BRN Discussion Ongoing

Diogenese

Top 20
To further expand on my post now I have some time to grab the info.

The snips below are from a NASA paper Aug last year that outlines the RadNeuro Project that we know we have been involved in with other partners and the hardware issues.

NASA refers to neuromorphic chips / computing as NMC and can see why someone like Alphacore etc may want to get a rad hard chip in there....how our SNN IP would be affected (if at all)....above my pay grade @Diogenese

Sorry D...caught up with Chelsea again :ROFLMAO:

Original paper HERE


View attachment 38077

View attachment 38080

View attachment 38082

View attachment 38083

Julian says "hi".

"The most important function to preserve in avionics is the memory, which suffers bit upsets that may not be detectable (n)or correctable."

So there may be a place for MemRistors/ReRAM because they are more naturally rad-hard and do not store information in the same way as CMOS bits are stored.

In other words, a hybrid technology of CMOS on FDSOI and ReRAM may be a solution. Some of my almost fully depleted neurons keep spiking random scintillations of the ghostly outline of patents for such a hybrid circuit

This Intel patent contemplates using ReRAM with MOSFET/CMOS circuits:

WO2019005057A1 NON-VOLATILE LOGIC CIRCUIT EMPLOYING LOW-POWER MOSFET ENABLED BY NON-VOLATILE LATCHED OUTPUTS

1686310439615.png


Techniques are disclosed for forming a non-volatile hybrid logic circuit employing low-power MOSFET enabled by non-volatile latched outputs. The hybrid arrangement is able to achieve both circuit-level non-volatility and relatively lower power levels, neither of which can be attained using MOSFET/CMOS or non-volatile logic/memory elements on their own. Further, standard MOSFET/CMOS alone cannot be used with relatively low threshold voltages (VTs) due to leakage currents and lack of non-volatility during power gating, for example. Accordingly, the non-volatile elements of the hybrid circuit serve as flip-flops or register files to provide non-volatile latched outputs for preserving the state of the logic circuit even when not receiving power. Thus, in the hybrid circuit arrangement, low-VDD, low-VT MOSFET devices are operatively coupled with non-volatile logic/memory elements (e.g., spintronic devices, ferroelectric devices, magnetoresistive devices) to enable energy efficient, low-VDD, low-VT, non-volatile operation for a logic circuit.

the non-volatile element may include at least one of a spin-torque switched magnet, spin-hall effect- switched magnet, ferroelectric field-effect transistor (FeFET), ferroelectric capacitor, magnetic tunnel junction (MTJ), resistive random-access memory (ReRAM or RRAM), or magneto-electric-switched magnet.

Western Digital:

WO2023064005A1 HYBRID MEMORY MANAGEMENT OF NON-VOLATILE MEMORY (NVM) DEVICES FOR USE WITH RECURRENT NEURAL NETWORKS

1686311592745.png


Recurrent Neural Networks (RNNs) wherein a non-volatile memory (NVM) array provides a memory bank for the RNN. The RNN may include a Neural Turning Machine (NTM) and the memory bank may be an NTM matrix stored in the NVM array. In some examples, a data storage device (DSD) that controls the NVM array includes both a data storage controller and a separate NTM controller. The separate NTM controller accesses the NTM matrix of the NVM array directly while bypassing flash translation layer (FTL) components of the data storage controller. Additionally, various majority wins error detection and correction procedures are described, as well as various disparity count-based procedures.

Neural Turing Machines (NTMs), or more generally Memory Augmented Neural Networks (MANNs), are types of recurrent neural networks. An NTM has a neural network controller coupled to external memory resources with which the controller interacts using attentional mechanisms (e.g. mechanisms that focus the attention of the network on particular portions of data stored in the external memory). NTMs have the potential to accelerate the manner by which RNNs process information. There is an on-going need to provide improvements within NTMs, MANNs, and other RNNs, and with devices that are configured to implement NTMs, MANNs, and other RNNs
.
 
Last edited:
  • Like
  • Haha
  • Fire
Reactions: 9 users
How cool is this autonomous vehicle from Valeo!



I’d love a little Akida droid R2D2 in the future which combines a stereo, drinks fridge, vacuum, projector, wifi, power bank etc.

Looking at how quickly the tech is progressing I won’t have long to wait!

1686312182638.png





:)
 
  • Like
  • Love
  • Fire
Reactions: 12 users
How cool is this autonomous vehicle from Valeo!



I’d love a little Akida droid R2D2 in the future which combines a stereo, drinks fridge, vacuum, projector, wifi, power bank etc.

Looking at how quickly the tech is progressing I won’t have long to wait!

View attachment 38090




:)
I need one of those as an Esky to follow me round with my beers :LOL:
 
  • Haha
Reactions: 8 users

Dr E Brown

Regular
And Valeo gets in on the act.
 
  • Like
  • Fire
  • Love
Reactions: 15 users

TECH

Regular
With July fast approaching we enter the downhill slope to Christmas, this in my opinion is the real start of our journey
with regards, AKD 1500 and AKD 2.0 being released from our foundry partners, tested and re-tested by Anil and his team
of engineers, released to our EAP's for their final evaluation before deals are done and dusted, we as a company have done
everything possible to accommodate these "potential clients", this pattern cannot continue whereby they need to evaluate
AKD 3.0....the time has come to accept what has been created here, get those designs completed and get production of products
underway, Intel, IBM and others aren't on the same page as us...commit, lets get this brilliant technology rolling !

If what was quoted in a recent email from Antonio to one of our forum members, well that really says it all, potential clients investing
millions in developing products with Akida IP embedded, how can we lose, we have already won, they love the technology, time will
simply prove me and others right.

Exciting 18 months ahead....love Brainchip x Tech ❤️🧡💛💚💙💜🖤🤎
 
  • Like
  • Love
  • Fire
Reactions: 73 users

IloveLamp

Top 20
Last edited:
  • Like
  • Fire
  • Love
Reactions: 47 users

IloveLamp

Top 20
I'd hazard a guess it is driven around the hardware not so much SNN tech of their own imo.

If you search their site for neuromorphic there are no results but their solutions are around the hardware.


I've read other NASA papers and statements that 22nm FDSOI is what they prefer rad hardened.

They absolutely want neuromorphic processing but the radiation fries most hardware.

Maybe Alphacore are wanting to prove up the hardware and then NASA or whoever can implement the neuromorphic IP accordingly.

My thoughts anyway.
 
  • Like
  • Love
  • Fire
Reactions: 20 users

Glen

Regular
  • Like
Reactions: 10 users
If AM likes it; I like it too!

1686351080180.png


It’ll be interesting to see if MB patents involve Akida.

😀
 
  • Like
  • Love
  • Fire
Reactions: 36 users

Getupthere

Regular
This video is a must watch for all BRN holders

 
  • Like
  • Love
  • Fire
Reactions: 12 users

Evermont

Stealth Mode
Anil is normally very reserved. I have seen three separate acknowledgements on LinkedIn today. 🔥
 
  • Like
  • Fire
  • Love
Reactions: 20 users

HopalongPetrovski

I'm Spartacus!
This video is a must watch for all BRN holders


Interesting video.
Great to get an insight into the nature of the evolving auto business and how innovative mindsets disrupt given opportunity and frozen mindsets can get left in the dust over time.
Thanks for sharing. 🤣
 
  • Like
  • Fire
Reactions: 11 users
This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful :( But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/
 
  • Thinking
  • Fire
  • Love
Reactions: 7 users

Dr E Brown

Regular
This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful :( But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/
Perhaps because he’s the CEO of Tenstorrent?
 
  • Like
  • Haha
Reactions: 8 users

MrNick

Regular
This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful :( But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/
Jim Keller has also been very, publicly, wrong, on quite a few occasions.
 
  • Like
  • Love
Reactions: 10 users
Perhaps because he’s the CEO of Tenstorrent?


Hi @Dr E Brown and @MrNick I’m not saying he’s right.

I found a lot of his interview quite interesting and enlightening as I’m not in the industry so it’s nice to hear from thought leaders who are.

I’ve put my money where my mouth is and backing Brainchip however I respect others opinions. His disregard of SNN did seem to have more of a software focus so maybe he’s not up to date with Akida in particular; but I’m not knowledgable enough to disagree with him.

As most people in the industry he would have an agenda to push; but overall I enjoyed the interview.

:)

Edit: I also liked how he discussed the fact that the larger companies such as Intel or Nvidia don’t necessarily have entitlement to the next big successful thing and said smaller start-ups can have wins too!
 
  • Like
  • Love
  • Fire
Reactions: 19 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful :( But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/


It seemed like Jim Keller was downplaying SNN's. Comparing neuromorphic computing to just another type of encoding method isn't exactly fair or particularly accurate I'd have thought. I would have liked to have seen him address the known benefits such as real-time on-chip learning and training, reduced latency, improved privacy and security, low power consumption, etc..

And, he came across a little disingenuously IMO when he said "It's not likely that interesting, but maybe.."

Not that interesting? Good luck telling that to our growing list of partners as well as Renesas and MegaChips who are in the process of making this technology widely available.
 
  • Like
  • Fire
  • Love
Reactions: 35 users

HopalongPetrovski

I'm Spartacus!
This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful :( But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/
Interesting guy with an interesting and insightful take on how our minds work and the recent history of computing technology.
He poo poo's our spiking stuff as mere switches but that may just be bias built from his experience and personal narrative.
But I think he is worth a listen as he tries to distil his 40 years in the business into a prognosis of where we might be heading over the next 5 or so years. And I think he does it in a fairly genuine and honest way.
Thanks for sharing.
 
  • Like
  • Love
Reactions: 5 users
S

Straw

Guest
Interesting guy with an interesting and insightful take on how our minds work and the recent history of computing technology.
He poo poo's our spiking stuff as mere switches but that may just be bias built from his experience and personal narrative.
But I think he is worth a listen as he tries to distil his 40 years in the business into a prognosis of where we might be heading over the next 5 or so years. And I think he does it in a fairly genuine and honest way.
Thanks for sharing.
Aren't neurons essentially switches that have evolved with senses to be useful in the real world?
 
  • Like
  • Haha
  • Love
Reactions: 6 users

manny100

Top 20
Sean said at the Understanding AI interview after the AGM that Data Centre businesses and AI at the Edge businesses would complement each other (as opposed to compete).
There will be some data suitable for Data Centre's and some for AI at the Edge, eg BRN. Both will co exist side by side.
As AI moves to IOT, Autos, Industrial machinery and Health a lot of the data will be more suitable for the Edge for reasons we all know about, latency, low power use, cost, privacy etc.
The above is what is holding us up........... the delay in demand for items that use the Edge. Its only a matter of time before demand becomes explosive.
The above is the only risk BRN faces IMO and that is the explosion in Edge demand happens well before our First mover advantage is used up.
I figure we have at least 2 years maybe more as the advantage.
As Sean said once business is on board they are on board for generations of products.
He also said in a decade BRN aim to be one of the few leaders in Edge business (or words to that effect).
Anyway the key is understanding is that Data Centers' and At the Edge busineses are not in competition. Even a lot of Analysts do not get that.
 
  • Like
  • Fire
  • Love
Reactions: 18 users
Top Bottom