Learning from inconsistent and noisy data: The AQ18 approach

Kaufman, Kenneth A.; Michalski, Ryszard S.

doi:10.1007/bfb0095128

Cited by 36 publications

(24 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some decision trees learners are CART [7], ID3 [67], C4.5 [65], T1 [41], and C5.0 [73]. Example rule learners are the AQ family of algorithms [42], [56], INDUCE [30], FOIL [68], REP [24], C4.5 rules [65], IREP [37], RISE [31], RIPPER [25], [27], DiVS [75], BEXA [77], DLG [80], SLIPPER [23], LAD [5], LERILS [14], and IREP++ [29]. Hybrid learners are represented by the CN2 [21], [22], and CLIP family of algorithms [16], [19].…”

Section: State-of-the-art Rule Induction and Decision Treesmentioning

confidence: 99%

Highly scalable and robust rule learner: performance evaluation and comparison

Kurgan

Cios

Dick

2006

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

Abstract-Business intelligence and bioinformatics applications increasingly require the mining of datasets consisting of millions of data points, or crafting real-time enterprise-level decision support systems for large corporations and drug companies. In all cases, there needs to be an underlying data mining system, and this mining system must be highly scalable. To this end, we describe a new rule learner called DataSqueezer. The learner belongs to the family of inductive supervised rule extraction algorithms. DataSqueezer is a simple, greedy, rule builder that generates a set of production rules from labeled input data. In spite of its relative simplicity, DataSqueezer is a very effective learner. The rules generated by the algorithm are compact, comprehensible, and have accuracy comparable to rules generated by other state-of-the-art rule extraction algorithms. The main advantages of DataSqueezer are very high efficiency, and missing data resistance. DataSqueezer exhibits log-linear asymptotic complexity with the number of training examples, and it is faster than other state-ofthe-art rule learners. The learner is also robust to large quantities of missing data, as verified by extensive experimental comparison with the other learners. DataSqueezer is thus well suited to modern data mining and business intelligence tasks, which commonly involve huge datasets with a large fraction of missing data.

show abstract

Section: State-of-the-art Rule Induction and Decision Treesmentioning

confidence: 99%

Highly scalable and robust rule learner: performance evaluation and comparison

Kurgan

Cios

Dick

2006

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

show abstract

“…In Machine Learning mode, LEM1 employs an AQ-type learner (specifically, AQ15; Wnek et al, 1995, Kaufman & Michalski, 1999. In Darwinian Evolution mode, LEM1 uses a simple genetic algorithm, GA2 (Section 3.4).…”

Section: An Overviewmentioning

confidence: 99%

“…At present, we are in the process of completing and experimenting with a new system, LEM2. In Machine Learning mode, LEM2 uses AQ18 learner (an enhancement of AQ15c; Kaufman & Michalski, 1999), and in Darwinian Evolution mode uses an evolutionary algorithm EV. The following subsections describe briefly the AQ learning process and evolutionary algorithms used in the experiments.…”

Section: An Overviewmentioning

confidence: 99%

“…The latter feature enables the program to automatically search for a better representation space when the original one is found inadequate. For more details on the recent work on AQ learning consult (Kaufman & Michalski, 1999;Michalski, to appear). As mentioned earlier, an H-group and an L-group in LEM may logically intersect, that is, contain inconsistent examples.…”

Section: Aq Learningmentioning

confidence: 99%

See 1 more Smart Citation

Untitled

Michalski

2000

Machine Learning

Self Cite

177

View full text Add to dashboard Cite

Abstract.A new class of evolutionary computation processes is presented, called Learnable Evolution Model or LEM. In contrast to Darwinian-type evolution that relies on mutation, recombination, and selection operators, LEM employs machine learning to generate new populations. Specifically, in Machine Learning mode, a learning system seeks reasons why certain individuals in a population (or a collection of past populations) are superior to others in performing a designated class of tasks. These reasons, expressed as inductive hypotheses, are used to generate new populations. A remarkable property of LEM is that it is capable of quantum leaps ("insight jumps") of the fitness function, unlike Darwinian-type evolution that typically proceeds through numerous slight improvements. In our early experimental studies, LEM significantly outperformed evolutionary computation methods used in the experiments, sometimes achieving speed-ups of two or more orders of magnitude in terms of the number of evolutionary steps. LEM has a potential for a wide range of applications, in particular, in such domains as complex optimization or search problems, engineering design, drug design, evolvable hardware, software engineering, economics, data mining, and automatic programming.

show abstract

“…Discretization is often performed prior to the learning process and has played an important role in data mining and knowledge discovering. For example, many classification algorithms as AQ [1], CLIP [2], and CN2 [3] are only designed for category data, therefore, numerical data are usually first discretized before being processed by these classification algorithms. Assume A is one of the continuous attributes of a dataset, A can be discretized into n intervals as…”

Section: Introductionmentioning

confidence: 99%

A Discretization Algorithm for Uncertain Data

Xia

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper proposes a new discretization algorithm for uncertain data. Uncertainty is widely spread in real-world data. Numerous factors lead to data uncertainty including data acquisition device error, approximate measurement, sampling fault, transmission latency, data integration error and so on. In many cases, estimating and modeling the uncertainty for underlying data is available and many classical data mining algorithms have been redesigned or extended to process uncertain data. It is extremely important to consider data uncertainty in the discretization methods as well. In this paper, we propose a new discretization algorithm called UCAIM (Uncertain Class-Attribute Interdependency Maximization). Uncertainty can be modeled as either a formula based or sample based probability distribution function (pdf). We use probability cardinality to build the quanta matrix of these uncertain attributes, which is then used to evaluate class-attribute interdependency by adopting the redesigned ucaim criterion. The algorithm selects the optimal discretization scheme with the highest ucaim value. Experiments show that the usage of uncertain information helps UCAIM perform well on uncertain data. It significantly outperforms the traditional CAIM algorithm, especially when the uncertainty is high.

show abstract

Learning from inconsistent and noisy data: The AQ18 approach

Cited by 36 publications

References 6 publications

Highly scalable and robust rule learner: performance evaluation and comparison

Highly scalable and robust rule learner: performance evaluation and comparison

Untitled

A Discretization Algorithm for Uncertain Data

Contact Info

Product

Resources

About