Mercedes uses Akida, page-320

I read in one of the Mercedes articles and others have posted it a couple of times that AKIDA is using 2 to 4 watts doing the ‘Hey Mercedes’ well to be using this much power AKIDA is doing much more in my opinion based on the paper available on the Brainchip website. I have included the link but the extracted two paragraphs make the point very clear:

https://brainchipinc.com/keyword-spotting-ee-times/

Training AkidaA keyword spotting application using the Akida chip trained on the Google Speech Commands Dataset can run for years off a penlight battery. The same circuit configured to use 30 layers and all 80 neural processing units on the chip can be used to process the entire ImageNet dataset in real-time at less than 200 milliwatts (about five days on a penlight battery).

The MobileNet network for image classification fits comfortably on the chip, including all the required memory. The on-chip, real-time learning capability makes it possible to add to the library of learned words, a nice feature that can be used for personalized word recognition like names, places and customized commands."

What this clearly tells me is that the author of the article either misheard what he was told, heard correctly but did not understand or Mercedes engaged in a little misinformation to keep competitors of track as to how much of the comfortable 1,000 kilometre range is attributable to the AKIDA technology advantage.

My preference is for hearing correctly and Mercedes games as in this same article the author also referred to AKIDA having 1.2 million neurons and 10 billion synapses which is straight from the AKD1000 play book. In saying this I refer you to the first sentence of the above extract "the Akida chip trained on the Google Speech Commands Dataset can run for years off a penlight battery."

This is of course my anonymous opinion only but I get some comfort in putting it forward because of Rob Telson's statement prior to Christmas that AKIDA technology was leading the way to a range of 1000 kilometres for EVs. Little did I know when I became aware of this statement that it was going to lead to a futuristic Mercedes that has stolen my heart with its throw back to the Aston Martin rear end design.

My opinion only so DYOR
FF

AKIDA BALLISTA (at ultra low power in 2022)