Population-Based Incremental Learning: A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning

By Shumeet Baluja. 1994

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, methodology): “Related methods include probability distributionbased EAs (Baluja, 1994; Larraanaga & Lozano, 2001; Sałustowicz & Schmidhuber, 1997; Saravanan & Fogel, 1995), Covariance Matrix Estimation Evolution Strategies (CMA-ES) (Hansen, Müller, & Koumoutsakos, 2003; Hansen & Ostermeier, 2001; HeidrichMeisner ”
Local Rule-Based Explanations of Black Box Decision Systems (2018, background): “arning. We aim instead at generating new instances that separate well the decision boundary of the black box b. The usage of classifiers within fitness functions of genetic algorithms can be found in [5, 8, 12, 41]. However, the classifier they use is always the one for which the population must be ”
Hybrid Genetic Algorithms: A Review (2006, methodology): “Population based incremental learning (PBIL) [67], univariate marginal distribution algorithm (UMDA), compact genetic algorithm (CGA), bivariate marginal distribution algorithms (BMDA), factorized distribution algorithms (FDA) and the Bayesian optimisation algorithm (BOA) [68] are all examples of…”
Classifier selection for majority voting (2005, methodology): “Other evolutionary based selection approaches including tabu search [11,28,30], population-based incremental learning [1,30],”
Optimizing connection weights in neural networks using the whale optimization algorithm (2016, background): “For the veriﬁcation of the results, a set of conventional, evolutionary, and swarm-based training algorithms were employed: BP, GA, PSO, ACO, DE, and PBIL.”
Evolutionary Computation Meets Machine Learning: A Survey (2011, methodology): “In the literature, statistical methods [33], competitive learning techniques [34], Bayesian network [35], and linkage learning techniques [36] are reportedly being used to improve probability models.”
The compact genetic algorithm (1998, unknown): “Population-based incremental learning (PBIL) was introduced by Baluja [2], [3].”
Time-series forecasting using flexible neural tree model (2005, unknown): “PIPE combines probability vector coding of program instructions, population-based incremental learning [14], and tree-coded programs.”
A survey on optimization metaheuristics (2013, methodology): “Common univariate EDAs include Population Based Incremental Learning (PBIL)[14], Univariate Marginal Distribution Algorithm (UMDA) [188] and Compact Genetic Algorithm (cGA) [125].”
BOA: the Bayesian optimization algorithm (1999, methodology): “This is the basic principle of the population based incremental learning (PBIL) algorithm (Baluja, 1994), the compact genetic algorithm (cGA) (Harik et al.”
Cooperative Co-Evolution With Differential Grouping for Large Scale Optimization (2014, background): “Estimation of distribution algorithms [41], [42] fall into this category.”
Experimental study on population-based incremental learning algorithms for dynamic optimization problems (2005, methodology): “The Population-Based Incremental Learning (PBIL) algorithm, first proposed by Baluja [3], is a combination of evolutionary optimization and competitive learning.”
Linkage Problem, Distribution Estimation, and Bayesian Networks (2000, methodology): “…there has been a growing interest in optimization methods that explicitly model the good solutions found so far and use the constructed model to guide the further search (Baluja, 1994; Mühlenbein and Paaß, 1996; Mühlenbein, 1997; Harik et al., 1998; Pelikan and Mühlenbein, 1999; Harik, 1999).”