”
An Overview of Deep-Structured Learning for Information Processing (2011, methodology): “Higher accuracy than DBN is reported, especially after a ―fine-tuning‖ technique developed in (Yu and Deng, 2011) is exploited.”
A fast maximum likelihood nonlinear feature transformation method for GMM-HMM speaker adaptation (2014, methodology): “ELM has been used as building blocks for example in the deep convex network (DCN) [15,16].”