Resources for DS & ML & DL

02-03-2021 / Edit on Github

πŸ‘‰ Note: Useful tools for working & studying.
πŸ‘‰ Note: Web Dev tools & resources.

Blogs & Tuts #

  • Airbnb β€” Engineering & Data Science – Medium.
  • AI Curious β€” Viet Anh's personal blog, in Vietnamese.
  • Colah's blog β€” personal blog.
  • Facebook AI Blog.
  • Google's AI Hub -- a platform that lets us centralize our code and knowledge in a way that can step up the pace of deployment and learnings globally, giving us the scale to deliver data-driven marketing excellence.
  • Google Codelabs -- Google Developers Codelabs provide a guided, tutorial, hands-on coding experience. Most codelabs will step you through the process of building a small application, or adding a new feature to an existing application. They cover a wide range of topics such as Android Wear, Google Compute Engine, Project Tango, and Google APIs on iOS.
  • Math ∩ Programming β€” personal blog.
  • Netflix TechBlog
  • Ong Xuan Hong β€” personal blog.
  • Sebastian Ruder β€” personal blog.

Books #

Services & API #

  • Mapbox β€” Precise location data and powerful developer tools to change the way we navigate the world.
  • Foursquare β€” the trusted location data.
  • OpenStreetMap β€” a map of the world, created by people like you and free to use under an open license.

Frameworks #

  • Caffe β€” deep learning framework.
  • D3js β€” Data-Driven Documents.
  • Hydra β€” A framework for elegantly configuring complex applications. It's Facebook's.

Python libs #

  • daft β€” a Python package that uses matplotlib to render pixel-perfect probabilistic graphical models for publication in a journal or on the internet.
  • CSAPS β€” a Python package for univariate, multivariate and n-dimensional grid data approximation using cubic smoothing splines. The package can be useful in practical engineering tasks for data approximation and smoothing.

For Vietnamese #

πŸ‘‰ Dataset for Vietnamese.

  • KbQAS (ISWC 2013): Video demo of the knowledge-based Vietnamese question answering system KbQAS.
  • PhoBERT (EMNLP 2020 Findings): Pre-trained language models for Vietnamese.
  • PhoW2V (2020): Pre-trained Word2Vec syllable- and word-level embeddings for Vietnamese.
  • RDRsegmenter (LREC 2018): A fast and accurate Vietnamese word segmenter.
  • ViText2SQL (EMNLP 2020 Findings): A dataset for Vietnamese Text2SQL semantic parsing.
  • VnCoreNLP (NAACL 2018): A Vietnamese NLP pipeline of word (and sentence) segmentation, POS tagging, named entity recognition and dependency parsing.
  • VnDT (NLDB 2014): A Vietnamese dependency treebank.
  • VnMarMoT (ALTA 2017): A pre-trained Vietnamese POS tagging model.

Tools #

  • Caffe Model Zoo -- reasearcher share their Caffe models.
  • Chart.js | Open source HTML5 Charts for your website
  • DeepKit -- The collaborative real-time open-source machine learning devtool and training suite: Experiment execution, tracking, and debugging. With server and project management tools.
  • Embedding Projector tool from tensorflow.
  • Flourish β€” Data Visualization & Storytelling.
  • Foursquare β€” Put the most trusted, independent location data and technology platform to work for your business.
  • Google Data Studio.
  • Graphviz export
  • Teachable Machine -- Train a computer to recognize your own images, sounds, & poses.
  • idyll β€” A toolkit for creating data-driven stories and explorable explanations.
  • Mapbox β€” Maps and location for developers.
  • ml5js -- Friendly Machine Learning For The Web.
  • nbdev β€” Create delightful python projects using Jupyter Notebooks.
  • Observale β€” Observable is the magic notebook for exploring data and thinking with code.
  • Streamlit β€” The fastest way to build data apps in Python.
  • Replicate β€” Version control for machine learning.
  • TensorBoard -- TensorFlow's visualization toolkit.
  • TensorFlow Playground
  • Travis-CI β€” a hosted continuous integration service used to build and test software projects hosted at GitHub and Bitbucket.
  • Vaex β€” Handle huge dataframe.