Ah! Thanks for posting this Tom. It's such a well designed, simple to understand video series, and the backing track is utterly delightful.  

Given the growing applications of machine learning for conservation, I've been wondering if a 'machine learning 101 for conservation' webinar or article might be a worthwhile resource to look into for our community. In looking for a link to put in here to a UCL course I know exists on this topic, I actually just came across this article: A PRACTICAL GUIDE TO MACHINE LEARNING IN ECOLOGY. Seems that Jon Lefcheck had the same thought as me and got right down to it.

If you're interested in more introductory, practical resources on machine learning, do let me know below! Also, if you know of any other go to tutorials that you've found useful, please share them. 

Steph

Hi Jason, 

Thanks for sharing this demo, it's interesting to see the fluke id process in action. Is this part of the flukebook project? How do you see the project progressing - are there opportunities for people to get involved or challenges it would be helpful to get outside input on? 

Cheers,

Stephanie

Hi,

I am jason Holmberg from WildMe.org. I am one of the developers of Wildbook (wildbook.org), an open source data management platform for wildlife research. I'm using ML as part of the IBEIS.org project to boost and metascore multiple computer vision algorithms for individual humpback and sperm whales. David, I would love to speak offline if you have the time: [email protected].

Cheers,

Jason

"TensorFlow, you see, deals in a form of AI called deep learning. With deep learning, you teach systems to perform tasks such as recognizing images, identifying spoken words, and even understanding natural language by feeding data into vast neural networks. "

Would this be applicable to an acoustic monitoring network? For example. my research has shown tigers have unique, identifiable vocalizations down to the individual and sex. If this software is applied to my recording network for tigers, would it be able to automatically recognize and categorize these individuals?

For example: when it hears Tiger 108, it would know and then input that it heard Tiger 108 at a particular time and date.

The catch will be (and for any neural network or AI type learning I would expect the same) the training phase. If you are able to tell the sounds apart or identify a specific sound as belonging to a certain individual, the AI should afterwards be able to automatically identify the critical factors needed to distinguish the voices of the individuals. But it will need enough input from each individual as well as the different vocalizations used by tigers. AFAIKT it will be able to do this automatically afterwards, but I am not sure if (a) you will get enough identifiable vocalisations and (b) with a wide enough range of typical tiger vocalisations for it to be really reliable. Training on zoo animals might work? I am also interested in this, but for jackals instead of tigers.

I'd like to suggest our open source package Wildbook (http://www.wildbook.org) as a base data management platfor for this. I agree with the above that there are a number of challenges around the vocalizations themselves, but having the identity information in a good database and data model is a great foundation. That's what we're doing for our computer vision/deep learning project at www.IBEIS.org.

Our non-profit WildMe.org is running both. Feel free to contact us with questions. We have played with time series matching (often used for speech recognition)...but actually for whale flukes. Would be happy to discuss potential for audio ID.