Lions, Tigers, and Bears, Oh My! While Dorothy’s list of animals are not included in Elon Musk’s latest tweet regarding animal recognition by Tesla’s Neural Network, dogs, cats, and horses are included.
Speaking to Tesla’s object recognition abilities, it appears that Tesla is preparing to release an update that includes new visualizations of various animals that may stray across the car’s path.
As far as animal recognition, Teslas currently only visualize dogs, but it will often display a dog even if it’s another animal.
This is due to a lack of training, where the car can’t yet differentiate between a dog, a horse or a cat. It can be easily fixed by training their NN by adding and categorizing photos of addition animals.
It looks like we’ll soon get new animal visualizations. The most obvious may be animals that are regularly found near streets, such as deer, horses, possums or other creatures.
While automotive competitors have made gains in developing electric vehicles after years of lagging behind Tesla, one cannot deny that Tesla’s neural networks are cutting edge.
These neural networks give Tesla the ability to gather live data from over one million participating vehicles. They utilize these vast datasets of real-world data to train their AI algorithms to identify objects that may be a hazard to drivers.
Tesla claims that « a full build of Autopilot neural networks involves 48 networks that take 70,000 GPU hours to train. »
While users have noticed drastic improvements in the car’s ability to recognize various car types (as seen by improved visualizations in 2022.16), the likely addition of new animals is an interesting addition.
With FSD Beta 10.12, Tesla added numerous visualization updates. Will more animals be added in FSD Beta 10.13, which is expected in about two weeks?
While too early to tell, it remains exciting that the objection recognition abilities of Teslas continue to improve.
Source : https://www.notateslaapp.com/software-updates/upcoming-features/id/788/tesla-to-show-new-animal-visualizations
