DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency

no code implementations • 9 Nov 2023 • Azhar Shaikh, Michael Cochez, Denis Diachkov, Michiel de Rijcke, Sahar Yousefi

This paper introduces DONUT-hole, a sparse OCR-free visual document understanding (VDU) model that addresses the limitations of its predecessor model, dubbed DONUT.

document understanding Key Information Extraction +3

Learn to Bind and Grow Neural Structures

no code implementations • 21 Nov 2020 • Azhar Shaikh, Nishant Sinha

Task-incremental learning involves the challenging problem of learning new tasks continually, without forgetting past knowledge.

Bayesian Optimization Continual Learning +1

Parsimonious Computing: A Minority Training Regime for Effective Prediction in Large Microarray Expression Data Sets

1 code implementation • 18 May 2020 • Shailesh Sridhar, Snehanshu Saha, Azhar Shaikh, Rahul Yedida, Sriparna Saha

We leveraged the functional property of Mean Square Error, which is Lipschitz continuous to compute learning rate in shallow neural networks.