Reshmi Ghosh


Ph.D. Applied Scientist, Microsoft (Office of Applied Research)

   ABOUTACADEMICS   PROJECTS   Reviewing Activities


I love reading state of the art Machine and Deep Learning research papers and experiment with new model architectures by reimplmenting papers from scratch. I am currently working on end-to-end Automatic Speech recognition model with LibriSpeech data (project link coming soon!) using Transformer based architecture to parallelize the training process.

Moreover, during the course of my graduate studies I completed a series of academic and personal projects, with active participation in competitions like the MIT Energy Hackathon, Yale Graduate Case Competition(YGCC), Duke Graduate Case Competition, etc. During YGCC my team was one of the finalists in the competition, where we were touted as one of the most innovative teams to present a strategic solution to revolutionize electric scooter business using data-driven analysis.

Some of my other academic and personal projects are listed below:


[Personal] Attention based end-to-end speech to text model: Implemented the Listen, Attend and Spell paper to design a system for speech-to-text transcription using Locked Dropout, Teacher Forcing, and padded Cross-Entropy Loss.
[Personal] Machine and Deep Learning framework framework from scratch only using NumPy. </tr>
[DL research] Leveraged the VizWiz dataset (collection of 20,000 images captured by blind people through their mobile phones) to implement MobileNetv3 (CNN model) \& an LSTM based language model to develop a Visual Question Answering based framework. Achieved an accuracy of approximately 60\% using PyTorch library and NVIDIA K80 GPUs on AWS. </a>
[ML research] Conducted end-to-end data analysis to examine user behavior on Instagram about climate change by using unsupervised clustering techniques on web-scraped images \& associated hashtags. Determined that only ~10\% of all users posted relevant climate change related content between November-December'19.
[Personal-Kaggle] Developed an ML pipeline to conduct data-cleaning, pre-processing, feature engineering, \& built 'stacking' ensemble model using Logistic Regression, Support Vector, \& Random Forest classifier to predict survival rate in Titanic Disaster with ~93\% accuracy.
[Personal] The aim of the project was to augment enrollment strategy for Udacity. Coducted A/B Testing on a large dataset of students enrolling for *free* courses on Udacity to analyze the effect of 'studytime-filter' on students. Concluded based on statistically significant conversion rate numbers that filter shouldn't be launched.