Dynamically Typed

By Leon Overweel (Dynamically Typed)

#60: Google Pixel car crash detection, Model Search for TensorFlow, an a movie frame search engine

#60・
340

subscribers

76

issues

Dynamically Typed
#60: Google Pixel car crash detection, Model Search for TensorFlow, an a movie frame search engine
Hey everyone, welcome to Dynamically Typed #60. Two weeks after we were ice skating on the canals, spring has arrived in Amsterdam and I’m sitting on the roof, writing this issue in the sun after a great row this morning! 🌞🚣‍♂️
For productized AI, I wrote about the car crash detection feature on Google’s Pixel phones, and about an NYT article on Exposing.AI, a tool that traces facial recognition datasets back to their Flickr origins. For ML research, I’ve got a cool new open-source AutoML tool from Google called Model Search, plus three new long reads from Distill. Finally, for cool things, I found an ML-powered website that lets you find movie screenshots based on the objects in them.

Productized Artificial Intelligence 🔌
Machine Learning Research 🎛
  • ⚡️ Google has released Model Search, an open-source AutoML platform for the TensorFlow ecosystem. The pitch: “Model Search is domain agnostic, flexible and is capable of finding the appropriate architecture that best fits a given dataset and problem, while minimizing coding time, effort and compute resources.” It can run on a single machine or in a distributed setting, and uses a reinforcement learning-inspired “explore & exploit” methodology to find a model architecture that optimizes for user-specified metrics. For efficiency, Model Search also uses knowledge distillation and weight sharing between experiments runs. It’s available on GitHub at google/model_search.
  • 📜 Three new long reads on Distill: a bit of a meta article about how they think about Visualizing Weights, which has been an important feature in lots of the publication’s recent articles; a new entry to the Circuits thread on reverse-engineering Curve Circuits; and an application of Neural Cellular Automata (NCA) for generating Self-Organizing Textures. That last one features a fun interactive graphic at the top. I didn’t get around to reading these in detail before sending out today’s DT — they’re quite long — but wanted to share them anyways.
Cool Things ✨
Searching for "clock" on Film.
Searching for "clock" on Film.
  • 🎞 After I wrote about same.energy, a visual search engine in the last issue of DT, I came across another similar project this week: Flim is a search engine for famous movie frames, which uses a computer vision model to tag screenshots with the objects featured in them. A search for “clock”, for example, yields screen caps from Slumdog Millionaire, V for Vendetta, and Peter Pan. I can imagine this’ll become a very useful tool for cinematographers or film students who are exploring the different creative ways in which certain subjects have been portrayed in the past.
Thanks for reading! As usual, you can let me know what you thought of today’s issue using the buttons below or by replying to this email. If you’re new here, check out the Dynamically Typed archives or subscribe below to get a new issues in your inbox every second Sunday.
If you enjoyed this issue of Dynamically Typed, why not forward it to a friend? It’s by far the best thing you can do to help me grow this newsletter. 🍝
Did you enjoy this issue?
Leon Overweel (Dynamically Typed)

My thoughts and links on productized artificial intelligence, machine learning technology, and AI projects for the climate crisis. Delivered to your inbox every second Sunday.

If you don't want these updates anymore, please unsubscribe here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Powered by Revue