Master Thesis:TinyML for Solar Panels: Bringing Edge Computing Applications to Solar Energy Systems
August 2020
In this work, we work on novel applications of edge computing for Solar Power Systems for 1)Identification and Estimation of Power Loss of Solar Panels 2)Classification of Soiling on Solar Panels and 3)Solar Irradiance Forecasting through Sky Images:
ACL 2019: Pre-trained BioBERT with Attention Visualisation for Medical Natural Language Inference
August 2019
This paper explores the use of Bidirectional Encoder Representation from Transformer (BERT) for solving MedNLI. The proposed model, BERT pre-trained on PMC, PubMed and fine-tuned on MIMICIII v1. 4, achieves state of the art results on MedNLI (83.45%) and an accuracy of 78.5% in MEDIQA challenge.
Convolutional Neural Networks In Classifying Cancer Through DNA Methylation
July 2018
A CNN based Deep Learning model that can classify the cancer of a new DNA methylation profile based on the learning from publicly available DNA methylation datasets
Compositional Attention Networks for Interpretability in Natural Language Question Answering
October 2018
We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture-the separation between memory and control, facilitates data-driven iterative reasoning.
Gallium Nitride Power Device Modeling using Deep Feed Forward Neural Networks
May 2018- IEEE WIPDA ASIA
this work proposes deep feed forward GaN ML device models which are highly accurate and can predict the switching behaviour of the device without having to delve into the physics and geometry of the device.