DeepMind claims its AI improved Google Maps travel time estimates by up to 50%

Reviewers also took notice and complained about this.

using the TFLite Tensorflow packages.allowing you to run machine-learning models on surprisingly small devices.

DeepMind claims its AI improved Google Maps travel time estimates by up to 50%

The system is designed to take a 15-second sound sample every minute or so.the planes heading into Heathrow arent the only flying things.I found that increasing the sample time to 30 seconds significantly improved accuracy.

DeepMind claims its AI improved Google Maps travel time estimates by up to 50%

from tiny wrens to the looming presence of the local sparrowhawk.The web console uses the Caddy web server.

DeepMind claims its AI improved Google Maps travel time estimates by up to 50%

and I was also able to change the notification confidence level to reduce the risk of false positives (a passing diesel locomotive sounds rather like a Great Bittern to the BirdNET model!).

Access to BirdNET-Pi is through a web browser.Atlas Obscuras community marked Want to Visit upwards of more than one million times across our worldwide database of approximately 15

From a huge musical instrument played by the ocean to a secret 140-year-old castle with underground caves.Atlas Obscuras community marked Want to Visit more than one million times across our worldwide database of approximately 15.

Hidden wonders in San Francisco appeared eight times in our list of Top 100 places Atlas Obscuras community most wanted to visit this yearhe was so vigorous in his pursuit of female tortoises that his grunts could be heard from the other end of the zoo and the Jardin des Plantes.

Jason Rodriguezon Google+

The products discussed here were independently chosen by our editors. NYC2 may get a share of the revenue if you buy anything featured on our site.

Got a news tip or want to contact us directly? Email [email protected]

Join the conversation
There are 675 commentsabout this story