Learn runtime introspection in Python to convert functions into JSON schema for function calling with LLMs
An overview of evaluation metrics for measuring linguistic diversity in LLM-generated synthetic data
A simple stack for generating custom feeds for Bluesky programmatically without a backend server
A dead-simple way to perform parallel processing with progress bars natively in tqdm
A mental model of how various components of a regular expression work from the bottom-up.
A general framework to transfer knowledge from deep self-supervised models to shallow task-specific models
Learn how to interactively explore sentence embeddings and labels in Tensorflow Embedding Projector
Learn how to setup and use VSCode as an IDE on Google Colab and Kaggle.
Learn how to use machine translation models in Hugging Face Transformers for data augmentation
Learn about unsupervised algorithms for automatically extracting representative keyword and phrases from documents
Learn about common metrics used to evaluate performance of information retrieval systems
An overview of the “CheckList” framework for fine-grained evaluation of NLP models
A comprehensive overview of recent semi-supervised learning methods in Computer Vision
A comprehensive guide to FastAPI with a side-by-side code comparison with Flask
Learn about lesser-known features in Google Colaboratory to improve your productivity.
A deep-dive into how FastText enriches word vectors with subword information
A deep-dive into how Universal Sentence Encoder learns to generate fixed-length sentence embeddings
An exploration of simple knowledge captured by language models
A text generation approach to zero-shot text classification with GPT-2
A summary of “Train Once, Test Anywhere” paper for zero-shot text classification
An overview of self-supervised pretext tasks in Natural Language Processing
An extensive overview of text data augmentation techniques for Natural Language Processing
What a commit history of version-controlled research papers could look like?
Understand how to use Recurrent Layers like RNN, GRU, and LSTM in Keras with diagrams
DeepCluster is a self-supervised method to combine clustering and representation learning
A self-supervised method to generate labels via simultaneous clustering and representation learning
Learn how to leverage unlabeled data using FixMatch for semi-supervised learning
Learn about the advanced python native features behind PyTorch
Learn how PIRL generates image representations invariant to transformation in a self-supervised manner
A visual guide to the SimCLR framework for contrastive learning of visual representations.
A visual introduction to self-supervised learning methods for visual representations.
Learn how to augment existing labeled text data for free using Google Sheets.
An illustrated summary of the ALBERT paper
Learn how to integrate and finetune tensorflow-hub modules in Tensorflow 2.0
Learn how to use the modern pathlib module to perform tasks you have been using os.path for
Learn the meaning behind mathematical symbols used in Machine Learning using your knowledge of Python.
Learn how to detect the language of a given piece of text using Natural Language Processing.
Learn how to automate repetitive commands after connecting to a SSH server
Learn how to use Django ORM by drawing analogies to equivalent SQL statements