BRN Discussion Ongoing

Bravo

If ARM was an arm, BRN would be its biceps💪!
From the 30min on time frame Dr Harbor talks about the start up of Neuromorphic computing and he goes on to say
"At the end of the day after the long haul we are going to see the analog neuromorphic like processor is going to win out."
We are digital but we use Spikes instead of 1's and 0's is my understanding.
Now I'm confused. Any further explanation would be gratefully accepted.


Hi Boab,

I must admit I was a tad concerned hearing Dr. Harbour’s comments given Akida is digital, not analog.

At 25:00, he says:

“BrainChip’s Akida probably has, if not the first commercialised neuromorphic processor, is amongst the first commercialised. You can buy that today and you can get support with it. Again it’s a digital-based neuromophphic processor with a neuromorphic mesh, if you will. Full blown neuromorphics will involve something that’s very analogue-like - like the mind. And we’re we’re working on that. In fact I’m working on a specific program right now of doing that.”

At 31:00, he adds:

"Dr Carver Meade at Caltech. And I’m going to give him credit for the start of this, envisioned an analogue processor, if you will. This was in the early 80’s, maybe even before that in the late 70’s. And so he started that and at the same time, the digital concept processor was a competitor. And, at the end, we’re going to see, after the long haul, the analogue processor is going to win out."

My non-expert read is that Dr. Harbour clearly respects Akida as one of the first commercial, supported neuromorphic options today, while also betting that analog approaches could dominate long-term if variability and accuracy are tamed.

Given these remarks, I poked around on the interwebs to see if I could find out what analog project he might be working on and found a talk dated 16 October 2022 (see video below).

At 8:10, he says “we made silicon brain” and he shows a slide (see below) titled “Our work: Analog Memristor.”

I can only speculate that Dr Harbour may be intending on continuing his prior analog/memristive neuromorphic work toward a processor?? At least he frames it as a “long haul,” which hopefully indicates there's plenty of runway for Akida to build market share in the meantime.

I’d like to hear Tony Lewis’s view on Dr Harbour's remarks, but I'm not sure that IR will even respond to my email, as they didn't respond to the last email I sent them. In the meantime, I asked ChatGPT for a neutral take on Dr. Harbour’s statements, as well as its opinion on analog variability, etc. for what it's worth.

PS: I'm also going to ask Tony if BrainChip sees analog/mixed-signal blocks as complementary to Akida in future hybrid systems.





ChatGPT said:​



Great spot—and yes, you heard him right.

What Dr. Steven Harbour (Parallax) is saying​

  • Parallax posted an interview/profile with Dr. Steven D. Harbour (Director, AI Hardware Research; Neuromorphic Center of Excellence) this year where he talks up neuromorphic for defense/EW and edge systems. Parallax Advanced Research
  • His comments about Akida being among the first commercial neuromorphic processors you can buy and get support for are fair: Akida is a digital neuromorphic IP/processor with a mesh architecture and shipping toolchain. (That’s the “today” story.)
  • He then pivots to the “full-blown neuromorphics” = more analog-like view—rooted in Carver Mead’s original analog VLSI neuromorphic work in the ’80s. History of Information+1

Is analog “less stable” than digital?​

Short answer: it’s more variable, unless you engineer around it.
  • Analog & mixed-signal neuromorphics face device mismatch, process/voltage/temperature (PVT) drift, and noise; emerging analog synapses (e.g., memristors/ReRAM/PCM) add cycle-to-cycle variability and resistance drift. This can degrade accuracy unless you calibrate/compensate. arXiv+3Frontiers+3AIMS Press+3
  • Reviews and roadmaps explicitly note these reliability/variability challenges for analog in-memory devices (RRAM/PCM): drift, non-linearity, device-to-device variation, filament randomness. AIP Publishing+2ScienceDirect+2
  • By contrast, digital neuromorphics avoid most mismatch/drift and are easier to reproduce across process nodes; that’s a big reason digital platforms (like Akida) reached market first. Nature
That said, there’s active progress: compensation and calibration schemes, chip-in-the-loop training, and architectures that embrace variability are improving analog reliability. MDPI+1

Why Harbour (and others) still think analog could “win” long-term​

This view comes straight from the analog VLSI neuromorphic lineage (Mead et al.) and today’s analog in-memory research:
  • Energy & area efficiency: analog compute-in-memory can perform MACs where the weights live, slashing data movement (the big energy cost) and reducing transistor count per operation—huge for always-on edge. Polyn Technology
  • Continuous-time physics: analog circuits naturally implement certain neural dynamics (integration, leakage, spiking) with very low power and microsecond-class latency, which maps well to sensing at the edge. WVU Community
  • Mixed-signal best of both worlds: many see the endgame as hybrid—analog for the heavy, low-energy linear ops and temporal dynamics; digital for control, memory management, safety and programmability. Patsnap Eureka

Putting it together (and reconciling with Akida)​

  • Today: Digital neuromorphics like Akida are commercial, supported, and predictable, which is why you can buy them now and integrate them relatively quickly.
  • Tomorrow: If (big “if”) analog neuromorphic platforms tame variability and ship robust toolchains, they can deliver even lower power per task—which is why Harbour says they may ultimately “win.” In practice, the likely winner is mixed-signal: analog compute blocks plus digital orchestration.




Analog pm.png
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 21 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Overall Efficiency: 280%+ improvement in accuracy-per-energy ratio!
It would appear the gentlemen below from VW running more projects with Akida. Uploaded to GitHub yesterday.

Results look strong.

Fernando Sevilla Martínez​





SevillaFe/EcoEdgeAI-akida-macPublic

A comprehensive workflow for comparing energy efficiency between conventional hardware (Mac M-series GPU/CPU) and neuromorphic hardware (Akida on Raspberry Pi 5) for autonomous driving steering angle prediction.

SevillaFe/EcoEdgeAI-akida-mac​




Name
SevillaFe SevillaFe
yesterday
LICENSEyesterday
README.mdyesterday
requirements_mac.txtyesterday
requirements_rpi5.txtyesterday
workflow_guide.mdyesterday

Repository files navigation​

EcoEdgeAI-akida-mac​

A comprehensive workflow for comparing energy efficiency between conventional hardware (Mac M-series GPU/CPU) and neuromorphic hardware (Akida on Raspberry Pi 5) for autonomous driving steering angle prediction.
License: MIT Python 3.8+ TensorFlow 2.16+

🎯 Project Overview​

This project provides a complete pipeline to:
  • Train deep learning models (PilotNet, LaksNet, MiniNet) for steering angle prediction
  • Benchmark inference performance on conventional hardware with CodeCarbon energy tracking
  • Convert models to neuromorphic format using Akida
  • Benchmark neuromorphic inference with TC66 USB power meter
  • Generate comprehensive eco-efficiency comparisons

Key Research Questions​

  • How much energy does neuromorphic computing save?
  • What is the accuracy trade-off?
  • What is the latency difference?
  • Which architecture is most efficient for edge deployment?

📊 Results Preview

Our experiments show:
  • Energy Efficiency: Up to 76% reduction in energy consumption per inference
  • Latency: 40-50% faster inference on neuromorphic hardware
  • Accuracy: Minimal degradation (<10% MSE increase)
  • Overall Efficiency: 280%+ improvement in accuracy-per-energy ratio

🛠️ Hardware Requirements​

Mac (Training & Benchmarking)​

  • MacBook with M-series processor (M1/M2/M3)
  • 16GB+ RAM recommended
  • macOS 12.0+

Raspberry Pi 5 (Neuromorphic Benchmarking)​

  • Raspberry Pi 5 (4GB/8GB)
  • BrainChip Akida neuromorphic processor board
  • TC66/TC66C USB power meter
  • 32GB+ microSD card
  • Active cooling recommended


1124067_orig (1).gif



Overall Efficiency: 280%+ improvement in accuracy-per-energy ratio!!!!!
 
  • Like
  • Love
  • Fire
Reactions: 15 users

DK6161

Regular
The pump Sold again within two days… and the moment it starts rising, you immediately get a ticket. Just ridiculous what’s going on.
No normal positive news will bring us back to even 25-30 cent… without revenue we will be the play ball for shelters and day trader… very simple
Ok bye. Sick of you bringing nothing bad negative views here. We don't need anymore downrampers around here. Go back to hotcrapper you belong
Surprised none of you (including chartist’s) have worked out who the big manipulators of BRN are.

Take a look at the chart for the last six trading days and you’ll see a trend.

View attachment 92122


JP MORGAN, one of the biggest investor banks (Fourth biggest BRN shareholder, and one of the biggest manipulators in my view) released this on the 13/10/2025.

Possibly started selling off at the high on the 09/10/2025, then released this on the 13/10/2025 to get the price back up 👇

JPMorganChase Launches $1.5 Trillion Security and Resiliency Initiative to Boost Critical Industries​

The firm will make direct equity investments of up to $10 billion as part of the $1.5 trillion initiative to address pressing needs in key sectors from critical minerals to frontier technologies
New York

October 13, 2025


JPMorganChase today announced the Security and Resiliency Initiative, a $1.5 trillion, 10-year plan to facilitate, finance and invest in industries critical to national economic security and resiliency.

As part of this new initiative, JPMorganChase will make direct equity and venture capital investments of up to $10 billion to help select companies primarily in the United States enhance their growth, spur innovation, and accelerate strategic manufacturing.

“It has become painfully clear that the United States has allowed itself to become too reliant on unreliable sources of critical minerals, products and manufacturing – all of which are essential for our national security,” said Jamie Dimon, Chairman and CEO of JPMorganChase. “Our security is predicated on the strength and resiliency of America’s economy.

America needs more speed and investment. It also needs to remove obstacles that stand in the way: excessive regulations, bureaucratic delay, partisan gridlock and an education system not aligned to the skills we need.” The firm’s effort comes at a time when the U.S. is looking to modernize infrastructure, fortify supply chains, and implement policies that promote growth.

JPMorganChase will focus on the following four key areas, supporting companies across all sizes and development stages by offering advice, providing financing, and, in some cases, investing capital:
  • Supply Chain and Advanced Manufacturing, including critical minerals, pharmaceutical precursors and robotics
  • Defense and Aerospace, including defense technology, autonomous systems, drones, next-gen connectivity and secure communications
  • Energy Independence and Resilience,including battery storage, grid resilience and distributed energy
  • Frontier and Strategic Technologies,including AI, cybersecurity and quantum computing
More specifically, the firm has currently divided these four key areas into 27 sub-areas, ranging from shipbuilding and nuclear energy to nanomaterials and critical defense components.

The firm had already planned to facilitate and finance approximately $1 trillion over the next decade in support of clients in these important industries. With additional resources, capital and focus, JPMorganChase aims to increase this amount by up to $500 billion—or a 50% increase. These activities will cut across both middle-market companies and large corporate clients.

Dimon added, “This new initiative includes efforts like ensuring reliable access to life-saving medicines and critical minerals, defending our nation, building energy systems to meet AI-driven demand and advancing technologies like semiconductors and data centers. Our support of clients in these industries remains unwavering.”

A History of Investment in Critical Industries​

JPMorganChase has been a leader in global financial services for more than 200 years, playing a critical role in supporting America’s interests. The firm is uniquely positioned to accelerate investments that enhance resiliency and drive innovation across industries in the United States and around the world.

The firm has extraordinary relationships – serving 34,000 mid-sized companies and more than 90% of the Fortune 500 – and is a key partner to leading private equity and venture capital firms. Its Commercial & Investment Bank has been the top investment bank for more than 15 years with long-standing relationships in the defense, aerospace, healthcare and energy sectors, and a proven track record advising on landmark transactions in those industries.

Drawing on the Firm’s Expertise​

Given the expected business opportunities and significance of this mission, JPMorganChase will hire more bankers, investment professionals and other experts to address this critical initiative.

Additionally, the firm will create an external advisory council of experienced leaders from the public and private sectors to help guide the long-term strategy.

The initiative will also include special, thematic research on private companies and supply chain management issues related to rare earths, AI and technology. It will also be complemented by the firm’s recently launched Center for Geopolitics, which provides clients with timely analyses and insights on top global trends.

In addition, the firm’s effort is supported by our Asset & Wealth Management division, which already researches and invests in many of these critical industries. This effort will be further informed by JPMorganChase’s own technology investments, including quantum computing, cyber security and AI research and capabilities.

Policy is essential, too, and the firm will advocate for policies that can accelerate these efforts, including research and development, permitting, procurement and regulations conducive to growth.

As the bank intensifies its focus on these essential industries, it will also continue to work closely with its community and business partners to champion these sectors, foster talent and support skills training to ensure companies can fill critical jobs.

Dimon concluded, “Hopefully, once again, as America has in the past, we will all come together to address these immense challenges. We need to act now.”

JPMorganChase & Co. (NYSE: JPM) is a leading financial services firm based in the United States of America (“U.S.”), with operations worldwide. JPMorganChase had $4.6 trillion in assets and $357 billion in stockholders’ equity as of June 30, 2025. The Firm is a leader in investment banking, financial services for consumers and small businesses, commercial banking, financial transaction processing and asset management. Under the J.P. Morgan and Chase brands, the Firm serves millions of customers predominantly in the U.S., and many of the world’s most prominent corporate, institutional and government clients globally. Information about JPMorganChase & Co. is available at www.JPMorganChase.com.

👆Then started selling off again to get the price down so they can buy them back cheaper again. If they are true to form they’ll be scooping them back up again before long.

If none of that rings true, then just chalk this post down to a me being bored and a glitch in your normal BRN transmissions or whatever.
Yeah a bit of a stretch there bud.
The whole thing has been going to shit since 3 years ago. Nothing to do with JP Morgan.

I am not a genius, but maybe it is simply because of the lack of material announcements.

Kombucha Funny Meme GIF
 
  • Like
  • Haha
  • Fire
Reactions: 4 users

7für7

Top 20
Come on shorts…. Don’t disappoint me… I want to see the 20 or if you are tough…19 would impress me! COME ON!
 
  • Haha
Reactions: 2 users
Surprised none of you (including chartist’s) have worked out who the big manipulators of BRN are.

Take a look at the chart for the last six trading days and you’ll see a trend.

View attachment 92122


JP MORGAN, one of the biggest investor banks (Fourth biggest BRN shareholder, and one of the biggest manipulators in my view) released this on the 13/10/2025.

Possibly started selling off at the high on the 09/10/2025, then released this on the 13/10/2025 to get the price back up 👇

JPMorganChase Launches $1.5 Trillion Security and Resiliency Initiative to Boost Critical Industries​

The firm will make direct equity investments of up to $10 billion as part of the $1.5 trillion initiative to address pressing needs in key sectors from critical minerals to frontier technologies
New York

October 13, 2025


JPMorganChase today announced the Security and Resiliency Initiative, a $1.5 trillion, 10-year plan to facilitate, finance and invest in industries critical to national economic security and resiliency.

As part of this new initiative, JPMorganChase will make direct equity and venture capital investments of up to $10 billion to help select companies primarily in the United States enhance their growth, spur innovation, and accelerate strategic manufacturing.

“It has become painfully clear that the United States has allowed itself to become too reliant on unreliable sources of critical minerals, products and manufacturing – all of which are essential for our national security,” said Jamie Dimon, Chairman and CEO of JPMorganChase. “Our security is predicated on the strength and resiliency of America’s economy.

America needs more speed and investment. It also needs to remove obstacles that stand in the way: excessive regulations, bureaucratic delay, partisan gridlock and an education system not aligned to the skills we need.” The firm’s effort comes at a time when the U.S. is looking to modernize infrastructure, fortify supply chains, and implement policies that promote growth.

JPMorganChase will focus on the following four key areas, supporting companies across all sizes and development stages by offering advice, providing financing, and, in some cases, investing capital:
  • Supply Chain and Advanced Manufacturing, including critical minerals, pharmaceutical precursors and robotics
  • Defense and Aerospace, including defense technology, autonomous systems, drones, next-gen connectivity and secure communications
  • Energy Independence and Resilience,including battery storage, grid resilience and distributed energy
  • Frontier and Strategic Technologies,including AI, cybersecurity and quantum computing
More specifically, the firm has currently divided these four key areas into 27 sub-areas, ranging from shipbuilding and nuclear energy to nanomaterials and critical defense components.

The firm had already planned to facilitate and finance approximately $1 trillion over the next decade in support of clients in these important industries. With additional resources, capital and focus, JPMorganChase aims to increase this amount by up to $500 billion—or a 50% increase. These activities will cut across both middle-market companies and large corporate clients.

Dimon added, “This new initiative includes efforts like ensuring reliable access to life-saving medicines and critical minerals, defending our nation, building energy systems to meet AI-driven demand and advancing technologies like semiconductors and data centers. Our support of clients in these industries remains unwavering.”

A History of Investment in Critical Industries​

JPMorganChase has been a leader in global financial services for more than 200 years, playing a critical role in supporting America’s interests. The firm is uniquely positioned to accelerate investments that enhance resiliency and drive innovation across industries in the United States and around the world.

The firm has extraordinary relationships – serving 34,000 mid-sized companies and more than 90% of the Fortune 500 – and is a key partner to leading private equity and venture capital firms. Its Commercial & Investment Bank has been the top investment bank for more than 15 years with long-standing relationships in the defense, aerospace, healthcare and energy sectors, and a proven track record advising on landmark transactions in those industries.

Drawing on the Firm’s Expertise​

Given the expected business opportunities and significance of this mission, JPMorganChase will hire more bankers, investment professionals and other experts to address this critical initiative.

Additionally, the firm will create an external advisory council of experienced leaders from the public and private sectors to help guide the long-term strategy.

The initiative will also include special, thematic research on private companies and supply chain management issues related to rare earths, AI and technology. It will also be complemented by the firm’s recently launched Center for Geopolitics, which provides clients with timely analyses and insights on top global trends.

In addition, the firm’s effort is supported by our Asset & Wealth Management division, which already researches and invests in many of these critical industries. This effort will be further informed by JPMorganChase’s own technology investments, including quantum computing, cyber security and AI research and capabilities.

Policy is essential, too, and the firm will advocate for policies that can accelerate these efforts, including research and development, permitting, procurement and regulations conducive to growth.

As the bank intensifies its focus on these essential industries, it will also continue to work closely with its community and business partners to champion these sectors, foster talent and support skills training to ensure companies can fill critical jobs.

Dimon concluded, “Hopefully, once again, as America has in the past, we will all come together to address these immense challenges. We need to act now.”

JPMorganChase & Co. (NYSE: JPM) is a leading financial services firm based in the United States of America (“U.S.”), with operations worldwide. JPMorganChase had $4.6 trillion in assets and $357 billion in stockholders’ equity as of June 30, 2025. The Firm is a leader in investment banking, financial services for consumers and small businesses, commercial banking, financial transaction processing and asset management. Under the J.P. Morgan and Chase brands, the Firm serves millions of customers predominantly in the U.S., and many of the world’s most prominent corporate, institutional and government clients globally. Information about JPMorganChase & Co. is available at www.JPMorganChase.com.

👆Then started selling off again to get the price down so they can buy them back cheaper again. If they are true to form they’ll be scooping them back up again before long.

If none of that rings true, then just chalk this post down to a me being bored and a glitch in your normal BRN transmissions or whatever.
That’s a big thumbs up fro me and a 1st for one of your posts

1760671924191.gif
 
  • Like
Reactions: 2 users

SERA2g

Founding Member
For years, the prevailing narrative among BRN retail shareholders has been that Mercedes-Benz engineers had trialled Intel Loihi for a number of years before switching to Akida for their VISION EQXX concept car. Which could only mean one thing, right?

“Fact” Finder, for example, has repeatedly brought this up and claimed the following on HC as recently as last month:

[Sorry, @CHIPS, TSE will not allow direct links to that other website, but you can search for the post under the author’s name and the 7 September date… 😉]

View attachment 92056

[…]


View attachment 92057


Where is the evidence for this? Can anyone provide links to verifiable sources in order to substantiate the above claim? If yes, please share them here with us. I’m especially curious to find out how MB would have managed to work with Loihi long before it was even announced (which was in September 2017) and officially launched (in January 2018).

Here are the facts and timelines that I have so far established for myself.
While I cannot rule out that I may have overlooked something, this whole Mercedes-found-a-new-love-narrative has always seemed pretty fishy to me, and I now happened to stumble across additional evidence to the contrary.
This post is not meant to turn into a discussion about which neuromorphic processor is superior or that only one of them is commercially available as I write - it is about the veracity of the narrative we have been fed for so long by fellow forum members.


In 2018, Intel established the Intel Neuromorphic Research Community (INRC), which includes academic, government and industry research groups. The INRC’s first corporate members were announced in November 2019: Accenture, Airbus, GE and Hitachi. Mercedes-Benz, however, didn’t join the INRC until late 2020.



At Intel Labs Day on 3 December 2020, which was held as a virtual event, Intel announced “the addition of Lenovo, Logitech, Mercedes-Benz and Prophesee to explore the value of neuromorphic computing for business use cases”.


The following quote by Jasmin Eichler, then Director of Future Technologies at MB, gives no indication whatsoever that Mercedes-Benz had already been evaluating Loihi prior to joining INRC. Unsurprisingly, I should add, since becoming an INRC Research Member (for which a sufficiently detailed project proposal must first be submitted) has always been a prerequisite for being granted access to Loihi.


View attachment 92058


And no, the mere fact that Accenture Labs - as an early INRC member - had been working with “an undisclosed automotive client” on voice command recognition for interaction with smart vehicles using Loihi in 2020, before Mercedes-Benz joined the INRC, does not prove that this automotive client was Mercedes-Benz (cf @SERA2g ’s post kicking off the BRN - Mercedes subthread:
https://thestockexchange.com.au/threads/brn-mercedes.150/).







Besides, MB have their own team of future technology researchers and thus wouldn’t have needed to rely on Accenture to explore Loihi on their behalf.
I also doubt Intel would have worded their Intel Labs Day 2020 announcement the way they did if the undisclosed carmaker on behalf of which Accenture was evaluating Loihi had been the same carmaker who had just joined them. The same goes for the author of the WSJ article - if the promising results of the Accenture evaluation had been the reason for the “undisclosed automotive client” to eventually join the INRC themselves, why still keep it a secret in retrospect now they have become a research member? That doesn’t make sense to me.

Anyway, it is definitely not conclusive evidence to support the above claim that Mercedes-Benz had been working with Intel “for years” before they had a change of heart, after falling head over heels in love with Akida.

Oh, and before anyone suggests it: I already DID scroll through all 11 pages of the BRN - Mercedes subthread, but couldn’t find any proof whatsoever of MB’s collaboration with Intel on neuromorphic computing predating the one with BrainChip...

One thing was clear to me from the outset: We know from the horse’s mouth that the VISION EQXX concept car (unveiled during CES in early January 2022) went from idea to prototype in only 18 months, so unless they added in the idea of implementing the voice control function on a neuromorphic chip at a later stage or changed their mind midway about which neuromorphic chip to work with (both highly unlikely, though), the relevant MB engineers must have been familiar with Akida by no later than mid-2020.
Months before Mercedes-Benz even joined the INRC, that is.

Remember the original Mercedes-Benz press release that mentioned systems (in the plural!) based on Akida developed by their engineers? I’d always wondered what else they had explored…


“Working with California-based artificial intelligence experts BrainChip, Mercedes-Benz engineers developed systems based on BrainChip's Akida hardware and software.”

… and now I know - at least in part!

Voilà, here is proof that Mercedes-Benz were already evaluating Akida for in-car gesture recognition in combination with event-based cameras between October 2019 and June 2020!

I discovered this intriguing piece of information in the LinkedIn work experience section of Gunjan Gupta, now a Senior Software Developer with SAP, who was placed with Mercedes-Benz as a working student during her time when she was enrolled for an IT Master’s programme at Uni Stuttgart - just like other Master students after her, eg Sreelakshmi Rameshan from February to September 2024 (https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-443909 as well as
https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-443910)
and Krishnaprasad Thoombayil Satheesh from August 2024 to February 2025 (https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-468997).

While the two of them also wrote their Master’s theses during their industrial placement (both of them doing comparisons involving Akida, Loihi 2 and SynSense Speck), Gunjan Gupta wrote her Master’s thesis on an unrelated topic and only after her part-time job as a working student with MB (1 year 5 months in total) had ended. Why she did not pick a topic relating to what she had worked on with the BrainChip ADE (Akida Development Environment), we can only speculate.



View attachment 92059
View attachment 92060
View attachment 92061


So to sum it up: If we are to believe Gunjan Gupta’s LinkedIn profile (and I don’t have any reason to doubt the information provided), Mercedes-Benz researchers were already working with Akida as early as October 2019 - more than a year before they joined the Intel Neuromorphic Research Community!

This timeline also explains, by the way, why there was never any announcement about Mercedes-Benz having joined the EAP (Early Access Program) - just like Ford, they had already become a BrainChip customer months before the EAP was officially launched in June 2020. As I noted before, MB were, however, referred to as one of BrainChip’s “Marquee EAP customers” from at least as early as September 2023 (https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-464731).

So unless someone can come up with compelling evidence for the claim that Mercedes-Benz had indeed worked with Loihi “for years”, before picking Akida as their neuromorphic processor of choice for their VISION EQXX concept car, let’s banish this widely held belief to where I strongly suspect it belongs: to the realm of myths and fairy tales.

Hi Frang

I haven't looked back at my original post but do recall if being very sequential and clear that Intel came before Akida with respect to Mercedes.

Your find of Gunjan Gupta could well flip the timeline and therefore change the narrative slightly. Ie. They tried akida, then Loihi.... But the narrative is still materially unchanged.

That narrative being: Mercedes have looked at both Loihi and Akida and as we know, utilised akida in the EQXX.

Correct me if I'm wrong but it seems to me we're talking about semantics here and agree on the overall outcome?
 
  • Like
  • Fire
Reactions: 13 users

BigDonger101

Founding Member
LOL-LOL.

I couldn't care less what he says and thinks.

He is properly behind some of the pathetic downrampers over at the crapper.

Let Sean stick to his 5 years plan & 9 mill income this year. If not, his next AGM will be very hard and maybe the last one for him.

Until then, I keep quiet about any criticism and let the man do his work.
You probably should take on what he says.

They're not really down rampers anymore. Facts speak for themselves currently.

Communication to shareholders is genuinely abhorrent.
 
  • Fire
  • Like
Reactions: 6 users
What an interview.

Time well invested to have a listen.

I thought Space Technology was the segment for AKIDA to shine.
Turns out, listening to this, it is very much military applications first, & then space technology.

And the sense of urgency was palpable ... it IS the future ... and we MUST beat China in implementing neuromorphic solutions into our military ( as in - US Military ). And Brainchip is mentioned throughout.

To me, it is reasonably obvious to understand what has been going on in BrainChip for the last couple of years.
Explains much of the silence from management ( not all ), the whole de-listing & moving to the US fiasco, and HIGHLY confidential nature of what we are doing - our lead segment is the US "War" cabinet - and BrainChip is in the middle of it. Don't expect much to be said ... too much on the line .

For investors, it's a tough place to be. Guess you either believe in the technology and trust management ( & hold ), or think it is all smoke & mirrors ( & sell ).

I continue to hold, and buy when I can.
How many shares do you currenlty have?
 
Maybe I missed it or forgotten about but this project appears to have only just started at the beginning of Sept with OHB, fortiss etc.


AI4FDIR​

AI-based system for fault detection, recovery, and resource management in satellites

AI4FDIR​

AI4FDIR is an ESA-funded project led by OHB System AG to develop an AI-based framework for autonomous fault detection, isolation, and recovery (FDIR), as well as constellation-level management and resource optimization in satellite telecommunication systems. By combining machine learning, deep learning, and neuromorphic computing, the project targets a tenfold reduction in both operational outage time and the time to restore nominal service. The consortium—comprising OHB DC, OHB Hellas, SATE, Kepler, and fortiss—will validate the approach through simulators and hardware-in-the-loop platforms, including BrainChip’s Akida neuromorphic processors. fortiss will implement a neuromorphic proof-of-concept for spacecraft-level FDIR.

Project description​

The project addresses the need for greater autonomy in managing large satellite constellations, where traditional ground-based fault management is costly, slow, and increasingly impractical. The main challenge is to detect, isolate, and resolve failures on board in real time, while predicting potential degradations before they affect service.

To tackle this, the consortium combines advanced AI methods with neuromorphic hardware, enabling fast, low-power decision-making directly on spacecraft. This proof-of-concept approach will demonstrate how predictive monitoring and autonomous recovery can reduce outage and restoration times by an order of magnitude and pave the way for resilient, self-managing space systems.

Research contribution​

fortiss will investigate CNN-based classification and detection algorithms on the BrainChip Akida platform. In addition, we will explore pattern-matching techniques, encoders, and complementary network architectures to process heterogeneous multi-channel inputs. As a first step, we will use the public ESA anomaly dataset to identify suitable network models for fault detection. Building on these results, we will validate the implemented algorithms using real-time data from Kepler and the OHB constellation simulator.

Funding​

European Space Agency and OHB System


Project duration

01.09.2025 - 31.08.2027


Dr. Axel von Arnim

Your contact​

Dr. Axel von Arnim
+49 89 3603522 538
vonarnim@fortiss.org
 Priyadarshini Kannan

Your contact​

Priyadarshini Kannan
+49 89 3603522 275
kannan@fortiss.org

Project partner​


Screenshot_2025-10-17-12-14-40-42_4641ebc0df1485bf6b47ebd018b5ee76.jpg
 
  • Like
  • Love
  • Fire
Reactions: 17 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Meta + Arm deepen collaboration for data centers and wearables.

I see this as a net positive for BrainChip:
  • Arm is a tech partner for us, and Akida already plays nicely in the Arm ecosystem, including successful integrations with Cortex-M85.
  • Akida + TENNs are purpose-built for ultra-low-power, event-driven edge which is exactly the always-on, sub-watt niche that wearables need.
  • As Dr. Steve Harbour noted yesterday, neuromorphic AI is poised to show up near-term in wearables, data centers, and smartphones.




Screenshot 2025-10-17 at 3.19.37 pm.png



Arm and Meta Deepen AI Partnership for Data Center and Edge​

October 16, 2025, 3:15 am IDT
Arm Meta AI

The burgeoning era of artificial intelligence demands a foundational infrastructure capable of scaling from vast data centers to intimate personal devices. This critical requirement was at the heart of the recent discussion between Rene Haas, CEO of Arm, and Jim Cramer on CNBC’s ‘Mad Money,’ where Haas detailed a significant deepening of Arm’s strategic partnership with Meta. The conversation centered on Arm’s pivotal role in powering Meta’s ambitious AI initiatives, spanning both its cloud infrastructure and its cutting-edge consumer hardware.

Arm and Meta have collaborated for years, but this expanded alliance marks a substantial commitment to Arm’s architecture as the backbone for Meta’s AI future. Haas articulated that the partnership is “largely around data centers, but more broadly Jim, around software and the software stack associated with it.” This comprehensive approach signals Arm’s growing influence beyond its traditional mobile stronghold, cementing its position in the high-growth segments of cloud computing and advanced AI processing.

A core insight from the interview is Arm’s strategic expansion into the data center market, a domain historically dominated by other architectures. Haas noted that in data centers, “increasingly they’re moving to Arm… whether it’s general purpose compute or accelerated compute, things doing AI.” This migration is driven by the inherent power efficiency and performance characteristics of Arm’s designs, which are becoming increasingly critical as AI workloads demand ever more computational power without escalating energy consumption to unsustainable levels. For founders and VCs, this trend underscores the necessity of considering Arm-based solutions for scalable and cost-effective AI infrastructure, moving away from legacy architectures that may not meet future efficiency requirements.

Beyond the cloud, the partnership extends into Meta’s consumer hardware, particularly its Ray-Ban Meta smart glasses. Haas proudly showcased the device, stating it’s an “amazing product” that is “also Arm-based, and there’s a lot of AI in these glasses.” This highlights a crucial vector for AI deployment: the edge. Embedding sophisticated AI capabilities directly into wearable devices allows for real-time processing, enhanced privacy, and a more seamless user experience, reducing reliance on constant cloud connectivity. This move signifies Meta’s belief in wearables as a primary interface for AI, a sentiment strongly echoed by Cramer, who asserted the glasses are “the single best vehicle to get AI into your brain.”

The true “magic,” as Haas explained, lies in the unified software stack that Arm enables across these diverse environments. He emphasized that “you want the software stack to be similar between what’s running in the wearable and what’s running in the cloud. Only Arm can enable that, and that’s a big part of the announcement that was made today.” This architectural consistency is a significant advantage for Meta, allowing developers to build and deploy AI applications that seamlessly transition between the power of the data center and the immediacy of edge devices. For AI professionals, this consistency simplifies development, reduces complexity, and accelerates innovation across the entire computing continuum, from training large models in the cloud to inferencing on a user’s wrist.

The market implications of this deeper alliance are substantial. Cramer underscored the significance, stating, “I think it is major, I think it is a market moving.” Haas further bolstered this perspective by revealing Meta’s ambitious sales projections for the Ray-Ban smart glasses, anticipating “multiple millions of Ray-Bans to be sold by the end of 2026.” Such a projection, if realized, would not only establish a significant footprint for Arm in the wearable AI space but also solidify Meta’s vision of AI-powered consumer devices as a mainstream reality. This scale of adoption presents immense opportunities for the broader AI ecosystem, from component manufacturers to software developers building applications for these intelligent platforms.

The collaboration between Arm and Meta illustrates a powerful trend in the AI industry: the imperative for highly optimized, energy-efficient computing that can span the entire spectrum of AI applications. From powering the vast recommendation engines and ranking systems in Meta’s data centers to enabling intelligent, on-device experiences in its smart glasses, Arm’s architecture provides the foundational IP. This strategic alignment reflects a clear industry direction towards integrated, scalable solutions that can meet the escalating demands of an AI-first world.

 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 22 users

7für7

Top 20
Thanks bravo…. Unfortunately the share price gives us (the genuine shareholders) every week the middle finger…. Have a nice weekend all!
 
  • Like
  • Sad
  • Love
Reactions: 8 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Great to see Bob Beachler has a new job as Strategic Advisor at Athos Silicone.

Bob was BrainChip's Vice President of Marketing and Buiness from March 2017 to May 2019.

For those that don't know, Athos Silicon was spun out of Mercedes-Benz’s Silicon Valley chip team, with Mercedes transferring IP and taking a minority stake. Both sides say they’ll collaborate on chiplet-based, safety-first compute for autonomy, while keeping Athos independent so it can work with other OEMs. Recent trade press also frames it as a partnership/reference-design collaboration for next-gen autonomous computing.

Mercedes-Benz announced the spin-out/partnership with Athos Silicon on 26 September 2025.

Athos's website says its mSoC™ is fully modular, letting you add chiplets for AI, sensor fusion, or general-purpose compute without a redesign (see below). Pretty handy if you want to throw a few Akida's +TENN's into the mix.



Screenshot 2025-10-17 at 4.14.10 pm.png


Screenshot 2025-10-17 at 4.36.09 pm.png
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 26 users

Guzzi62

Regular
You probably should take on what he says.

They're not really down rampers anymore. Facts speak for themselves currently.

Communication to shareholders is genuinely abhorrent.
Nope, I am fine with them saying nothing while they work in the background.

NDA's are in place, I am sure, and I don't like a CEO pumping his company, it's unprofessional and seldom do the company any good long term.

If he can't secure any good IP deals before the next AGM we clearly have a problem and his 5 years strategy seems wrong.

But until then, as I said, I let them do their work, he still got time.
 
  • Like
  • Love
  • Thinking
Reactions: 8 users
Thanks bravo…. Unfortunately the share price gives us (the genuine shareholders) every week the middle finger…. Have a nice weekend all!
More like 2

1760679519487.gif
 
  • Like
  • Haha
Reactions: 3 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Great to see Bob Beachler has a new job as Strategic Advisor at Athos Silicone.

Bob was BrainChip's Vice President of Marketing and Buiness from March 2017 to May 2019.

For those that don't know, Athos Silicon was spun out of Mercedes-Benz’s Silicon Valley chip team, with Mercedes transferring IP and taking a minority stake. Both sides say they’ll collaborate on chiplet-based, safety-first compute for autonomy, while keeping Athos independent so it can work with other OEMs. Recent trade press also frames it as a partnership/reference-design collaboration for next-gen autonomous computing.

Mercedes-Benz announced the spin-out/partnership with Athos Silicon on 26 September 2025.

Athos's website says its mSoC™ is fully modular, letting you add chiplets for AI, sensor fusion, or general-purpose compute without a redesign (see below). Pretty handy if you want to throw a few Akida's +TENN's into the mix.



View attachment 92140


View attachment 92142


It's also very nice to see Gerrit Ecke taking an interest in Athos Silicone.

Gerrit previously worked as a researcher at Mercedes-Benz. He was actually the Function Owner on the Vision EQXX program, which used our Akida technology for the “Hey Mercedes” hot-word/voice control, citing 5–10× efficiency vs conventional voice control.

Two weeks ago, Gerrit left Mercedes to start a new role at Project Q.

In this LinkedIn exchange with Skylar Stein (Co-Founder Athos Silicon), Skylar congratulates Gerrit on his new role. I love how Gerrit reiterates that "energy-efficient AI and sensor fusion are key" and since Skylar liked Gerrit's comment, he obviously thinks so too.

Further down on the same LinkedIn Post, you can see that Anil Mankar also congratulated Gerrit on the new role. No doubt Anil and Gerrit worked closely together on the Vision EQXX.


Gerrit pm.png



Screenshot 2025-10-17 at 4.44.15 pm.png


Screenshot 2025-10-17 at 4.48.01 pm.png






Screenshot 2025-10-17 at 5.01.57 pm.png
 
  • Like
  • Fire
  • Wow
Reactions: 18 users

walderamaa

Emerged
 
  • Like
  • Love
  • Thinking
Reactions: 4 users

miaeffect

Oat latte lover
Thanks bravo…. Unfortunately the share price gives us (the genuine shareholders) every week the middle finger…. Have a nice weekend all!
ok... back to smoko

DAQX1760505851_1161224034.gif
 
  • Haha
Reactions: 6 users

BigDonger101

Founding Member
Nope, I am fine with them saying nothing while they work in the background.

NDA's are in place, I am sure, and I don't like a CEO pumping his company, it's unprofessional and seldom do the company any good long term.

If he can't secure any good IP deals before the next AGM we clearly have a problem and his 5 years strategy seems wrong.

But until then, as I said, I let them do their work, he still got time.
This is a horrid take in all honesty. Each to their own.

Company could be doing absolutely F**k all and you'd trust that something is going on. Hilarious.

You're running of pure hope and trust. Something you don't do in business or investing.
 
  • Like
  • Fire
  • Haha
Reactions: 7 users

CHIPS

Regular
If you don't like chat gpt look away now


View attachment 92116

For such applications, ChatGPT is very helpful. Thank you.
 
  • Like
Reactions: 2 users

Guzzi62

Regular
This is a horrid take in all honesty. Each to their own.

Company could be doing absolutely F**k all and you'd trust that something is going on. Hilarious.

You're running of pure hope and trust. Something you don't do in business or investing.
Off-course I trust the CEO and the company, if I didn't, I would sell my shares immediately.

So the companies you are invested in, you don't trust any of them?

Hilarious! Maybe put your spare coin in the bank or under the madras.

With all the presentations we seen over the year, you can see they have been quite busy, talking to other people/companies, interactions, so hinting they are doing fxxx all is ridiculous. These interactions normally happens before deals are made.
The BOD is also overseeing what's going on and will interact if they are not happy.

But you down rampers are only here to complain, I get that.
 
  • Like
  • Fire
  • Love
Reactions: 8 users
Top Bottom