Original Contribution: Stacked generalization
By David Hilton Wolpert. 1992
Subfields: Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Representation & Self-Supervised Learning
- Yoshua Bengio
- Jianfeng Gao
- Li Deng
- Noah A. Smith
- Sebastian Ruder
- Martial Hebert
- Dong Yu
- Kyunghyun Cho
Citations in the corpus
- Some Improvements on Deep Convolutional Neural Network Based Image Classification (2013, background): “Because most of the predictions are very similar (almost collinear), methods such as stacking [9] or similar algorithms tend to have trouble and can create large weights of opposing sign.”
- The Right Tool for the Job: Matching Model and Instance Complexities (2020, methodology): “We also considered feeding the output of previous classifiers as additional features to subsequent classifiers, known as stacking (Wolpert, 1992).”
- The Second Dialog State Tracking Challenge (2014, neutral): “The second approach to ensemble learning is stacking (Wolpert, 1992).”
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (2016, background): “Optimizing the ensemble weights, as in stacking [60] or adaptive mixture of experts [28], can further improve the performance.”
- Deep learning in neural networks: An overview (2014, neutral): “…of Section 5.15, or hierarchical Kohonen nets (Section 5.6.4), to facilitate subsequent SL. Compare Stacked Generalization (Ting &Witten, 1997; Wolpert, 1992), and FNNs that profit from pre-training by competitive UL (e.g., Rumelhart & Zipser, 1986) prior to BP-based fine-tuning (Maclin &…”
- Benchmark and Survey of Automated Machine Learning Frameworks (2019, background): “An interesting approach for ensemble learning is stacking (Wolpert, 1992).”
- Survey on Automated Machine Learning (2019, background): “An interesting approach for ensemble learning is stacking (Wolpert, 1992).”
- Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “In order to achieve this, we use the idea of stacked training [27,23].”