Search

Given a training set P ⊂ ℝ^d, the nearest-neighbor classifier assigns any query point q ∈ ℝ^d to the class of its closest point in P. To answer these classification queries, some training points are more relevant than others. We say a training point is relevant if its omission from the training set could induce the misclassification of some query point in ℝ^d. These relevant points are commonly known as border points, as they define the boundaries of the Voronoi diagram of P that separate points of different classes. Being able to compute this set of points efficiently is crucial to reduce the size of the training set without affecting the accuracy of the nearest-neighbor classifier. Improving over a decades-long result by Clarkson (FOCS'94), Eppstein (SOSA’22) recently proposed an output-sensitive algorithm to find the set of border points of P in 𝒪(n² + nk²) time, where k is the size of such set. In this paper, we improve this algorithm to have time complexity equal to 𝒪(nk²) by proving that the first phase of their algorithm, which requires 𝒪(n²) time, are unnecessary., LIPIcs, Vol. 244, 30th Annual European Symposium on Algorithms (ESA 2022), pages 54:1-54:10

Given the limitation of technologies, the subcellular localizations of proteins are difficult to identify. Predicting the subcellular localization and the intercellular distribution patterns of proteins in accordance with their specific biological roles, including validated functions, relationships with other proteins, and even their specific sequence characteristics, is necessary. The computational prediction of protein subcellular localizations can be performed on the basis of the sequence and the functional characteristics. In this study, the protein–protein interaction network, functional annotation of proteins and a group of direct proteins with known subcellular localization were used to construct models. To build efficient models, several powerful machine learning algorithms, including two feature selection methods, four classification algorithms, were employed. Some key proteins and functional terms were discovered, which may provide important contributions for determining protein subcellular locations. Furthermore, some quantitative rules were established to identify the potential subcellular localizations of proteins. As the first prediction model that uses direct protein annotation information (i.e., functional features) and STRING-based protein–protein interaction network (i.e., network features), our computational model can help promote the development of predictive technologies on subcellular localizations and provide a new approach for exploring the protein subcellular localization patterns and their potential biological importance Given the limitation of technologies, the subcellular localizations of proteins are difficult to identify. Predicting the subcellular localization and the intercellular distribution patterns of proteins in accordance with their specific biological roles, including validated functions, relationships with other proteins, and even their specific sequence characteristics, is necessary. The computational prediction of protein subcellular localizations can be performed on the basis of the sequence and the functional characteristics. In this study, the protein-protein interaction network, functional annotation of proteins and a group of direct proteins with known subcellular localization were used to construct models. To build efficient models, several powerful machine learning algorithms, including two feature selection methods, four classification algorithms, were employed. Some key proteins and functional terms were discovered, which may provide important contributions for determining protein subcellular locations. Furthermore, some quantitative rules were established to identify the potential subcellular localizations of proteins. As the first prediction model that uses direct protein annotation information (i.e., functional features) and STRING-based protein-protein interaction network (i.e., network features), our computational model can help promote the development of predictive technologies on subcellular localizations and provide a new approach for exploring the protein subcellular localization patterns and their potential biological importance.

The problem of nearest-neighbor classification is a fundamental technique in machine-learning. Given a training set P of n labeled points in ℝ^d, and an approximation parameter 0 < ε ≤ 1/2, any unlabeled query point should be classified with the class of any of its ε-approximate nearest-neighbors in P. Answering these queries efficiently has been the focus of extensive research, proposing techniques that are mainly tailored towards resolving the more general problem of ε-approximate nearest-neighbor search. While the latest can only hope to provide query time and space complexities dependent on n, the problem of nearest-neighbor classification accepts other parameters more suitable to its analysis. Such is the number k_ε of ε-border points, which describes the complexity of boundaries between sets of points of different classes. This paper presents a new data structure called Chromatic AVD. This is the first approach for ε-approximate nearest-neighbor classification whose space and query time complexities are only dependent on ε, k_ε and d, while being independent on both n and Δ, the spread of P., LIPIcs, Vol. 204, 29th Annual European Symposium on Algorithms (ESA 2021), pages 44:1-44:15

A conceptually simple way to classify images is to directly compare test-set data and training-set data. The accuracy of this approach is limited by the method of comparison used, and by the extent to which the training-set data cover configuration space. Here we show that this coverage can be substantially increased using coarse-graining (replacing groups of images by their centroids) and stochastic sampling (using distinct sets of centroids in combination). We use the MNIST and Fashion-MNIST data sets to show that a principled coarse-graining algorithm can convert training images into fewer image centroids without loss of accuracy of classification of test-set images by nearest-neighbor classification. Distinct batches of centroids can be used in combination as a means of stochastically sampling configuration space, and can classify test-set data more accurately than can the unaltered training set. On the MNIST and Fashion-MNIST data sets this approach converts nearest-neighbor classification from a mid-ranking- to an upper-ranking member of the set of classical machine-learning techniques.

An overview is given of prototype-based models in machine learning. In this framework, observations, i.e., data, are stored in terms of typical representatives. Together with a suitable measure of similarity, the systems can be employed in the context of unsupervised and supervised analysis of potentially high-dimensional, complex datasets. We discuss basic schemes of competitive vector quantization as well as the so-called neural gas approach and Kohonen's topology-preserving self-organizing map. Supervised learning in prototype systems is exemplified in terms of learning vector quantization. Most frequently, the familiar Euclidean distance serves as a dissimilarity measure. We present extensions of the framework to nonstandard measures and give an introduction to the use of adaptive distances in relevance learning. (C) 2016 Wiley Periodicals, Inc.

An overview is given of prototype-based models in machine learning. In this framework, observations, i.e., data, are stored in terms of typical representatives. Together with a suitable measure of similarity, the systems can be employed in the context of unsupervised and supervised analysis of potentially high-dimensional, complex datasets. We discuss basic schemes of competitive vector quantization as well as the so-called neural gas approach and Kohonen's topology-preserving self-organizing map. Supervised learning in prototype systems is exemplified in terms of learning vector quantization. Most frequently, the familiar Euclidean distance serves as a dissimilarity measure. We present extensions of the framework to nonstandard measures and give an introduction to the use of adaptive distances in relevance learning. (C) 2016 Wiley Periodicals, Inc.

An overview is given of prototype-based models in machine learning. In this framework, observations, i.e., data, are stored in terms of typical representatives. Together with a suitable measure of similarity, the systems can be employed in the context of unsupervised and supervised analysis of potentially high-dimensional, complex datasets. We discuss basic schemes of competitive vector quantization as well as the so-called neural gas approach and Kohonen's topology-preserving self-organizing map. Supervised learning in prototype systems is exemplified in terms of learning vector quantization. Most frequently, the familiar Euclidean distance serves as a dissimilarity measure. We present extensions of the framework to nonstandard measures and give an introduction to the use of adaptive distances in relevance learning. (C) 2016 Wiley Periodicals, Inc.

Introducing adaptive metric has been shown to improve the results of distance-based classification algorithms. Existing methods are often computationally intensive, either in the training or in the classification phase. We present a novel algorithm that we call Cluster-Based Adaptive Metric (CLAM) classification. It first determines the number of clusters in each class of a training set and then computes the parameters of a Mahalanobis distance for each cluster. The derived Mahalanobis distances are then used to estimate the probability of cluster- and, subsequently, class-membership. We compare the proposed algorithm with other classification algorithms using 10 different data sets. The proposed CLAM algorithm is as effective as other adaptive metric classification algorithms yet it is simpler to use and in many cases computationally more efficient. (C) 2011 Elsevier B.V. All rights reserved.

We present a novel approach to classification, based on a tight coupling of instancebased learning and a genetic algorithm. In contrast to the usual instance-based learning setting, we do not rely on (parts of) the given training set as the basis of a nearestneighbor classifier, but we try to employ artificially generated instances as concept prototypes. The extremely hard problem of finding an appropriate set of concept prototypes is tackled by a genetic search procedure with the classification accuracy on the given training set as evaluation criterion for the genetic fitness measure. Experiments with artificial datasets show that - due to the ability to find concise and accurate concept descriptions that contain few, but typical instances - this classification approach is considerably robust against noise, untypical training instances and irrelevant attributes. These favorable (theoretical) properties are corroborated using a number of hard real-world classification problems.