The original work done on e-Nose doing the identification of the 20 gas data set each set consisting of 10 gases with state of the art performance and a latency of 3 seconds using the ADE only required 200 neurons.
In hardware it is logical to expect this performance would improve and as such could run on less neurons and still produce the same state of the art performance and latency.
The significance of the robot diagram showing all five senses is, as I understand it, one AKD1000 chip could be running all five applications as it has that much capacity or power.
My opinion only DYOR
FF
AKIDA BALLISTA
2021 BRN Discussion, page-19895
-
- There are more pages in this discussion • 13,686 more messages in this thread...
You’re viewing a single post only. To view the entire thread just sign in or Join Now (FREE)
Add BRN (ASX) to my watchlist
 (20min delay)
|
|||||
|
Last
15.5¢ |
Change
-0.005(3.13%) |
Mkt cap ! $309.0M | |||
| Open | High | Low | Value | Volume |
| 16.5¢ | 16.5¢ | 15.5¢ | $368.8K | 2.299M |
Buyers (Bids)
| No. | Vol. | Price($) |
|---|---|---|
| 7 | 350961 | 16.0¢ |
Sellers (Offers)
| Price($) | Vol. | No. |
|---|---|---|
| 14.5¢ | 106078 | 4 |
View Market Depth
| Last trade - 15.59pm 10/09/2024 (20 minute delay) ? |
| BRN (ASX) Chart |