Narayan

Will Share Tomorrow What actually caused this💀.

heard somewhere that if you want to be great at a domain in ml, replicate old papers and try to exactly match the results table. here is my attempt to solve subgraph matching problem from original paper from "The Graph Neural Network Model" Scarselli et al. , 2009 using a linear non-positional GNN > implemented model from scratch > 600 graphs , 5000 epochs > state_dim = 5 , hidden_neuron = 5 > max_iters = 50 , epsilon = 1e-5 for computing next node-states > will probably take forever in my laptop :) will attach github link in comments

Hold on I forget that I have TCS NQT tomorrow 🥲 , will be back to building soon 🥀

BERT with Numpy: My "BERT from scratch" project is a disaster. 😅 (In the best way possible). I've successfully built the BERT Model, all the layers, and the tokenizer. It works. What's Missing are optimizations like vectorize in numpy, stable gradients etc. Repo 👇

I think this is one of the best VS Code Extensions you can have , it's really helpful especially for a guy like like me who tends to forget my own ideas by morning. Extension Name: Todo Tree 🌳