Live data from Hacker News

Listening for illegal logging chainsaws using TensorFlow

blog.google

81–90 of 128 posts

Re: Listening for illegal logging chainsaws using TensorFlow

#83

Earlier quoted context omitted.

What company is this if you dont mind saying?

I assume he is talking about Planet Labs ( https://www.planet.com/ ) - a very cool service.

Yes, this is it as far as I can tell.

Re: Listening for illegal logging chainsaws using TensorFlow

#84
post #81

5 years from now: "listening for illegal speech in city streets using TensorFlow"

sign language will be everyone's primary language. Better yet a combination of sign and spoken.

Neural nets seem to be doing pretty amazing with video as well.....

Re: Listening for illegal logging chainsaws using TensorFlow

#85

Earlier quoted context omitted.

That's a great question. Actually, one of the sounds that are pretty close to a chainsaw are mosquitos that are circling around our microphones due to the Doppler effect. We found ways of dealing with signals that are close to chainsaws by aggregating multiple models and also a time-based analysis. The system can draw causal/correlative conclusions such as a vehicle is usually present before a chainsaw. If there's no…

How do you quantify the confidence of your model? Do you use a Bayesian model or just the log-likelihood? Because the latter can act strangely in some cases.

Logger-likelyhood ;)

Re: Listening for illegal logging chainsaws using TensorFlow

#86
post #78

The title is asking for attention unnecessarily since the neural network will not be able to distinguish between "legal" and "illegal" chainsaws. It should just say: Listening for logging chainsaws [...]

Presumably they are listening in areas which are already protected from logging, so any chainsaws in this area are illegal if they are cutting trees.

Re: Listening for illegal logging chainsaws using TensorFlow

#87
post #3

Great, now you can't escape Google's tracking even in the middle of the fucking jungle. Those bastards will triangulate your position from the sound of your footsteps and send BigDog to slice you up.

Come on now. You are worth more alive. They'll send bigdog with a video ad display strapped to his side to "impress" you.

Re: Listening for illegal logging chainsaws using TensorFlow

#88
post #22

Earlier quoted context omitted.

This is a really cool application of this technology, great work! Do you have any blog posts explaining the types of models you're using or open source repos that one could contribute to? (Asking as a ML/Software Engineer who's pleasantly surprised and yearning to contribute to something like this!)

Thanks! We are a relatively small engineering team and we were mainly focused on improving our system. This took a lot of effort and time, we just haven't had a chance yet to think about open sourcing or blogging. Our days were focused on coding. If there's interest in blog posts, I could write up some of our technology. Just let me know whether there's an interest and what you'd like to know.

Do you setup wifi hotspots in the forest for this devices to send data back? Solar chargers is it universal for any android phone? what happens if phone is unable charge and shuts down? are those solar chargers available for sale to use in other forest projects?

Re: Listening for illegal logging chainsaws using TensorFlow

#89
post #38
post #33

How about detecting fraudulent blockchain ads?

What would constitute a non-fraudulent blockchain ad? All ICOs are all designed to be the same Ponzi-Pyramid scheme, as how they're incentivized - which is what makes Bitcoin, Ethereum's Ether et al in the same boat.

Most ICOs are speculative but not Ponzi/pyramid schemes. They do not borrow against previous investors' funds and they do not have referral DAGs. Do you consider Facebook's IPO a Ponzi/pyramid scheme?
Post reply on HN