SUNNYVALE, Calif., 15th November 2019 - Apurba is happy to inform that a paper "Sankhya: An Unbiased Benchmark for Bangla Handwritten Digits Recognition" has been accepted for the Open Science in Big Data (OSBD) workshop, to be held in conjunction with the 2019 IEEE BigData Conference in Los Angeles on 9-12th December 2019.
This paper focuses on benchmarking five robust machine learning algorithms: K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF), Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), on all publicly available Bangla handwriting digits datasets, including Ekush, NumtaDB, CMARTdb, and BDRW.
The Open Science in Big Data (OSBD) is a workshop of the IEEE BigData Conference exploring the challenges and opportunities of Open Science philosophy and practice in Big Data. This workshop will focus on the current practices of and future directions for democratizing big data analytics and improving reproducibility of research in big data. For more information about the workshop, please visit the website Open Science in Big Data 2019.
Apurba Technologies is a Dhaka, Bangladesh, based software development company that creates enterprise big data solutions for natural language processing, visualization and analytics. Apurba has been a leader in Bangla language processing, focussed on developing large scale computerization of Bangla at every aspect: but especially targeted to government, banking, finance and healthcare sectors.