Monotonic Multi-layer Perceptron Networks as Universal Approximators

By B. Lang. 2005

78 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. Bernhard Schölkopf
2. Biwei Huang
3. Kun Zhang
4. Bernie Wang
5. Jan Gasthaus
6. Tim Januschowski
7. Hao Wang
8. Syama Sundar Rangapuram

Citations in the corpus

• Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation (2020, background): “In experiments, this strict monotonicity can be easily implemented through monotonic multi-layer perceptron network [21], in which positive signs of the weights are guaranteed by introducing their exponential form [22].”
• Probabilistic Forecasting with Spline Quantile Function RNNs (2019, methodology): “While the general framework is applicable to other choices of Q (see e.g (Lang, 2005) for some other options), we focus on linear isotonic regression splines here.”