Glimpse PoW

CF #1005

Solved A pretty Quickly Solved B at mid time , 24 mins , It was easy Problem C While solving C, I started getting defocused from the problem solving and more concerned with the ranks. Next time won’t do that. even after solving C Now the issue with my main logic was that I made it over-complicated. Moreover during the implementation I wasn’t ... Read more

CF #1004

Choked so hard. Couldn’t solve B , took too much time on finding the “elegant” solution for A What did I learn : Move on quickly STOP CARING ABOUT RANK!! Just solve A nd B quickly, warm up an hour before maybe. No pressure. Even if you choke on B , quickly solve C , cause it is solvable for sure. Question B Almost solved , just needed to ad... Read more

PEFT

Introduction Parameter-efficient fine-tuning is particularly used in the context of large-scale pre-trained models (such as in NLP), to adapt that pre-trained model to a new task without drastically increasing the number of parameters. The challenge is this: modern pre-trained models (like BERT, GPT, T5, etc.) contain hundreds of millions, if no... Read more

VAEs

Introduction Autoencoders are a class of neural networks primarily used for unsupervised learning and dimensionality reduction. The fundamental idea behind autoencoders is to encode input data into a lower-dimensional representation and then decode it back to the original data, aiming to minimize the reconstruction error. They are also used for ... Read more

GANs

Introduction Generative Adversarial Networks (GANs) are a class of deep learning models introduced by Ian Goodfellow and his colleagues in 2014. The core idea behind GANs is to train a generator network to produce data that is indistinguishable from real data, while simultaneously training a discriminator network to differentiate between real an... Read more