This article talks about the famous Transformers architecture in Natural Language Processing.
Attention is all you need - The Transformer
Hi there!
I am Raviteja Ganta, a data scientist. This is the place where I write articles in area of deep learning.
Latest Articles
Understanding Backpropagation in Neural Networks
Backpropagation is workhorse behind training neural networks and understanding what’s happening inside this algorithm is atmost importance for efficient learning. This post gives in depth explanation of Backpropagation for training neural networks.
Word Embeddings and Word2Vec
It’s obvious that any deep learning model needs to have some sort of numeric input to work with. In computer vision its not a problem as we have pixel values as inputs but in Natural language processing we have text...
Reformer - The Efficient Transformer
This article talks about the Reformer architecture in NLP which solves the memory efficiency challenges faced by Transformers architecture for long sequences.
Distilling the Knowledge in a Neural Network
How can we compress and transfer knowledge from a bigger model or ensemble of models(which were trained on very large datasets to extract structure from data) to a single small model without much dip in performance?
Sentiment Analysis using BERT and hugging face
This article talks about how can we use pretrained language model BERT to do transfer learning on most famous task in NLP - Sentiment Analysis