Home /
Research
Showing 505 - 510 / 897
BanglaWriting: A multi-purpose offline Bangla handwriting dataset
M.F.Mridha, AbuQuwsarOhi, M.AmeerAli....
Published date-11/15/2020
This article presents a Bangla handwriting dataset named BanglaWriting that contains single-page handwritings of 260 individuals of different personalities and ages. Each page includes bounding-boxes that bounds each word, along …
Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
ShuoZhang, YangLiu, LeiXie....
Published date-11/15/2020
DrugDiscovery, FormationEnergy
The prediction of physicochemical properties from molecular structures is a crucial task for artificial intelligence aided molecular design. A growing number of Graph Neural Networks (GNNs) have been proposed to …
CDT: Cascading Decision Trees for Explainable Reinforcement Learning
ZihanDing, PabloHernandez-Leal, GavinWeiguangDing....
Published date-11/15/2020
ImitationLearning, RepresentationLearning
Deep Reinforcement Learning (DRL) has recently achieved significant advances in various domains. However, explaining the policy of RL agents still remains an open problem due to several factors, one being …
Open4Business(O4B): An Open Access Dataset for Summarizing Business Documents
AmanpreetSingh, NiranjanBalasubramanian....
Published date-11/15/2020
A major challenge in fine-tuning deep learning models for automatic summarization is the need for large domain specific datasets. One of the barriers to curating such data from resources like …
Automated Large-scale Class Scheduling in MiniZinc
Md.MushfiqurRahman, SabahBinteNoor, FazlulHasanSiddiqui....
Published date-11/15/2020
Class Scheduling is a highly constrained task. Educational institutes spend a lot of resources, in the form of time and manual computation, to find a satisficing schedule that fulfills all …
Deep Ordinal Regression using Optimal Transport Loss and Unimodal Output Probabilities
UriShaham, JonathanSvirsky....
Published date-11/15/2020
We propose a framework for deep ordinal regression, based on unimodal output distribution and optimal transport loss. Despite being seemingly appropriate, in many recent works the unimodality requirement is either …