tMan26
February 14, 2018, 9:12am
1
Hello everyone,
i just started to learning about HTMs and have few questions for which I cant find answers on Google or this forums.
Does input to HTM must be sparse (can i just convert rgb pixels into bit sequence? If yes, is there any better way to encode image than encoding RGB pixels into three integers using integer sparse coder?
3 Likes
It is not as simple as it seems.
Definitely read through this thread, which exposes a lot of the challenges involved in this problem:
@sunguralikaan I hope you don’t mind I pulled this into a new topic since it seems like it could spawn a whole discussion of its own. I’ve tried a few things for encoding visual input to HTM; here are my thoughts.
(1 - color discretization) The simplest starting point that I’ve used for a visual encoder is to bin each pixel into one of 8 categories based on the RGB intensity: low-red/low-green/low-blue, low-red/low-green/high-blue, low-red/high-green/low-blue, low-red/high-green/high-blue, and…
Another relevant thread:
Hi everyone, I have been a lurker for a while now and reading many of the questions, but now signing up to post my question as I have been working towards my own implementation of Sparse Vectors.I am trying to encode images to enable an SDR to recognize , say cats and dogs - a canonical problem in machine vision.
I followed the guidelines in the [encoding data for htm] (Encoding Data for HTM Systems ) and encoding the pixel levels in each of the Blue,Green,Red Channels with w=50 and n=1000. He…