Deep Learning using Support Vector Machines
By Yichuan Tang. 2013
199 citations recorded by the source corpus.
Subfields: Model Architectures, Optimization & Training
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Model Architectures
- Sergi Valverde
- Sarah Monazam Erfani
- Sutharshan Rajasegarar
- C. Leckie
- Fabio Roli
- Giorgio Fumera
- Xavier Lladó
- Vittorio Murino
In Optimization & Training
- Sergi Valverde
- Robert Marti
- Sarah Monazam Erfani
- Gavin Brown
- Battista Biggio
- Sutharshan Rajasegarar
- C. Leckie
- Fabio Roli
Citations in the corpus
- Towards Deep Neural Network Architectures Robust to Adversarial Examples (2014, methodology): “However, performance is suboptimal compared to state-of-the-art DNNs, possibly due to lack of end-to-end training Vinyals et al. (2012); Tang (2013).”
- Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid (2017, background): “Notably, previous work has shown that replacing the softmax layer in deep networks with a multiclass SVM can be effective also in different applications [27].”
- When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “convolutional kernel networks [23], SVM neural networks [33]).”
- Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review (2017, background): “fiers. Hinge loss is another type of loss function, which in conjunction with margin-based classifiers was reported to perform better than cross-entropy loss in a standard image classification challenge [75]. More recently, the research in [76] proposed a Large-Margin Softmax Loss (L-softmax), which is”
- Deep Facial Expression Recognition: A Survey (2018, background): “Alternatively, [93] demonstrated the benefit of using a linear support vector”
- High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning (2016, methodology): “, a DBN in combination with labelled SVMs such as binary or multiclass SVMs) have been used in several application domains, such as object classification [14], text classification [27], music classification [29], face expression recognition [41], and speech separation [42].”