Home

Introduction Masked attention is typically used in the Decoder part of (vanilla) transformer architecture to prevent the model from looking at future tokens. This left me with the impression that the models trained using Masked Language Modelling (MLM) objective use Masked Attention. However, masked language models like BERT (Bidirectional En...

Introduction If you are training a deep learning model or fine-tuning LLMs (Large Language Models), then at some point in time you need to connect with a remote machine that has required amount of computing power (about 80GB or 320 GB of GPU Memory). Data scientists often use Jupyter Notebooks for experimentation. Jupyter Notebook is designed t...

Theory is not enough, you must apply. The objective of this workshop is to give you hands on experience in building models using the pytorch's core component called Tensor . Beleive me, everything you are gonna build is simply stacking or connecting copies of this single core component!. It make sense as all the models takes in Tensors (data) a...

"கண்ணா, வெளியில விளையாடப் போறயா, குடை எடுத்துட்டு போப்பா, மழை வர 60% வாய்ப்பிருக்குனு (Chance) போட்ருக்குப்பா ", என்றாள் திண்ணையில் ஸ்மார்ட் போனை ஸ்க்ரால் செய்தபடி அமர்ந்திருந்த பாட்டி. "அட போ பாட்டி, வெயில் கொளுத்துது" என்று அவள் சொன்னதை அசட்டை செய்து விட்டு சென்றான் பேரன் ஹரி . இவர்களது பேச்சை கேட்டவாறே வீட்டினுள் சென்றாள் பேத்தி மீனா . ...

Gradient as a Guide : A Simple Game   The Backpropagation algorithm is the powerhouse of all Deep Learning models. It is one of the methods of efficiently calculating Gradient for billions of parameters. Therefore, it is vital to understand how the Gradient information g...

Jupyter notebook has always been a de-facto choice when you teach the Python programming language or while developing prototype machine learning models or doing exploratory data analysis. The reasons are manifold. The most important reason is due to its ability to interleave the rich set of explanatory notes using markdown cells and ...

Motivation Are you wondering about the peculiar use of a sinusoidal function to encode the positional information in Transformer architecture? Are you asking why not just use simple one-hot encoding or something similar to encode positions?. Welcome, this article is for you. Perhaps you are here after reading a few articles explaining the posit...

Initially, I thought of writing an article on transformer architecture. However, I realized that it would go beyond some 90 pages if I cover every detail of it. So I thought of putting the presentation (which is almost self-reliant) prepared by me for the deep learning course taught at IITM by Prof.Mitesh Khapra. Here is the presentation (wait ...