Probabilistic Incremental Program Evolution

By Rafal Salustowicz, J. Urgen Schmidhuber. 1997

How researchers see this paper

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

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “raph-like programs, including NNs (Khan et al., 2010) and their topology (Turner and Miller, 2013). Related methods include probability distributionbased EAs (Baluja, 1994; Saravanan and Fogel, 1995; Sałustowicz and Schmidhuber, 1997; Larraanaga 27 and Lozano, 2001), Covariance Matrix Estimation Evo”
Optimal Ordered Problem Solver (2002, neutral): “For instance, we could plug in a time-consuming algorithm such as Probabilistic Incremental Program Evolution ( Salustowicz & Schmidhuber, 1997, 1998; Salustowicz, Wiering, & Schmidhuber, 1998).”
Improving Symbolic Regression with Interval Arithmetic and Linear Scaling (2003, methodology): “Salustowicz and Schmidhuber report that the best error achieved on problem 4 by their PIPE system was a sum of absolute errors of 1.18 using 20 runs of 100,000 evaluations in length [ 13 ].”
Order of Nonlinearity as a Complexity Measure for Models Generated by Symbolic Regression via Pareto Genetic Programming (2009, background): “The second function originates from [43]; we call it the Salustowicz function.”
Semantically-based crossover in genetic programming: application to real-valued symbolic regression (2011, methodology): “16 In fact one simple way to use our method is to transform boolean function learning problems to realvalued ones as in [54].”
A Survey of Optimization by Building and Using Probabilistic Models (2000, methodology): “In the probabilistic incremental program evolution (PIPE) algorithm (Salustowicz & Schmidhuber , 1997) computer programs or mathematical functions are evolved as like in genetic programming (Koza, 1992).”
A Field Guide to Genetic Programming (2008, methodology): “The first EDA-type GP system was effectively an extension of PBIL to trees called probabilistic incremental program evolution (PIPE) (Salustowicz and Schmidhuber, 1997; Sa lustowicz, Wiering, and Schmidhuber, 1998; Salustowicz and Schmidhuber, 1999).”
Time-series forecasting using flexible neural tree model (2005, methodology): “The hierarchical structure is evolved using probabilistic incremental program evolution algorithm (PIPE) [12,13] with specific instructions.”