Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About Me
About me
Page not in menu
This is a page not in th emain menu
Posts
Machine Unlearning and Data Privacy
A question that naturally arises with machine learning is, how do we selectively erase information from a trained model?
Learning DS / ML Concepts
To fully understand a data science or machine learning concept, we need to be exposed to all three perspectives—the idea, the math, and the code.
Welcome to my blog!
Welcome to my blog! This is where I plan to dump my musings on recent LLM hype, my unfiltered notes on recent papers, and updates on what I’m up to. Feel free to connect with me on LinkedIn and let me know your thoughts and opinions on the topics!
portfolio
Mixture-of-Experts Implementation Permalink
Implemented a Switch Transformer alongside a conventional autoregressive transformer and trained on TinyShakespeare to research effects of mixture-of-experts architecture on validation loss, sample-efficiency and training time.
Art Generation with GANs Permalink
Implemented and compared DCGANs and Creative Adversarial Network (CAN)s to generate paintings, performed hyperparameter tuning and metric evaluations, developed interactive Streamlit demo.
LLMs for Question Answering Permalink
Fine-tuned encoder-decoder model T5 with LoRA for extractive question answering on reading comprehension dataset SQuAD v1.1.
TinyTransformer Permalink
Built and trained decoder transformer models in parallel from scratch on TinyStories, investigated scaling laws of dataset and model size with validation loss and created story generation demo.
Machine Unlearning Permalink
Implemented common machine unlearning (MU) algorithms such as zero-glance and zero-shot unlearning via error-maximizing noise and gated knowledge transfer respectively, selective synaptic dampening (SSD), incompetent teacher unlearning, etc., exploring the nascent field of MU and its applications in the right to be forgotten, debiasing, influence functions and model interpretability, and more.
publications
Published in , 1900
Download here
talks
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.