On Friday, September 03, 2021, at 8:04 AM, magnuswootton81 wrote: > a) Run it per sample, to get all overlaps. Per each 44.1 kHz sample? Surely not? Also, do you do FFT first? > b) do a knn match to a database, if it isnt near enough to any of them, you > store it as a new class. (so its unsupervised learning, at least this part > of it.) Hmm ok. I get this part, but I'm not sure what exactly the object is you put into the database. KNN is an interesting choice for a "dumb smart" algorithm (super simple but probably useful). Isn't it getting slow though over time?
I always like to hear about surprisingly simple algorithms. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T89dc799e249e2d0b-Mdd6055a601b53e564bf7b21a Delivery options: https://agi.topicbox.com/groups/agi/subscription
