BRN Discussion Ongoing

[Esq.111]

Afternooon Bravo ,

Love your work. .

In Keeping with my generally off topic comments ........

For $1,000,000,000.00AU thay could also purchase Hamilton Island , She's on the market.
With their remaining $600,000,000.00AU then purchase a few BRN shares.

Stress Less i say.

Regards,
Esq.

 

[jtardif999]

Many ways lead to Rome, new on device abilities of Qualcomm, software solutions (don't heat up), low power consumption enabled by the integration of 5G and Bluetooth, In Memory computing and so on. It's not always about the best technology, it's about making money. Let's say Rolls Royce builds the best engines in the world, there is still no need all cars in the world use them.

Software solutions will not be able to or be limited to keep up with the evermore sophisticated AI models and use cases. 20th century tech will hit a wall in about 2025 imo.

 

[jtardif999]

We all know having the best technology doesn't equate to sales.

..yet

 

[Learning]

That look like the Akida 1000 PCIe Board to me?

Anyone has a zooming software?

Home

www.edgx.space

Nick Destrycker on LinkedIn: #edgx #space #spacetech #innovation #ai #neuromorphic #dpu #obdp #edhpc

🚀 Exciting News 🚀 EDGX emerging from the shadows to join the SpaceTech Revolution! 🛰️ Thrilled to announce the official launch of EDGX, a brand-new…

www.linkedin.com

Learning

 

[Esq.111]

Afternoon Learning ,

I concure.


.

Best I could zoom....

Regards,
Esq.

 

[Damo4]

View attachment 46049
View attachment 46051
View attachment 46053

That look like the Akida 1000 PCIe Board to me?

Anyone has a zooming software?

Home

www.edgx.space

Nick Destrycker on LinkedIn: #edgx #space #spacetech #innovation #ai #neuromorphic #dpu #obdp #edhpc

🚀 Exciting News 🚀 EDGX emerging from the shadows to join the SpaceTech Revolution! 🛰️ Thrilled to announce the official launch of EDGX, a brand-new…

www.linkedin.com

Learning

HUGE

and yes definitely Brainchip - if you squint you can make out the name hahah

 

[IloveLamp]

View attachment 46049
View attachment 46051
View attachment 46053

That look like the Akida 1000 PCIe Board to me?

Anyone has a zooming software?

Home

www.edgx.space

Nick Destrycker on LinkedIn: #edgx #space #spacetech #innovation #ai #neuromorphic #dpu #obdp #edhpc

🚀 Exciting News 🚀 EDGX emerging from the shadows to join the SpaceTech Revolution! 🛰️ Thrilled to announce the official launch of EDGX, a brand-new…

www.linkedin.com

Learning

 

[Damo4]

Edit it's also shown in their documentation manuals, so perhaps it comes pre-loaded, I'm just used to see the below image.

wonder what they've attached here:

 

[Jasonk]

Yea it is you can even see the brainchip logo on the PCB next to the chip.

 

[Bravo]

 

[SERA2g]

Yea it is you can even see the brainchip logo on the PCB next to the chip.

Yep, 100% correct.

Here's the PCB below, ignore the red box, just re-used Damo's picture..

And here's theirs - same akida * on the corner of the AKD1000 chip and diagonal to the round gold thing.

Great find @Learning

Edit: Great work to @chapman89 who commented on the EdgX announcement post on LinkedIn before the pictures surfaced here on TSEX. 1000 eyes strikes again!

 

[jtardif999]

There’s easy ways a round that..

“top holders would 100% block…”

Price gets bled down whilst “unrelated parties” continue to sell to each other increasing their ownership.. It wouldn’t be that hard to accumulate over several years a controlling interest that can vote out majority holders like PVDM and Anil.and others if they “don’t play ball”.. The price has come down around 90%.. Easy sell to vote out underperformance on executive BOD’s if they don’t “play ball” so to speak..

Once they control the vote, they then can manipulate what any large holder does.. It’s fairly well recognised that this sort of behaviour occurs constantly in business to funnel money and power to where the controlling elite want it to go..

Who you know and who benefits is more important than who has the ideas and has done all the groundwork..

But.. Peter owns the foundation patent (circa 2008 - Brain-inspired Device) good till 2028. They whoever would need him to sell that patent - even if BRN board agreed to a buy out of the other patents, which they wouldn’t imo he still has control of the foundation patent and he’s not likely to give that up.

 

[Learning]

Yep, 100% correct.

Here's the PCB below, ignore the red box, just re-used Damo's picture..

View attachment 46063
And here's theirs - same akida * on the corner of the AKD1000 chip and diagonal to the round gold thing.

View attachment 46064

Great find @Learning

Was about to post the same thing.

Woohoo

Learning

 

[Damo4]

Damn, Chapman was on it almost 24hrs ago!
You guys are the best, this forum has literally changed overnight with the removal of the trouble makers.

Company links for anyone interested:
https://www.edgise.com/
https://www.edgx.space/

 

[Pappagallo]

NASA, TCS, ANT61 and now EDGX.

Akida will be spending more time in space than Sigourney Weaver.

 

[wilzy123]

Afternoon Learning ,

I concure.


.

Best I could zoom....

Regards,
Esq.

I just checked to make sure

 

[AusEire]

I just checked to make sure

View attachment 46068

To be honest I think this is too much dot joining!!!!!

My opinion only

DYOR

 

[Damo4]

I just checked to make sure

View attachment 46068

Did you break something on your board, or was the mod for something else?

 

[wilzy123]

Did you break something on your board, or was the mod for something else?

That's an original board (unmodified).

 

[jtardif999]

This is Apple's toaster patent:

US2022222510A1 MULTI-OPERATIONAL MODES OF NEURAL ENGINE CIRCUIT 20210113



View attachment 45961

[0052] Referring to FIG. 3, an example neural processor circuit 218 may include, among other components, neural task manager 310 , a plurality of neural engines 314 A through 314 N (hereinafter collectively referred as “neural engines 314 ” and individually also referred to as “neural engine 314 ”), kernel direct memory access (DMA) 324 , data processor circuit 318 , data processor DMA 320 , and planar engine 340

[0053] Each of neural engines 314 performs computing operations for machine learning in parallel. Depending on the load of operation, the entire set of neural engines 314 may be operating or only a subset of the neural engines 314 may be operating while the remaining neural engines 314 are placed in a power-saving mode to conserve power. Each of neural engines 314 includes components for storing one or more kernels, for performing multiply-accumulate operations, for performing parallel sorting operations, and for post-processing to generate an output data 328 , as described below in detail with reference to FIGS. 4A and 4B. Neural engines 314 may specialize in performing computation heavy operations such as convolution operations and tensor product operations. Convolution operations may include different kinds of convolutions, such as cross-channel convolutions (a convolution that accumulates values from different channels), channel-wise convolutions, and transposed convolutions.


View attachment 45962


[0063] FIG. 4A is a block diagram of neural engine 314 , according to one embodiment. Specifically, FIG. 4A illustrates neural engine 314 perform operations including operations to facilitate machine learning such as convolution, tensor product, and other operations that may involve heavy computation in the first mode. For this purpose, neural engine 314 receives input data 322 , performs multiply-accumulate operations (e.g., convolution operations) on input data 322 based on stored kernel data, performs further post-processing operations on the result of the multiply-accumulate operations, and generates output data 328 . Input data 322 and/or output data 328 of neural engine 314 may be of a single channel or span across multiple channels.

It has 16 neural engines each with an array of MAC (multiply

I skimmed it and these guys look like they know their sheet..
And they are bagging AKIDA, in a sense, lumping us with TrueNorth and Loihi 2..

View attachment 46025

What they're doing is "Open source" WTF is their game?..

I'd like to know what Diogenese thinks too and Peter, on this one..

But we know Akida is agnostic both in terms of the data it can process and the preprocessor it works with to specify the synaptic weights. Akida1500 has been created to plug in any preprocessor tech so the info in that paper is a little outdated and somewhat misleading imo.