Writing
Notes from the bench
Explainers with working code: retrieval, transformers, embeddings, and the PyTorch underneath.
2024
- Multi-Label Classification Using Hugging Face TransformerThis time, I have decided to work on multi-label classification problem, While I was searching for dataset, I found one in datahack.analyticsvidya.Topic Modeling for Research Articles
- Multi-Label Classification Using PyTorch TransformerEncoderLayerIn previous blog we used pretrained BERT-base-uncased model for text classification, Which was 99% accurate.Topic Modeling for Research Articles
- Search NeurIPS-2022 Similar PapersThis article is about simplifing the steps of achieving similar document retrieval and deploying it in Streamlit app.Document Retrieval
- PyTorch Functions You Should Know Before Building TransformerThe PyTorch tensor operations you need before implementing a transformer from scratch, each with a short example.Natural Language Processing
- Concepts You Should Know Before Getting into TransformerNeural network learn through numbers, so each words will be mapped to vectors to represent particular word.Natural Language Processing
- Convolution for NLP TaskThe blog explains about how 1D-Convolution Neural Network is used for Natural language processing problems, and how the inner calculation wil be happing.Natural Language Processing
- Understanding and Implementing a Recurrent Neural NetworkThis blog helps you to understand the Recurrent Neural Network and implement Recurrent Neural Network using Pytorch.Recurrent Neural Network
- Sentiment Classification and Word EmbeddingsSentiment classification on IMDB movie reviews: data exploration, word embeddings, an LSTM classifier, and t-SNE views of what the embeddings learn.Sentiment Classification
- Understanding Linear Regression in Supervised LearningLinear regression from first principles: the model, the cost function, and gradient descent, with an interactive plot and a from-scratch notebook.Linear Regression
- Retrieval-Augmented Generation (RAG)Large Language Models are designed to read, understand, and generate text almost like humans, They have been trained on vast amounts of text data.Retrieval-Augmented Generation