output
20132024
most citedSMOTified-GAN for class imbalanced pattern classification problems

156 citations

13 papers

cs.LG2024★ 2 cited

Data Distribution-based Curriculum Learning

Shonal Chaudhry, Anuraganand Sharma

The order of training samples can have a significant impact on the performance of a classifier. Curriculum learning is a method of ordering training samples from easy to hard. This…

cs.LG2021★ 156 cited

SMOTified-GAN for class imbalanced pattern classification problems

Anuraganand Sharma, Prabhat Kumar Singh, Rohitash Chandra

Class imbalance in a dataset is a major problem for classifiers that results in poor prediction with a high true positive rate (TPR) but a low true negative rate (TNR) for a majori…

cs.LG2021★ 29 cited

Guided parallelized stochastic gradient descent for delay compensation

Anuraganand Sharma

Stochastic gradient descent (SGD) algorithm and its variations have been effectively used to optimize neural network models. However, with the rapid growth of big data and deep lea…

cs.NE2020★ 2 cited

Optimistic variants of single-objective bilevel optimization for evolutionary algorithms

Anuraganand Sharma

Single-objective bilevel optimization is a specialized form of constraint optimization problems where one of the constraints is an optimization problem itself. These problems are t…

stat.ML2020★ 3 cited

Topological Gradient-based Competitive Learning

Pietro Barbiero, Gabriele Ciravegna, Vincenzo Randazzo +1

Topological learning is a wide research area aiming at uncovering the mutual spatial relationships between the elements of a set. Some of the most common and oldest approaches invo…

cs.CV2020★ 35 cited

Classification with 2-D Convolutional Neural Networks for breast cancer diagnosis

Anuraganand Sharma, Dinesh Kumar

Breast cancer is the most common cancer in women. Classification of cancer/non-cancer patients with clinical records requires high sensitivity and specificity for an acceptable dia…

cs.LO2017★ 10 cited

Evaluating the Stream Control Transmission Protocol Using Uppaal

Shruti Saini, Ansgar Fehnker

The Stream Control Transmission Protocol (SCTP) is a Transport Layer protocol that has been proposed as an alternative to the Transmission Control Protocol (TCP) for the Internet o…

cs.NE2016★ 17 cited

Guided macro-mutation in a graded energy based genetic algorithm for protein structure prediction

Mahmood A. Rashid, Sumaiya Iqbal, Firas Khatib +2

Protein structure prediction is considered as one of the most challenging and computationally intractable combinatorial problem. Thus, the efficient modeling of convoluted search s…

cs.LO2015★ 26 cited

Modeling and Verification of the Bitcoin Protocol

Kaylash Chaudhary, Ansgar Fehnker, Jaco van de Pol +1

Bitcoin is a popular digital currency for online payments, realized as a decentralized peer-to-peer electronic cash system. Bitcoin keeps a ledger of all transactions; the majority…

math.GN2014★ 8 cited

Completion of continuity spaces with uniformly vanishing asymmetry

Alveen Chand, Ittay Weiss

The classical Cauchy completion of a metric space (by means of Cauchy sequences) as well as the completion of a uniform space (by means of Cauchy filters) are well-known to rely on…

math.RA2014★ 3 cited

Weak crossed-product orders over valuation rings

John S. Kauta

Let be a field, let be a valuation ring of of arbitrary Krull dimension (rank), let be a finite Galois extension of with group , and let be the integral…

math.RT2014

Writing representations over minimal fields

S. P. Glasby, R. B. Howlett

The chief aim of this paper is to describe a procedure which, given a -dimensional absolutely irreducible matrix representation of a finite group over a finite field $\mathbb{E}…

math.GN2013★ 8 cited

A note on the metrizability of spaces

Ittay Weiss

With the blessing of hind sight we consider the problem of metrizability and show that the classical Bing-Nagata-Smirnov Theorem and a more recent result of Flagg give complementar…