Currently diving deep into practical and theoretical aspects of deep learning.

Top projects

Look inside the workings of "Label Smoothing"
This blog post describes how and why does "trick" of label smoothing improves the model accuracy and when should we use it
deep-learning classification image-classification computer-vision
An Introduction to Bayes' Theorem
This blog post introduces the reader to one of the most important concept in probability theory - Bayes' Theorem
probabaility-and-statistics bayesian-deep-learning tutorial article
Revelations of Gradients and Hessians.
This blog post explores some of the insights gained from looking at gradients and Hessian matrices of the objective functions/loss functions.
deep-learning article
Image Captioning
This project is an attempt to build image captioning models using CNN and Transformers. Libraries used - fastai2, Huggingface Tokenizers and WandB.
image-captioning representation-learning computer-vision arxiv:2006.06666

Top collections