Posts

Machine Unlearning

Widely used machine learning algorithms are able to learn from new data using batch or online training methods but are incapable of efficiently adapting to data removal. Why do we need data removal though you might think.

Dismantling Disentanglement in VAEs

Over the years neuroscience has inspired many quantum leaps in Artificial Intelligence. One such remarkable development inspired by the visual ventral system of the brain is Disentangled Variational Autoencoders. So first things first -

Adversarial Attacks on Aligned Language Models

I decided to ask a certain popular language model how to build an explosive, from everday items (for no particular reason), but it didn’t give me a plausible answer. What is happening here?

Password Cracking

On hearing the term “password-cracking,” many will think this post will be about how to guess someone’s password or somewhat similar, but the reality is not always so satisfying. What is Password Cracking In general, whenever anybody types a password on any device or software, passwords don’t get stored in the raw format in the database.

Riding the Noisy Research Track

Alright, people! This article will share my experience and learnings during the last eight months as an undergrad researcher. For those reading one of my blogs for the first time, I am a CSE undergrad (about to enter 3rd year) and am working as a Research Intern at SHI Lab @ UO and Picsart.

What doing research as an undergrad can teach you.

Although my coaching teachers used to say now and then ki “itna deep me jaake kya karega topic me, research karni he kya tereko isme?” If someone told me in my first few months at college, that I’ll be spending most of my time pursuing research as an undergrad, I would have probably laughed it off.

Optimizer: diving deep into Neural Networks

Waiting for the neural network to train is always annoying, make sure you use the right optimizers !

Metric Learning: It’s all about the Distance (Medium)

Going deeper and deeper works, but only when we know what exactly to learn. Let’s make sure we learn the right thing.

The Curse of Dimensionality (Medium)

Some say breaking this curse is as herculian of a task as breaking the Curse of Medusa. Well, who are we to judge…

Principal Component Analysis (Medium)

Too many dimensions can be bad for your model’s health. Here comes PCA to the rescue.