BRN Discussion Ongoing

Bravo

If ARM was an arm, BRN would be its biceps💪!
This video was posted 2 weeks ago on the NVDIA developer page and I would love to watch it because I think there's a very good chance that we're involved in some way, shape or form with the NVIDIA DRIVE IX intelligent experience software stack with DRIVE Hyperion 8 (or Hyperion 9). Hyperion 8 offers the sensors and the headroom for AI for 2024 vehicle models and Hyperion 9 is for deployment in 2026 production vehicles.

Unfortunately the video is for developers only so I think you may have to join the developer program to access this material. 💩


Screen Shot 2023-04-20 at 1.07.02 pm.png





Screen Shot 2023-04-20 at 1.00.56 pm.png



 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 14 users

Dang Son

Regular
Sean Hehir - Commsec interview May 22
 
  • Like
  • Fire
Reactions: 6 users

Dang Son

Regular
Rookie numbers my guy, DreddBot has me in the naughty corner as we speak.
Let me tell you it sucks. Not sure if you will even see this message hahah

@zeeb0t , plz help
View attachment 34687
Hi Damo , this is a perfect example of why Ai in its early iterations may not be well received by the practical human.
 
  • Like
  • Haha
  • Love
Reactions: 6 users

Dang Son

Regular
Does anyone know what Edge Impulse relationship is with Innatera? _ https://www.innatera.com/
It seems to me like our direct competition.

Innatera

UNLOCKING TRUE NEUROMORPHIC PATTERN RECOGNITION​


Innatera’s ultra-efficient neuromorphic processors mimic the brain’s mechanisms for processing sensory data. Based on a proprietary analog-mixed signal computing architecture, Innatera’s processors leverage the computing capabilities of spiking neural networks to deliver ground-breaking cognition performance within a narrow power envelope. With an unprecedented combination of ultra-low power consumption and short response latency, these devices enable high-performance always-on pattern recognition capabilities in applications at the sensor-edge.

UP TO 10,000X HIGHER PERFORMANCE PER WATT​

than conventional microprocessors and digital accelerators​



500X LOWER ENERGY​

Always-on pattern recognition within an extremely narrow power envelope

100X SHORTER LATENCY​

Blazingly fast recognition of spatial and temporal patterns in complex sensor data

PATTERN RECOGNITION SIMPLIFIED​

Simple to program and deploy with Innatera’s powerful SDK
 
  • Like
  • Fire
Reactions: 3 users

Iseki

Regular
Does anyone know what Edge Impulse relationship is with Innatera? _ https://www.innatera.com/
It seems to me like our direct competition.

Innatera

UNLOCKING TRUE NEUROMORPHIC PATTERN RECOGNITION​


Innatera’s ultra-efficient neuromorphic processors mimic the brain’s mechanisms for processing sensory data. Based on a proprietary analog-mixed signal computing architecture, Innatera’s processors leverage the computing capabilities of spiking neural networks to deliver ground-breaking cognition performance within a narrow power envelope. With an unprecedented combination of ultra-low power consumption and short response latency, these devices enable high-performance always-on pattern recognition capabilities in applications at the sensor-edge.

UP TO 10,000X HIGHER PERFORMANCE PER WATT​

than conventional microprocessors and digital accelerators​



500X LOWER ENERGY​

Always-on pattern recognition within an extremely narrow power envelope

100X SHORTER LATENCY​

Blazingly fast recognition of spatial and temporal patterns in complex sensor data

PATTERN RECOGNITION SIMPLIFIED​

Simple to program and deploy with Innatera’s powerful SDK
"analog-mixed signal computing architecture" is bad. Akida's pure digital approach the way to go for cheap, billions of IP orders inside billions of MCUs. We're in the box seat. We just need someone to spill the beans and tell us they just pre-ordered some Akida 2000's
 
  • Like
  • Fire
Reactions: 23 users
Recall seeing the Teksun website blurb revisited recently and supposedly Linaro was in it so thought have a dig around.

Whilst can't see anything of us yet, various 96boards are out with NPUs with people like Qualcomm, HiSilifin, Xilinx, Rockchip and some boards that don't specify.


They big into AI obviously with edge, auto and IoT as well but I liked a certain couple of our mutual partners ;)

Worth keeping an eye on me thinks.





Automotive, IoT & Edge Devices​

Automotive, IoT & Edge Devices dark icon

Software defined functionality is no longer restricted to the cloud network but is now expected to extend to the edge.
Autonomous AI-driven features are being deployed to positions of trust in gateways and even sensors.The Zonal Architecture revolution driving the evolution to software-defined vehicles is just one indicator that industry has switched to a software-first methodology. The technologies underpinning these use cases are continuously evolving but all suffer from one common denominator - the lack of open software standardization.
Arm
HiSilicon
QuIC
ST
Socionext
Xilinx
 
  • Like
  • Fire
Reactions: 11 users

Rise

Emerged
Just
I just took a look at this vid link, which Walhik Joe put up over at HC.

It's an interview with Nandan Nayampally, I don't believe I have seen it here, what I liked was the way Nandan articulates what AIoT is and a bit of an exploration of AI market.

I like the well considered way Nandan comes across.

Something I would like BRN executives focus upon more in their various interviews, is the one or two shot on chip learning capability of the various Akida iterations i.e. would have been good to see Sean slip the one shot learning thing somewhere in the conversation he had with Zach Shelby the other day.

One shot learning is a major differentiator, Akida is way more than an accelerator.

The link: https://lnkd.in/eRXqqdcx
Thanks for the link I totally forgot about watching this one when it was released.
RFTA.
 
  • Like
Reactions: 1 users
"analog-mixed signal computing architecture" is bad. Akida's pure digital approach the way to go for cheap, billions of IP orders inside billions of MCUs. We're in the box seat. We just need someone to spill the beans and tell us they just pre-ordered some Akida 2000's
Can you please share the evidence of your digital claim? I have done some reading myself and emailed Tony to ask Peter about why we are implementing digital and not analog after getting some feedback from the slasher in the other site
 

M_C

Founding Member
  • Like
  • Love
  • Fire
Reactions: 25 users

M_C

Founding Member


“Whether our technology is going into a smartphone or whether it’s going into a factory or a robot or a drone flying around Mars, our AI is a horizontal that permeates all of those device categories and applications,” said Don McGuire, Qualcomm’s chief marketing officer.

The technology Qualcomm brings to artificial intelligence is a digital platform, based on Snapdragon computer chips. Aaron Elkins is the director of the Artificial Intelligence Center based at San Diego State. He says Qualcomm’s role in AI is providing devices that can operate AI systems in the real world.

"AI is happening in our labs, with our supercomputers and our robots,” Elkins said. “But when it’s trained, and we’re past this development phase, AI needs to exist on devices that can actually run them but they don’t take a lot of power and they can handle these algorithms. So Qualcomm fits in at the edge and actually using AI.”

“People expect when they are querying ChatGPT for instance, and the answers are coming back. Where are they coming from and where is that happening? Today it’s happening on the cloud. A data center somewhere,” McGuire said.

The problem with that, he says, is data centers don’t have the infrastructure or power to accommodate artificial intelligence as its use dramatically increases.

“So really what’s going to have to happen is AI is going to have to become hybrid, meaning a certain amount of AI and behavioral algorithms have to happen on device as well as in the cloud.”

And that, McGuire says, is where Qualcomm’s comes in. On-device artificial intelligence computing is something they’re doing effectively on their Snapdragon platforms


Screenshot_20230420_151816_LinkedIn.jpg
 
  • Like
  • Fire
  • Love
Reactions: 19 users

Dang Son

Regular
"analog-mixed signal computing architecture" is bad. Akida's pure digital approach the way to go for cheap, billions of IP orders inside billions of MCUs. We're in the box seat. We just need someone to spill the beans and tell us they just pre-ordered some Akida 2000's
Thanks Iseki, I'm none too technical but they seem to use all they same terms as Brainchip.
Maybe they're just faking it.
 
  • Like
Reactions: 2 users

Iseki

Regular
Thanks Iseki, I'm none too technical but they seem to use all they same terms as Brainchip.
Maybe they're just faking it.
Well, we need @Diogenese , a free thinker who has suffered penury all these centuries whose tide is about to turn.
 
  • Like
Reactions: 5 users

skutza

Regular
Damn it, I said no more, I accidently :) grabbed another 21,428 shares at the end of day Auction........

1681972562088.png
 
  • Like
  • Haha
  • Love
Reactions: 29 users

suss

Regular
  • Haha
  • Like
  • Wow
Reactions: 11 users

manny100

Top 20
Yes they will, as Tony previously stated.
Sean said in one of the recent April investor presentations that License fees were 7 digits or multiple of. Royalties after that.
 
  • Like
  • Fire
Reactions: 10 users

Dang Son

Regular
"analog-mixed signal computing architecture" is bad. Akida's pure digital approach the way to go for cheap, billions of IP orders inside billions of MCUs. We're in the box seat. We just need someone to spill the beans and tell us they just pre-ordered some Akida 2000's
"Innatera’s processors leverage the computing capabilities of spiking neural networks to deliver ground-breaking cognition performance within a narrow power envelope."
Does this claim from Innatera sound like its processors leverage Akida to perform the function of

UNLOCKING TRUE NEUROMORPHIC PATTERN RECOGNITION​

?

 
  • Like
  • Thinking
Reactions: 3 users

Terroni2105

Founding Member
  • Like
  • Fire
  • Love
Reactions: 58 users
Hi @Sirod,

Thanks so much for offering to keep me company in the naughty corner. That's such a lovely thing to say! How about you bring the milk and I'll bring the cat food and scratchy pole? 😆

Miraculously I haven't been ejector-seated out of here just yet. It isn't that I want to go, it's just that someone keeps reporting my posts, which I think is not very kosher and an abuse of the reporting system itself IMO. And I believe this may have also happened to @Fact Finder.

I can't help but feel very suspicious about the motivations of some of these posters who are doing nothing but complaining. I have never begrudged anyone for having an opinion, but there's a difference between expressing legitimate concerns as opposed to completely saturating the thread with negative sentiment, over and over, rehashing the same complaints for no material purpose. They are not actually seeking to have any of their concerns addressed, as others have pointed out there are avenues for them to go down if they wish to do so without chocking up the thread unnecessarily. I can't help but call out that kind of behaviour and they don't seem to like it, which speaks volumes I think.


View attachment 34678

"Miraculously I haven't been ejector-seated out of here just yet."
And nor should you be Bravo. Keep fighting the good fight, your contributions are welcomed and valued by those of us genuine holders who have been here since the start. I have been sitting back, reading and watching of late and agree that there definitely has been a suss element that has emerged. I am as confident as I have been for a long time as I watch BRN continue to drive forward. In my opinion Its only a matter of time until the opportunists who are currently trading in doubt and negativity move on to their next meal.
 
  • Like
  • Fire
  • Love
Reactions: 29 users

buena suerte :-)

BOB Bank of Brainchip
  • Like
  • Haha
  • Fire
Reactions: 19 users

Adam82

Member
IMG_8921.jpeg
IMG_8920.jpeg
 
  • Like
  • Fire
Reactions: 11 users
Top Bottom