BRN Discussion Ongoing

manny100

Top 20
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.
 
  • Like
Reactions: 4 users

Diogenese

Top 20
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?
 
  • Like
  • Fire
  • Love
Reactions: 9 users
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."
1752054726053.gif
 
  • Haha
  • Like
Reactions: 3 users

HopalongPetrovski

I'm Spartacus!
"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.
 

Attachments

  • NVU announce.pdf
    489.6 KB · Views: 50
  • Fire
  • Like
Reactions: 3 users

HopalongPetrovski

I'm Spartacus!
Their webinar with comparison info and claims of being the best edge device.
 

Attachments

  • webinar.pdf
    3 MB · Views: 42
  • Like
  • Fire
Reactions: 4 users
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 😂
 
Last edited:
  • Like
Reactions: 1 users

Diogenese

Top 20
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!
 
  • Haha
Reactions: 2 users

HopalongPetrovski

I'm Spartacus!
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.
 
  • Like
  • Fire
Reactions: 4 users

FJ-215

Regular
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. (y)(y) 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.......:mad:

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!!!
 
  • Like
  • Love
  • Fire
Reactions: 13 users

Diogenese

Top 20
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)
.

1752058074515.png




[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
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. .
 
Last edited:
  • Like
  • Fire
  • Haha
Reactions: 11 users

Tothemoon24

Top 20
IMG_1231.jpeg




Stephan Sokolov, Software Engineer at DeGirum, demonstrates the company’s latest edge AI and vision technologies and products in BrainChip’s booth at the 2025 Embedded Vision Summit. Specifically, Sokolov demonstrates the power of real-time AI inference at the edge, running DeGirum’s PySDK application directly on BrainChip hardware.

This demo showcases low-latency, high-efficiency performance as a script performs live inference on a video stream. Sokolov also highlights the DeGirum AI Hub—a cloud-based platform that allows developers to evaluate models and test deployments.

 
  • Like
  • Love
  • Fire
Reactions: 21 users

Diogenese

Top 20
View attachment 88304



Stephan Sokolov, Software Engineer at DeGirum, demonstrates the company’s latest edge AI and vision technologies and products in BrainChip’s booth at the 2025 Embedded Vision Summit. Specifically, Sokolov demonstrates the power of real-time AI inference at the edge, running DeGirum’s PySDK application directly on BrainChip hardware.

This demo showcases low-latency, high-efficiency performance as a script performs live inference on a video stream. Sokolov also highlights the DeGirum AI Hub—a cloud-based platform that allows developers to evaluate models and test deployments.





"We have integrated Akida into our PySDK and AI Hub." ... " running DeGirum’s PySDK application directly on BrainChip hardware"

So, on the PCIe board, the grey square below the asterisk is Akida

1752070538057.png


This is a nude Akida, without its flashy outer case. Bottom right is the characteristic chamfered corner. So is this from a new production run, or from the first engineering samples, or just an unboxed "commercial run" chip - or maybe 1500 (remembering that PCIe is not the mother board, so the CPU is on a different board)?

Here's a link to DeGirum's AI Hub:

https://www.prnewswire.com/news-rel...accelerate-edge-ai-development-302346154.html

SANTA CLARA, Calif., Jan. 13, 2025 /PRNewswire/ -- DeGirum®, a leader in edge AI software, announced the release of its AI Hub, an accessible evaluation platform designed to simplify AI prototyping and development at the edge. DeGirum's AI Hub enables developers to experiment with AI models for their applications. The platform supports a range of accelerators and application processors, including Hailo®, Intel®, MemryX®, BrainChip®, Rockchip®, and Google®.

"We are excited to launch our AI Hub which allows our customers to try many different industry leading AI processors and accelerators. 1000+ models are immediately available to try, with a wide range of algorithms and hardware solutions," said Bill Eichen, VP of Business Development at DeGirum.

DeGirum AI Hub
DeGirum's AI Hub enables rapid AI prototyping by providing access to hardware through an evaluation platform. The platform offers extensive model support, giving developers access to a diverse library of machine learning models to kickstart development. It features a model porting toolchain that converts training checkpoints into deployable models optimized for supported hardware targets. The AI Hub also hosts a model zoo, enabling edge devices to load and update models on demand, eliminating the need to bundle models within applications
.




https://degirum.us.auth0.com/login?state=hKFo2SAycm5ubGxCU25EdnRwWmVhc0ZmTUlQdlRqUzVNVDB3UKFupWxvZ2luo3RpZNkgckw0RllpSkExSXJVV3p5YllJdWNUNkttMmhlcWdFUFCjY2lk2SBBQWxoeUltNFpxWWVBbEhQdjlqSnp0b09yRkhWQTNLYg&client=AAlhyIm4ZqYeAlHPv9jJztoOrFHVA3Kb&protocol=oauth2&scope=openid profile email offline_access&redirect_uri=https://hub.degirum.com&audience=https://degirum.us.auth0.com/api/v2/&response_type=code&response_mode=query&nonce=WTNhdUFRekxuTWRkRmdCMThaQ25OazROa0g1M0J2X2ZOTUJYaTQwOWJzWQ==&code_challenge=ZR0xgT2SjDRFBkZyZajqQt95XXbu5let9B_I7JUZ7L8&code_challenge_method=S256&auth0Client=eyJuYW1lIjoiYXV0aDAtdnVlIiwidmVyc2lvbiI6IjIuMy4xIn0=

Supported Hardware​

Hailo DEEPX Intel MemryX Brainchip Google DeGirum Rockchip
 
  • Like
  • Fire
  • Love
Reactions: 43 users

Frangipani

Top 20
Laurent Hili on the ESA-supported BrainChip -Frontgrade Gaisler partnership:


25A66BBB-7E7A-49CC-A7F4-C09B80CFA25D.jpeg
 
  • Like
  • Love
  • Fire
Reactions: 42 users

Frangipani

Top 20
Akida gets a favourable mention alongside Loihi in a recent paper (“From Tiny Machine Learning to Tiny Deep Learning: A Survey”) by Texas State University researchers:

“[Neuromorphic] architectures promise efficient always-on inference on MCU-scale devices ideal for continuous monitoring applications-with hardware platforms like BrainChip’s Akida and Intel’s Loihi leading the way.”



C7782EC6-3DA5-4826-9A96-4B1A48BCA1FF.jpeg

(…)

A978198B-54CF-4D60-844D-3DD3D3F84157.jpeg
5D88DC54-1798-4BE7-A41D-594DF7D7EEB3.jpeg
 
  • Like
  • Fire
  • Love
Reactions: 28 users

manny100

Top 20
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 key to using AI Chat boxes eg Gemini, co pilot etc is understanding that they have great long term memory but very poor short term memory.
It is hugely expensive to build short term memory in LLMs. So it's limited.
If you extend your conversation it will forget important details from early on in the conversation. Hence errors.
Questions need to be precise, explicit and provide context.
If the conversation goes on details from earlier may need to be resupplied in case it's forgotten.
If you want more detail on this ask your chat box and it will fill you in on the best way to use it.
Ask your chatbox. Are you always reliable with the infornation you supply.
It will tell you as it is.
It will even tell you when to be cautious etc.
Ask it. Are you smart.
 
  • Like
Reactions: 4 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Here's a new Analog Devices job ad (posted 7 days ago) for an AI Compute Architect being hired to lead architectural integration of µAI (micro AI) compute blocks, analog AI, in-memory computing and spiking neural networks / neuromorphic computing.

A pretty clear signal IMO that neuromorphic approaches are on ADI’s SoC roadmap.

As you can see, they’re looking for someone to help with early RTL and analog prototyping, interface definition and IP integration, which shows they’re not just researching but planning to potentially integrate third-party IPs (like BrainChip’s Akida or some other similar neuromorphic technology).

The job responsibilities include:

“Support early RTL and analog prototyping of both internal and third-party IP blocks.”

That's a pretty strong indicator they’re at least open to collaborating with companies like BrainChip. 🤞

Obviously, it's by no means confirmation of any sort of partnership, but it’s certainly a door that seems to be open.

No need to wait on the welcome mat, Sean. Cruise on through like you mean business!




Screenshot 2025-07-10 at 5.17.59 am.png




Screenshot 2025-07-10 at 5.18.30 am.png


Screenshot 2025-07-10 at 5.18.44 am.png



 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 18 users

Esq.111

Fascinatingly Intuitive.
Morning Chippers,


Nothing on us , .....yet .

Meta buying a little stake .... Smart Glasses.

Shares of Ray-Ban maker EssilorLuxottica jump on reported Meta stake https://share.google/3o9s29xk9X9uwZDJV

Regards,
Esq.
 
  • Like
  • Fire
Reactions: 18 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
  • Like
  • Wow
  • Fire
Reactions: 8 users

7für7

Top 20
  • Like
  • Fire
Reactions: 8 users
Top Bottom