Artificiality Bites 💊 Issue #52
Hello Human! This is a new issue from my weekly newsletter holding a tiny compilation made of interesting articles from last week, projects, tutorials and tools; all related to Data, Artificial Intelligence and adjacent topics. Buen provecho!
📝 Interesting publications from last week
- AI Doesn’t Have to Be Too Complicated or Expensive for Your Business
9'
"Companies should focus on gathering high-quality data, shifting the focus of their engineering corps away from model-centric approaches, and make the deployment process and MLOps tools needed to support it a central part of the planning project for any AI project". - How Airbnb Built “Wall” to prevent data bugs
9'
A blog post about the challenges they faced while adding a massive number of data checks (i.e. data quality, accuracy, completeness and anomaly checks) to prevent data bugs company-wide. - Everyone in Your Organization Needs to Understand AI Ethics
10'
"The responsible deployment of AI requires awareness of the ethical risks of AI and organizational buy-in to a strategy that mitigates them". - The State of AI Ethics Report (Volume 5)
201p
This issue captures the most relevant developments in AI Ethics since the first quarter of 2021. - How to avoid machine learning pitfalls: a guide for academic researchers
17p
This document gives an outline of some of the common mistakes that occur when using machine learning techniques, focusing on issues that are of particular concern within academic research.
🔧 Tutorials
- Create Realistic AI-Generated Images With VQGAN + CLIP
A Colab notebook that allows you to create realistic AI generated images with as few clicks as possible and no coding or machine learning knowledge required. - Building Your Own Google Translate App with Plotly Dash
6'
How to show translated text as you hover around a country.
📦 Repositories
- evidentlyai/evidently
Evidently helps analyze machine learning models during validation or production monitoring. The tool generates six different interactive visual reports at the moment. - thu-ml/tianshou
Tianshou (天授) is a reinforcement learning platform based on pure PyTorch. - facebookresearch/DONERF
Source code for DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks. - ploomber/ploomber
Ploomber turns your notebooks, Python/R/SQL scripts or Python functions into a reproducible data pipeline. - facebookresearch/droidlet
A modular embodied agent architecture and platform for building embodied agents. - mlfoundations/open_clip
An open source implementation of OpenAI’s CLIP. - giddyyupp/ganilla
Official Pytorch implementation of GANILLA.
- labmlai/annotated_deep_learning_paper_implementations
Implementations and tutorials of deep learning papers with side-by-side notes.
🎓 Courses / Events
- Geometric Deep Learning 📹
The African Institute for Mathematical Sciences (AIMS) has made available a course on Geometrical Deep Learning. - An Introduction to Statistical Learning 📕
The 2nd Edition of the famous book is now available for everyone to download! - Time to Learn Machine Learning 📑
This book about Machine Learning tries to be as concise but easy to grasp as possible.
🚀 Extra bits
👋 Hasta la vista!