BRN Discussion Ongoing

[HopalongPetrovski]

Anyone else concerned about NVU?
They seem to be cutting our lunch somewhat, with much more aggressive marketing and moving quickly.
They have a webinar starting at 3pm if interested.

 

[Diogenese]

Anyone else concerned about NVU?
They seem to be cutting our lunch somewhat, with much more aggressive marketing and moving quickly.
They have a webinar starting at 3pm if interested.

View attachment 88285

The board and management are overweight on financial/management expertise. Mohamad Sarby/Aly, founder of EMASS, is a rare tech exception.

Nanoveu bought EMASS which is RISC-V

https://nanoveu.com/our-offerings/emass/

This is a recent webinar:

https://wcsecure.weblink.com.au/pdf/NVU/02966008.pdf

DL = deep learning.

Apart from this diagram, tech details are hard to find.

They list Weebit as ReRAM partner.

This is a Nanyang Tech Uni patent application with Sarby Aly as inventor, ie, the Emass patent:

WO2023140778A1 CONVOLUTION ENGINE AND METHODS OF OPERATING AND FORMING THEREOF 20220118

Inventors: ZHAO BIN [SG]; KONG ANMIN [SG]; CHUI KING JIEN [SG]; DO ANH TUAN [SG]; CHAI TSHUN CHUAN KEVIN [SG]; ALY MOHAMED MOSTAFA SABRY [SG]​

a convolution engine configured to perform neural network computations.
The convolution engine including: a plurality of convolution processing blocks,
each convolution processing block being configured to perform convolution based on a 2D array of first feature map data stored therein to produce a set of first convolution outputs,
each set of first convolution outputs including a plurality of channels; and
a plurality of weight memory blocks communicatively coupled to the convolution processing blocks.
Each weight memory block is configured to store and supply weight parameters to the corresponding convolution processing blocks to perform convolution.
Each convolution processing block further comprises a plurality of processing element blocks and each processing element block can further comprise a plurality of sub-blocks and corresponding weight memory sub-blocks.

Emass/Nanoveu is not SNN.

 

[TECH]

Shareholders,
Do you believe that our technology has advanced over the last 3 years or not ?
I think yes, you think what ?
Shareholders,
Do you think our website has improved, as in, overall information sharing ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio lied during the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio's comments at the AGM were addressed by fellow Board members after the conclusion of the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Sean, who is 3 years 9 months into his tenure will deliver before his 5 year (agreement) is due to expire ?
I think yes, you think what ?
Shareholders,
Do you believe that the Board will suggest that we re-domicle to the US in early 2026 ?
I think not, you think what ?
Shareholders,
Are you happy with how our share price is being manipulated by an automated robotic algorithm, to the point of artificial control ?
I think not, you think what ?
Shareholders,
Do you believe that Tony is the right man to be leading our technology team ?
I think yes, you think what ?

Just some honest, genuine questions that may confirm why you are still invested in our company.

The Akida family, we are growing, please don't loose sight of that FACT !

Tech x

 

[HopalongPetrovski]

The board and management are overweight on financial/management expertise. Mohamad Sarby/Aly, founder of EMASS, is a rare tech exception.

Nanoveu bought EMASS which is RISC-V

https://nanoveu.com/our-offerings/emass/

This is a recent webinar:

https://wcsecure.weblink.com.au/pdf/NVU/02966008.pdf

View attachment 88287

DL = deep learning.

Apart from this diagram, tech details are hard to find.

They list Weebit as ReRAM partner.

This is a Nanyang Tech Uni patent application with Sarby Aly as inventor, ie, the Emass patent:

WO2023140778A1 CONVOLUTION ENGINE AND METHODS OF OPERATING AND FORMING THEREOF 20220118

Inventors: ZHAO BIN [SG]; KONG ANMIN [SG]; CHUI KING JIEN [SG]; DO ANH TUAN [SG]; CHAI TSHUN CHUAN KEVIN [SG]; ALY MOHAMED MOSTAFA SABRY [SG]​

View attachment 88288 View attachment 88289

View attachment 88290


a convolution engine configured to perform neural network computations.
The convolution engine including: a plurality of convolution processing blocks,
each convolution processing block being configured to perform convolution based on a 2D array of first feature map data stored therein to produce a set of first convolution outputs,
each set of first convolution outputs including a plurality of channels; and
a plurality of weight memory blocks communicatively coupled to the convolution processing blocks.
Each weight memory block is configured to store and supply weight parameters to the corresponding convolution processing blocks to perform convolution.
Each convolution processing block further comprises a plurality of processing element blocks and each processing element block can further comprise a plurality of sub-blocks and corresponding weight memory sub-blocks.

Emass/Nanoveu is not SNN.

Thanks Dio.
I bow to your technical knowledge in this regard that they are apparently dressing mutton up as lamb.

However, I guess my concern is that they are targeting our Edge market and all the similar and popular applications, just like us, spruiking their product using very similar terminology and claiming to be the best and most advanced product available.

They are also seemingly moving and advancing incredibly quickly in contrast to our apparently glacial progress and being presented in a very winning and no nonsense manner by a couple of veteran yankee salesfolk.

I was hoping for a chance to quiz them on a comparison to BrainChip's Akida but they didn't take any questions.

You can view their Webinar presentation slideshow which they have released as a price sensitive announcement and where they provide further comparative information.

They come across as a more competent, less bloated version of us, but, in a hurry, eager to impress and knowing what they are doing.
To be transparent, I have not invested in them, yet.
Come on BrainChip.
FFS, don't just lie there. Do Something.

 

[Pom down under]

Shareholders,
Do you believe that our technology has advanced over the last 3 years or not ?
I think yes, you think what ?
Shareholders,
Do you think our website has improved, as in, overall information sharing ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio lied during the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio's comments at the AGM were addressed by fellow Board members after the conclusion of the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Sean, who is 3 years 9 months into his tenure will deliver before his 5 year (agreement) is due to expire ?
I think yes, you think what ?
Shareholders,
Do you believe that the Board will suggest that we re-domicle to the US in early 2026 ?
I think not, you think what ?
Shareholders,
Are you happy with how our share price is being manipulated by an automated robotic algorithm, to the point of artificial control ?
I think not, you think what ?
Shareholders,
Do you believe that Tony is the right man to be leading our technology team ?
I think yes, you think what ?

Just some honest, genuine questions that may confirm why you are still invested in our company.

The Akida family, we are growing, please don't loose sight of that FACT !

Tech x

 

[manny100]

I asked AI whether the Brainchip and HaiLa partnership would work well with the Ericcson collaboration.
To save reading all the detail i have just reproduced the Conclusion.
Synergies Between BrainChip–HaiLa and BrainChip–Ericsson Collaborations:

Conclusion​

The BrainChip–HaiLa partnership dovetails neatly with BrainChip’s work with Ericsson. By combining event-driven AI, passive backscatter connectivity, and solar-harvested 6G links, all three players can deliver the industry’s first truly zero-energy, multi-protocol IoT nodes.


If they all did get together AI says:

Overall Market Shifts​

• Supply-chain realignment toward mixed-signal neuromorphic-backscatter SoCs.
• Emergence of “batteryless IoT” as a mainstream category—attracting new entrants and VC dollars.
• Legacy comms players will either partner with neuromorphic/backscatter pioneers or risk commoditization to white-label clones.

By forcing a convergence of neuromorphic AI, passive backscatter and solar-harvest radios, the BrainChip–HaiLa–Ericsson trifecta sets a new benchmark for zero-energy IoT. Competitors must evolve or cede ground in both standardization bodies and field deployments.

What angle would you like to explore next—competitors’ counter-strategies, standard-setting roadmaps, or emerging use-case verticals?

 

[manny100]

Shareholders,
Do you believe that our technology has advanced over the last 3 years or not ?
I think yes, you think what ?
Shareholders,
Do you think our website has improved, as in, overall information sharing ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio lied during the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio's comments at the AGM were addressed by fellow Board members after the conclusion of the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Sean, who is 3 years 9 months into his tenure will deliver before his 5 year (agreement) is due to expire ?
I think yes, you think what ?
Shareholders,
Do you believe that the Board will suggest that we re-domicle to the US in early 2026 ?
I think not, you think what ?
Shareholders,
Are you happy with how our share price is being manipulated by an automated robotic algorithm, to the point of artificial control ?
I think not, you think what ?
Shareholders,
Do you believe that Tony is the right man to be leading our technology team ?
I think yes, you think what ?

Just some honest, genuine questions that may confirm why you are still invested in our company.

The Akida family, we are growing, please don't loose sight of that FACT !

Tech x

Shareholders,
Do you believe that our technology has advanced over the last 3 years or not ?
I think yes, you think what ?
Shareholders,
Do you think our website has improved, as in, overall information sharing ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio lied during the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio's comments at the AGM were addressed by fellow Board members after the conclusion of the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Sean, who is 3 years 9 months into his tenure will deliver before his 5 year (agreement) is due to expire ?
I think yes, you think what ?
Shareholders,
Do you believe that the Board will suggest that we re-domicle to the US in early 2026 ?
I think not, you think what ?
Shareholders,
Are you happy with how our share price is being manipulated by an automated robotic algorithm, to the point of artificial control ?
I think not, you think what ?
Shareholders,
Do you believe that Tony is the right man to be leading our technology team ?
I think yes, you think what ?

Just some honest, genuine questions that may confirm why you are still invested in our company.

The Akida family, we are growing, please don't loose sight of that FACT !

Tech x

Oddly enough if a BOD member said today we are not going to the US it would be a true statement. We are actually going nowhere until holders vote for it with a YES..
If the question was 'is Brainchip investigating a move to the US' and the BOD member said no - that would be a lie or a very unfortunate brain fade at the least.
It all depends on the wording of the question. I cannot recall the actual question.
From my point of view the real problem was that Tony V allowed the Questioner to rile him up. He let himself down.
It is likely that at BOD level other possible destinations were discussed if only briefly. We will never know.
It's no secret i am patiently bullish on BRN.

 

[Baron Von Ricta]

Manny, I don't trust AI generated responses, and don't use any AI search engines.
Have you, or would you ask your AI, something negative along the lines of, "I don't think Brainchip will be a successful business, what do you think?"
Just interested in what then reply would be.

B

 

[The Pope]

Manny, I don't trust AI generated responses, and don't use any AI search engines.
Have you, or would you ask your AI, something negative along the lines of, "I don't think Brainchip will be a successful business, what do you think?"
Just interested in what then reply would be.

B

Your wish is done and here is one AI response to your question . Lmfao

You're skeptical about Brainchip's prospects. That's a fair opinion, especially given the competitive landscape in the tech industry. Brainchip's focus on neuromorphic AI might give them an edge, but it's hard to predict success without knowing more about their product roadmap and market traction. What's specifically got you doubting their potential?

 

[manny100]

Manny, I don't trust AI generated responses, and don't use any AI search engines.
Have you, or would you ask your AI, something negative along the lines of, "I don't think Brainchip will be a successful business, what do you think?"
Just interested in what then reply would be.

B

I often preface questions by asking for unbiased answer. Its not always correct. Sometimes misses things.
Only gives replies valid until the last time it was updated/trained.
I put your question in and the conclusion was.
"My Take BrainChip sits at an intriguing crossroads. Its tech leads in power efficiency and on-device learning, but it must leap from proofs-of-concept into high-volume, revenue-generating partnerships. I’d assign a moderate probability of success—around 40–50%—contingent on landing a marquee, large-scale customer in the next 12–18 months.

What concerns you most about their outlook—market fit, finance, or competitive threats? Let’s dig deeper into that."

 

[manny100]

Manny, I don't trust AI generated responses, and don't use any AI search engines.
Have you, or would you ask your AI, something negative along the lines of, "I don't think Brainchip will be a successful business, what do you think?"
Just interested in what then reply would be.

B

Full text of reply:
I don't think Brainchip will be a successful business, what do you think

Assessing BrainChip’s Prospects​

BrainChip has carved out a niche in neuromorphic Edge AI with its Akida processor, but whether it becomes a long-term commercial success hinges on several interlocking factors:

1. Technological Differentiation​

• Strengths:
  • Event-driven spiking architecture offers sub-milliwatt inference and on-chip continual learning.
  • Strong IP portfolio—over 170 patents—protects its neuromorphic approach.
• Challenges:
  • Competing accelerators (Qualcomm, NVIDIA’s Jetson, Google’s Edge TPU) dominate edge-AI mindshare.
  • Neuromorphic benchmarks are still emerging; customers often default to more familiar CNN accelerators.

2. Market Adoption & Partnerships​

• Wins:
  • Collaborations with Ericsson (6G zero-energy IoT), NXP, and Renesas lend credibility.
  • Design-wins in aerospace, defense and industrial IoT verticals demonstrate real-world traction.
• Risks:
  • Volume rollouts remain modest; translating prototypes into high-margin production units is the critical next step.
  • Larger chip vendors could sidestep BrainChip by integrating their own low-power AI blocks.

3. Financial & Execution Risks​

• Positives:
  • Raised capital in recent funding rounds, extending runway for product development and sales.
• Concerns:
  • Ongoing R&D burn outpaces revenue—if new customer wins stall, further dilution or fundraising may be required.
  • Go-to-market hinges on small sales teams converting highly technical demos into purchase orders.

4. Competitive and Ecosystem Factors​

• Ecosystem Power:
  • Neuromorphic remains a boutique approach—if standards bodies or cloud-to-edge toolchains ignore spiking frameworks, integration friction grows.
• Opportunity:
  • Edge AI’s hunger for lower power and privacy may open greenfield segments (batteryless sensors, micro-drones) where Akida shines.

My Take BrainChip sits at an intriguing crossroads. Its tech leads in power efficiency and on-device learning, but it must leap from proofs-of-concept into high-volume, revenue-generating partnerships. I’d assign a moderate probability of success—around 40–50%—contingent on landing a marquee, large-scale customer in the next 12–18 months.
What concerns you most about their outlook—market fit, finance, or competitive threats? Let’s dig deeper into that.

 

[Diogenese]

Thanks Dio.
I bow to your technical knowledge in this regard that they are apparently dressing mutton up as lamb.

However, I guess my concern is that they are targeting our Edge market and all the similar and popular applications, just like us, spruiking their product using very similar terminology and claiming to be the best and most advanced product available.

They are also seemingly moving and advancing incredibly quickly in contrast to our apparently glacial progress and being presented in a very winning and no nonsense manner by a couple of veteran yankee salesfolk.

I was hoping for a chance to quiz them on a comparison to BrainChip's Akida but they didn't take any questions.

You can view their Webinar presentation slideshow which they have released as a price sensitive announcement and where they provide further comparative information.

They come across as a more competent, less bloated version of us, but, in a hurry, eager to impress and knowing what they are doing.
To be transparent, I have not invested in them, yet.
Come on BrainChip.
FFS, don't just lie there. Do Something.

"All that glitters ..."

Nanoveu's original business is in nanocoatings and 3D microlens screens.

Nanoveu seems to be run by non-technical people, with the exception of Sarby Aly, so I wonder how they did their DD in assessing Emass. I mean, what's a neuromorphic computer anyway?

 

[Pom down under]

I often preface questions by asking for unbiased answer. Its not always correct. Sometimes misses things.
Only gives replies valid until the last time it was updated/trained.
I put your question in and the conclusion was.
"My Take BrainChip sits at an intriguing crossroads. Its tech leads in power efficiency and on-device learning, but it must leap from proofs-of-concept into high-volume, revenue-generating partnerships. I’d assign a moderate probability of success—around 40–50%—contingent on landing a marquee, large-scale customer in the next 12–18 months.

What concerns you most about their outlook—market fit, finance, or competitive threats? Let’s dig deeper into that."

 

[HopalongPetrovski]

"All that glitters ..."

Nanoveu's original business is in nanocoatings and 3D microlens screens.

Nanoveu seems to be run by non-technical people, with the exception of Sarby Aly, so I wonder how they did their DD in assessing Emass. I mean, what's a neuromorphic computer anyway?

Hi again Dio.
I can't of course answer for them, but reiterate that even if they are shonk's they are presenting well, getting investor attention and stealing our thunder in the Edge space.
Here follows their ASX price sensitive announcements from today.

 

[HopalongPetrovski]

Their webinar with comparison info and claims of being the best edge device.

 

[Pom down under]

Hi again Dio.
I can't of course answer for them, but reiterate that even if they are shonk's they are presenting well and getting investor attention.
Here follows their ASX price sensitive announcements from today.

Fingers crossed the shorters will leave us alone soon with a steady increase in income and it will NVU times next

 

[Diogenese]

Hi again Dio.
I can't of course answer for them, but reiterate that even if they are shonk's they are presenting well, getting investor attention and stealing our thunder in the Edge space.
Here follows their ASX price sensitive announcements from today.

Shonks!!!? - Venture capitalists and MBAs - heaven forefend!

 

[HopalongPetrovski]

Fingers crossed the shorters will leave us alone soon with a steady increase in income and it will NVU times next

Frankly I'd much rather be talking about BrainChip.
After all, it's where I am invested, but think these guy's are showing the potential of serious commercial competition, or, at the least, are muddying the waters, none of which is immediately helpful for us.
Dio's expertise allows him to dismiss them, but most of us are vulnerable to a pretty story, particularly when its spun by experienced and well connected, commercially savvy (if non -technical) fang flashers.
We have our own, but beyond an occasional AGM, they seem content to rake in the RSU's and enjoy the lifestyles of a BOD.

 

[FJ-215]

Shareholders,
Do you believe that our technology has advanced over the last 3 years or not ?
I think yes, you think what ?
Shareholders,
Do you think our website has improved, as in, overall information sharing ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio lied during the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Antonio's comments at the AGM were addressed by fellow Board members after the conclusion of the AGM ?
I think yes, you think what ?
Shareholders,
Do you believe that Sean, who is 3 years 9 months into his tenure will deliver before his 5 year (agreement) is due to expire ?
I think yes, you think what ?
Shareholders,
Do you believe that the Board will suggest that we re-domicle to the US in early 2026 ?
I think not, you think what ?
Shareholders,
Are you happy with how our share price is being manipulated by an automated robotic algorithm, to the point of artificial control ?
I think not, you think what ?
Shareholders,
Do you believe that Tony is the right man to be leading our technology team ?
I think yes, you think what ?

Just some honest, genuine questions that may confirm why you are still invested in our company.

The Akida family, we are growing, please don't loose sight of that FACT !

Tech x

G'day Tech,
Glad to have you back. Hopefully on a more permanent basis!!


1)Shareholders,
Do you believe that our technology has advanced over the last 3 years or not ?

A) Year on year, bit by bit. Definately.


Shareholders,
Do you think our website has improved, as in, overall information sharing ?

A) Maybe, still parts I don't like but I'm looking as a shareholder, not a potential client.


Shareholders,
Do you believe that Antonio lied during the AGM ?

A) He either lied or doesn't know what he is signing off on at board meetings. Just needs to go!!!

Shareholders,
Do you believe that Antonio's comments at the AGM were addressed by fellow Board members after the conclusion of the AGM ?

A) Silence of the lambs.......

Shareholders,
Do you believe that Sean, who is 3 years 9 months into his tenure will deliver before his 5 year (agreement) is due to expire ?

A) Can't comment as his 5 year plan has not been made public.

Shareholders,
Do you believe that the Board will suggest that we re-domicle to the US in early 2026 ?

A) Definitely!! Hard to see any of them keeping their jobs if the next AGM is in Australia.

Shareholders,
Are you happy with how our share price is being manipulated by an automated robotic algorithm, to the point of artificial control ?

A) pass and Antonio is doing just fine on his own.

Shareholders,
Do you believe that Tony is the right man to be leading our technology team ?
I think yes, you think what ?

A) A very big brain. Glad he is in our corner. And seems to understand the need to push our name out to the market.
Can he stand in as Chair while we search for a replacement for Tony V (for vendetta against S/holders)???


Anyway........

Good to have you back Tech.....

Roll on Royal Portrush!!!

 

[Diogenese]

Hi again Dio.
I can't of course answer for them, but reiterate that even if they are shonk's they are presenting well, getting investor attention and stealing our thunder in the Edge space.
Here follows their ASX price sensitive announcements from today.

Ok. Here's a later NVU/Emass/NanYang Uni patent app:
US2024296670A1 ACCELERATOR CIRCUITRY FOR ACCELERATION OF NON-MAXIMUM SUPPRESSION FOR OBJECT DETECTION 20230301 ALY MOHAMED MOSTAFA SABRY 20230301

[0003] Deep Neural Networks (DNNs), commonly referred to as deep learning machine learning models, are increasingly recognized as the de facto standard in modern artificial intelligence (AI) applications.

[0004] State-of-the-art Convolutional Neural Network (CNN) architectures require fast Non-Maximum Suppression (NMS) algorithms as NMS is mandatory and has become the major performance bottleneck in convolutional object detection pipelines.

[0005] … the de-facto standard for NMS, namely GreedyNMS, is composed of a sorting operation over confidence scores for tens of thousands of bounding boxes, followed by nested for loops to greedily select the boxes with high scores and remove the boxes significantly overlapped with the selected ones. Unlike convolutions which are inherently parallel, GreedyNMS cannot be parallelized due to the requirement of “nested for loops”. Thus, the GreedyNMS algorithm would gradually dominate the execution time of convolutional object detectors, as convolutions run faster thanks to the increasing parallelism on dedicated hardware (e.g., from P100 to V100 GPU).

[0050] FIG. 1 illustrates a block diagram representative of the accelerator circuitry for facilitating acceleration of object detection operations of an image in accordance with embodiments of the present disclosure. Accelerator circuitry 100 comprises relationship recovery module (RRM) 102 , kernel index compute units (KICUs) 104 and 106 , score map memories (SMMs) 108 and 110 , and optionally, arbitration module 112 . RRM 102 comprises a set of processing elements that are configured to perform a plurality of computations in parallel, KICUs 104 and 106 each comprise a set of processing elements that are configured to perform a plurality of computations, and SMMs 108 and 110 may comprise data buffers configured in a ping-pong arrangement.

So it seems that GreedyNMS, which captures thousands of bounding boxes per frame, wasn't able to be run in parallel and was becoming a bottleneck.

0006] As mentioned above, while convolution operations have experienced significant performance enhancements owing to advancements in both hardware scalable architectures (such as Graphics Processing Units (GPUs) and DNN accelerators) and algorithmic optimizations (including depth-wise and pruning techniques), the commonly utilized GreedyNMS algorithm has not seen commensurate improvements and, as a result, has become a dominant factor in inference time.


I won't bore you with the details ...

PS: I had wondered how they dealt with overlapping bounding boxes so para [0005] is enlightening for me.
PPS: Previously I had let the term "Greedy" pass through to the keeper, but, in the end, you've got to face your demons.
PPPS: This is probably the accelerator shown in the blue diagram at

• #102,362

above.
PPPPS: I wonder if the MRAM has been replaced by Weebit ReRAM?
PPPPPS: Bloody looks like it: https://www.listcorp.com/asx/nvu/nanoveu-limited/news/emass-to-embed-reram-technology-3116795.html :
18 November 2024ASX: NVUEMASS To Embed ReRAM Technology For Improved Scalable, Energy-Efficient MemoryHighlights:●Embedded AI System Pty Ltd (EMASS) has commenced the transition from Spin Transfer Torque Magnetic RAM (STT-MRAM) to Resistive Random Access Memory (ReRAM), incorporating next-generation memory technology to further its mission to deliver high-performance, energy-efficient AI applications. ...
Well maybe not - the article goes on to attribute the improved ReRAM to Sarby Aly, but, on the other hand, Weebit is listed as a partner, so maybe theirs is bigger than Sarby's. .