Artificiality Bites 💊 Issue #19
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. Bon appetit!
📝 Interesting articles last week
- Researchers detect ‘silent speech’ with electrodes and AI
3'
UC Berkeley researchers claimed they are the first to train AI using silently mouthed words and sensors that collect muscle activity. - Learning from Language Explanations (Stanford AI)
9'
In two short papers presented at ACL 2020, deep neural models are used to learn from language explanations to help tackle a variety of challenging tasks in Natural Language Processing and Computer Vision. - Navigating Recorder Transcripts Easily (Google AI)
10'
Google introduced a new ML-based feature in its Recorder app that automatically marks important sections in the transcript, choosing the most representative keywords, and making them navigable. The models used are lightweight enough to be executed on-device. This blog post explains aspects from its implementation. - Data Quality at Airbnb
11'
Airbnb introduces Midas, its initiative developed as a mechanism to unite the company behind a shared “gold standard” that serves as a guarantee of data quality.
🔧 Tutorials
- How to Train and Deploy Custom AI-Generated Quotes using GPT2, FastAPI, and ReactJS
14'
A fine-tuned GPT2 model which generates motivational, inspirational, funny or philosophical quotes, deployed in a ready-to-use website. - 2020’s Top AI & Machine Learning Research Papers
37'
10 important machine learning research papers from 2020, summarized.
📦 Repositories
- The Multilingual Amazon Reviews Corpus
A collection of Amazon reviews specifically designed to aid research in multilingual text classification. The dataset contains reviews in English, Japanese, German, French, Chinese and Spanish, collected between 2015 and 2019. - shreyashankar/create-ml-app
A Python library that makes it easier to start a machine learning project locally and handle package dependencies, abstracting away pip installs and virtual environment commands from the user. - openai/vdvae
Repository for the paper “Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images”
🎓 Courses / Events
- MIT 6.036 Introduction to Machine Learning
ML basic concepts exercised in supervised learning and reinforcement learning, with applications to images and time series. - Machine Learning 1 (University of Amsterdam)
ML course developed by the Amsterdam Machine Learning Lab and currently taught by Erik Bekkers. - Chai with Kagglers 📹
A huge video playlist full of interviews with Kaggle Masters.
🚀 Extra bits
👉 Newsletter en Español
👋 See you next week!
