Large‐scale data mining using genetics‐based machine learning

Bacardit, Jaume; Llorí, Xavier

doi:10.1002/widm.1078

Cited by 57 publications

(8 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods that infer a network as a whole are therefore more biologically interpretable, because they remove these indirect correlations. A large number of such methods have been described, as reviewed in [66, 67]. …”

Section: Modeling Dependence Among Examplesmentioning

confidence: 99%

Machine learning applications in genetics and genomics

2015

View full text Add to dashboard Cite

The field of machine learning promises to enable computers to assist humans in making sense of large, complex data sets. In this review, we outline some of the main applications of machine learning to genetic and genomic data. In the process, we identify some recurrent challenges associated with this type of analysis and provide general guidelines to assist in the practical application of machine learning to real genetic and genomic data.

show abstract

Section: Modeling Dependence Among Examplesmentioning

confidence: 99%

Machine learning applications in genetics and genomics

2015

View full text Add to dashboard Cite

show abstract

“…Within the LCS literature, scalability and learning speed have been largely synonymous targets for improvement [2,27,6,1,17,26,5]. Much of the progress in dealing with scalability to date has been made in the development of Pittsburgh-style LCS architectures [2,6,1,17,5].…”

Section: Introductionmentioning

confidence: 99%

“…Much of the progress in dealing with scalability to date has been made in the development of Pittsburgh-style LCS architectures [2,6,1,17,5]. The term scalability can refer to an algorithms ability to handle different types of increased size in the training environment.…”

Section: Introductionmentioning

confidence: 99%

“…To date, strategies to improve LCS scalability have included parallelization of the algorithm [17,33], more efficient rule representations [1,3,24], more efficient matching [27], running the algorithm as an ensemble where individual runs have access to only a subset of available attributes in the dataset [5], extracting and using building blocks from smaller problems [23], applying expert knowledge to bias the algorithm towards attribute more likely to be of predictive value [43,41], and using windowing mechanisms in Pittsburgh LCSs to learn incrementally [2]. …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ExSTraCS 2.0: description and evaluation of a scalable learning classifier system

2015

View full text Add to dashboard Cite

Algorithmic scalability is a major concern for any machine learning strategy in this age of ‘big data’. A large number of potentially predictive attributes is emblematic of problems in bioinformatics, genetic epidemiology, and many other fields. Previously, ExS-TraCS was introduced as an extended Michigan-style supervised learning classifier system that combined a set of powerful heuristics to successfully tackle the challenges of classification, prediction, and knowledge discovery in complex, noisy, and heterogeneous problem domains. While Michigan-style learning classifier systems are powerful and flexible learners, they are not considered to be particularly scalable. For the first time, this paper presents a complete description of the ExS-TraCS algorithm and introduces an effective strategy to dramatically improve learning classifier system scalability. ExSTraCS 2.0 addresses scalability with (1) a rule specificity limit, (2) new approaches to expert knowledge guided covering and mutation mechanisms, and (3) the implementation and utilization of the TuRF algorithm for improving the quality of expert knowledge discovery in larger datasets. Performance over a complex spectrum of simulated genetic datasets demonstrated that these new mechanisms dramatically improve nearly every performance metric on datasets with 20 attributes and made it possible for ExSTraCS to reliably scale up to perform on related 200 and 2000-attribute datasets. ExSTraCS 2.0 was also able to reliably solve the 6, 11, 20, 37, 70, and 135 multiplexer problems, and did so in similar or fewer learning iterations than previously reported, with smaller finite training sets, and without using building blocks discovered from simpler multiplexer problems. Furthermore, ExS-TraCS usability was made simpler through the elimination of previously critical run parameters.

show abstract

“…While successful, this study was performed on a relatively small dataset, and the computation was aided by a 1576 processor cluster, a resource to which few researchers may have access. Due to the complexity of LCS and the demands of large-scale data mining, the issue of scalability remains both a key challenge and opportunity for the LCS research community [4]. …”

Section: Introductionmentioning

confidence: 99%

A multi-core parallelization strategy for statistical significance testing in learning classifier systems

2013

View full text Add to dashboard Cite

Permutation-based statistics for evaluating the significance of class prediction, predictive attributes, and patterns of association have only appeared within the learning classifier system (LCS) literature since 2012. While still not widely utilized by the LCS research community, formal evaluations of test statistic confidence are imperative to large and complex real world applications such as genetic epidemiology where it is standard practice to quantify the likelihood that a seemingly meaningful statistic could have been obtained purely by chance. LCS algorithms are relatively computationally expensive on their own. The compounding requirements for generating permutation-based statistics may be a limiting factor for some researchers interested in applying LCS algorithms to real world problems. Technology has made LCS parallelization strategies more accessible and thus more popular in recent years. In the present study we examine the benefits of externally parallelizing a series of independent LCS runs such that permutation testing with cross validation becomes more feasible to complete on a single multi-core workstation. We test our python implementation of this strategy in the context of a simulated complex genetic epidemiological data mining problem. Our evaluations indicate that as long as the number of concurrent processes does not exceed the number of CPU cores, the speedup achieved is approximately linear.

show abstract

Large‐scale data mining using genetics‐based machine learning

Cited by 57 publications

References 88 publications

Machine learning applications in genetics and genomics

Machine learning applications in genetics and genomics

ExSTraCS 2.0: description and evaluation of a scalable learning classifier system

A multi-core parallelization strategy for statistical significance testing in learning classifier systems

Contact Info

Product

Resources

About