Deep Convex Net: A Scalable Architecture for Speech Pattern Classification

By Dong Yu, Li Deng. 2011

165 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Li Deng
2. Dong Yu
3. Jinyu Li
4. Yoshua Bengio
5. Jianfeng Gao
6. Xiaodong He
7. Tara N. Sainath
8. Quoc V. Le

In Computer Vision and Pattern Recognition

1. Li Deng
2. Luc Van Gool
3. Dacheng Tao
4. Trevor Darrell
5. Xiaogang Wang
6. Andrew Zisserman
7. Jitendra Malik
8. Jianfeng Gao

Citations in the corpus

• A survey of deep neural network architectures and their applications (2017, background): “Hence, Deng and Yu [35] pr oposed a novel deep architecture, referred to as deep convex networks (DCNs), to overcome the shortcomings in lea rning scalability.”
• Modeling temporal dependencies in data using a DBN-LSTM (2015, background): “The same goes for various other approaches that have tried to use deep architectures for speech recognition (as explained in [1], [2]).”
• Multi-Layer and Recursive Neural Networks for Metagenomic Classification (2015, unknown): “and signal processing [14], [15].”
• Acoustic Modeling With Hierarchical Reservoirs (2013, background): “Due to this, alternative deep architectures like Deep Convex Networks [44] or Deep Stacking Networks [12], [13] were proposed recently to overcome the scalability challenge of DBNs by solving convex learning problems in each module, allowing a faster parallel batch training.”
• Recent advances in deep learning for speech research at Microsoft (2013, methodology): “Following this approach, we recently explored the application of the deep stacking network or DSN [13][14] to this task.”
• Predicting speech recognition confidence using deep learning with word identity and score features (2013, background): “Section 4 presents the deep learning architectures in DNN and K-DCN.”
• Ensemble deep learning: A review (2021, methodology): “The authors showed that K-DCN performs better as compared to the DCN.”
• Tensor Switching Networks (2016, background): “Convex learning and inference in various deep architectures can be found in [11, 12, 13] too.”
• Scalable stacking and learning for building deep architectures (2012, background): “Some preliminary work and results for speech classification was presented in [10].”
• General Stochastic Networks for Classification (2014, methodology): “In order to solve the non-convex multi-objective optimization problem, variants of stochastic gradient descent (SGD) can be used.”
• Random features for Kernel Deep Convex Network (2013, methodology): “24 DCN ([3]) 6 (7000) 44.”