We already know that behemoths like NVIDIA etc permeate the mkt and have the name and resources to go with it. Power use will become and overriding issue at some point for various applications though.
Personally I get the read that they were trying to show that by adding Akida as a classifier to something like a Jetson which, let's face it, will be a first look for most "larger" comporations looking at the edge space like in this shipping example, that Akida compliments and actually enhances the performance of that sort of product by reducing the power and increasing outcomes.
Rather than this paper discussing Akida, models, SNN, processors stand alone comparisons per se, it is like trying to educatw and provide options to them where we can assist and enhance already maybe insitu processors....can we ride on the NVIDIA coat tails a little?
The other thought in this example is as Akida is being used as a classifier and the Jetson downstream processing, that the Jetson doesn't run SNN as far as I'm aware hence maybe YOLO utilised as it can be read by both Akida and Jetson? We're there for the front end sparsity, power reduction and classification.
"For edge computing tasks, it is common to have a smallgatingmodel which activates more costly downstream processing whenever necessary."
"We show that our classifier stage running on Akida benefits from a high degree of sparsity when processing the vast amounts of homogeneous bodies of water, clouds or land in satellite images, where only 0.3% of the pixels are objects of interest."
"The limitations of our system are the increased needs of size, having to fit two different accelerators instead of a single one.But by combining the strengths of different hardware platforms, we can optimize the overall performance, which is critical for edge computing applications in space"
BRN Price at posting:
21.5¢ Sentiment: Hold Disclosure: Held
(20min delay)