Introduction

Modules are present on the website, complete one to get the access to the next one. Each module has it’s deadline but you can do it before and move to next. In order to get access to the next module, mentors have to pass your submitted solution only then you will be allowed to move forward otherwise you will be asked to do changes for improvements.

Adhere strictly to deadlines. Submissions will be evaluated on approach, technical correctness, and clarity. Person submitting before the deadline will have a stricter evaluation than the others. The most technically accurate solution may not necessarily be the one chosen; clarity of thought and a well-reasoned approach will be valued more.

Communities

All resources and updates will be shared through **CSOC website and the** Discord Community. Ensure you’re registered on the website and join the Discord community. Your primary mode of communication should be strictly through Discord. In case we fail to repond on discord, you can contact us on Whatsapp:

Suyash - 7091263781
Tanishq - 8553505350

Resources

In this module, we’re stepping into the next frontier of NLP. Moving beyond traditional RNN-based architectures. You’ll explore the Sequence-to-Sequence (Seq2Seq) framework, understand the power of attention mechanisms, and finally dive into the revolutionary world of Transformers. Just a quick note before we jump into the resources, don’t feel restricted to only these! If any topic feels unclear or if you’re curious to explore further (which we highly recommend if you have the time), feel free to consult other resources. These are simply the ones we found helpful and worth sharing.

Seq to Seq

This video by statquest is a great start to know about seq to seq architecture. Seq to seq explained.
A video about encoder decoder, that deep dives into seq to seq: Encoder Decoder
Check out these blog posts as well. Exploring Seq2Seq , Understanding Encoders-Decoders with an Attention-based mechanism

Transformers

Now meet the architecture that changed everything in NLP - Transformers. Transformers leverage self-attention to understand context better and faster.

“Attention is All You Need”- this groundbreaking 2017 paper by Google introduced the Transformer architecture, sparking a revolution in NLP and paving the way for models like BERT and GPT. First paper for y’all(read it after you have gone through resources)