A Survey of Modern Questions and Challenges in Feature Extraction

By Dmitry Storcheus, Afshin Rostamizadeh, Sanjiv Kumar. 2015

68 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.

1. Elias Boutros Khalil
2. Xiaoyong Yuan
3. Qile Zhu
4. Udayan Khurana
5. Xiaolin Li
6. Marc-André Zöller
7. Horst Samulowitz
8. Deepak S. Turaga

Citations in the corpus

• Adversarial Examples: Attacks and Defenses for Deep Learning (2017, background): “For conventional ML algorithms, it is difficult to extract well-represented features due to limitations, such as curse of dimensionality [37], computational bottleneck [38], and requirement of the domain and expert knowledge.”
• Learning Feature Engineering for Classification (2017, background): “While they do not explicitly work on input features and transformations, they generate new features as means to solving another problem [Storcheus et al. , 2015].”
• Feature Engineering for Predictive Modeling using Reinforcement Learning (2017, methodology): “A recent survey on the topic appears can be found here (Storcheus, Rostamizadeh, and Kumar 2015).”