Incremental learning with support vector machines

Rüping, Stefan

doi:10.1109/icdm.2001.989589

Cited by 230 publications

(93 citation statements)

References 5 publications

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the possibility of incremental learning could be very helpful especially when the decision tuples are obtained at different intervals. There exist several approaches to incremental learning based on Support Vector Machines [71,68,32,18,78,10].…”

Section: Applymentioning

confidence: 99%

“…However, Rüping [68] argues that the assumption that a new decision relation is appropriate is wrong, i.e., the influence of previous support vectors on the decision function in the next learning step may be very small if the new decision tuples are distributed differently, so the final hyperplane does not differ significantly from the hyperplane obtained from the new decision relation. He claims that a new SVM result largely ignores the old support vectors and almost always corresponds to the decision function that would have been learned on the second decision relation alone.…”

Section: Applymentioning

confidence: 99%

See 1 more Smart Citation

Decisions: Algebra and Implementation

Danylenko

Lundberg

Löwe

2011

Machine Learning and Data Mining in Pattern Recognition

View full text Add to dashboard Cite

Processing decision information is a constitutive part in a number of applications in Computer Science fields. In general, decision information can be used to deduce the relationship between a certain context and a certain decision. Decision information is represented by a decision model that captures this information. Frequently used examples of decision models are decision tables and decision trees. The choice of an appropriate decision model has an impact on application performance in terms of memory consumption and execution time. High memory expenses can possibly occur due to redundancy in a decision model; and high execution time is often a consequence of an unsuitable decision model. Applications in different domains try to overcome these problems by introducing new data structures or algorithms for implementing decision models. These solutions are usually domain-specific and hard to transfer from one domain to another.Different application domains of Computer Science often process decision information in a similar way and, hence, have similar problems. We should thus be able to present a unifying approach that can be applicable in all application domains for capturing and manipulating decision information. Therefore, the goal of this thesis is (i) to suggest a general structure (Decision Algebra) which provides a common theoretical framework that captures decision information and defines operations (signatures) for storing, accessing, merging, approximating, and manipulating such information along with some general algebraic laws regardless of the used implementation. Our Decision Algebra allows defining different construction strategies for decision models and data structures that capture decision information as implementation variants, and it simplifies experimental comparisons between them.Additionally, this thesis presents (ii) an implementation of Decision Algebra capturing the information in a non-redundant way and performing the operations efficiently. In fact, we show that existing decision models that originated in the field of Data Mining and Machine Learning and variants thereof as exploited in special algorithms can be understood as alternative implementation variants of the Decision Algebra by varying the implementations of the Decision Algebra operations. Hence, this work (iii) will contribute to a classification of existing technology for processing decision information in different application domains of Computer Science.

show abstract

Section: Applymentioning

confidence: 99%

Section: Applymentioning

confidence: 99%

Decisions: Algebra and Implementation

Danylenko

Lundberg

Löwe

2011

Machine Learning and Data Mining in Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…But efficient online algorithm can make sure that parameter update is timely, and effectively. So it requires for efficiently completion of once-through operation in sampling period, which requires relatively low computational complexity [7][8]. To realize this objective, Suykens [2] has proposed online learning algorithm using Multi-mode constraints, OLAMMC, which can convert multi-mode constraints learning issues to solution by linear system of equations so as to improve the arithmetic speed.…”

Section: Introductionmentioning

confidence: 99%

College English learning platform based on Android smartphone

He¹,

Xiong²

2017

2017 International Conference on Advanced Education, Psychology and Sports Science (AEPSS 2017)

View full text Add to dashboard Cite

Abstract. Firstly a multi-mode binding mathematical model is provided for specific analysis on its properties. Then multi-mode constraints oriented Android smartphone based college English learning platform is proposed based on the properties of kernel function matrix and block matrix calculation formula. Application of this algorithm can achieve effective utilization of past training results, so as to effectively reduce storage and computing time. At last the validity of this learning method is verified by means of simulation experiments.

show abstract

“…Some researchers have tried some incremental methods used in SVM training. [11] proposed an incremental learning of SVM, that The support vectors from previous training set will be used involved in the new SVM optimization problem with different weights on them. This method can work for balanced data.…”

Section: Introductionmentioning

confidence: 99%

Incremental Multiple Classifier Active Learning for Concept Indexing in Images and Videos

Safadi

Tong

Quénot

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Active learning with multiple classifiers has shown good performance for concept indexing in images or video shots in the case of highly imbalanced data. It involves however a large number of computations. In this paper, we propose a new incremental active learning algorithm based on multiple SVM for image and video annotation. The experimental result show that the best performance (MAP) is reached when 15-30% of the corpus is annotated and the new method can achieve almost the same precision while saving 50 to 63% of the computation time.

show abstract

Incremental learning with support vector machines

Cited by 230 publications

References 5 publications

Decisions: Algebra and Implementation

Decisions: Algebra and Implementation

College English learning platform based on Android smartphone

Incremental Multiple Classifier Active Learning for Concept Indexing in Images and Videos

Contact Info

Product

Resources

About