Dataset
PyTorch supports two different types of datasets.
[Read More]
Unsupervised Machine Translation Using Monolingual Corpora Only!
Some notes from the paper
Paper Review!
My actual journey into deeplearning began with this paper. Although I could not reproduce it but I learnt many important techniques from this gem.
[Read More]
Neural approaches to Translation
An overview of important concepts for neural machine translation
Background
rule based -> statistical -> neural
a sequence to sequence problem.
[Read More]
Normalization in Deep Learning
Only the techniques I have encountered... there are many more!
These are basically a bunch of techniques that helps the model converge faster.
Batch Normalization
paper: https://arxiv.org/pdf/1502.03167.pdf%27
[Read More]
CISC to RISC
RISC is faster, more energy efficient and easier to design. CISC uses less memory and is simpler for compilers.
[Read More]