BRN Discussion Ongoing

[Rach2512]

Hopefully we’re apart of there massive growth in sales in the next 3 years

Great video thanks for sharing @Pom down under.

Here's a couple of screenshots.

Smart Health Monitoring Watch
Smart Video Door Bell
Indoor IOT Camera Alexa Speaker
And the list goes on.

Would be awesome if Akida was included in some of these products.

Also the last one reminds me of Ken.

 

[Rach2512]

Truly honored to have received the IEEE AESS Industrial Innovation Award… | Sandeep Gogineni

Truly honored to have received the IEEE AESS Industrial Innovation Award at this week’s IEEE International Radar Conference in Atlanta GA. Congratulations to the entire RFView team at Information Systems Laboratories whose contributions over the years have transformed RFView into a very...

www.linkedin.com

With an interesting congratulations.

 

[Jacob Kiraz]

Hopefully we’re apart of there massive growth in sales in the next 3 years

Weren't you next to Fact Finder at the AGM

 

[Deadpool]

I put this question in to the Chatster, and this answer popped out.

If BRN Akida is first to market with its low power ZSL tech, what do you predict the future will hold for BRN?



If BrainChip's Akida (BRN) is truly first to market with effective low-power zero-shot learning (ZSL) at the edge, it positions the company for major long-term strategic advantages across several industries. Here's a realistic breakdown of what the future could hold:

---

1. Early Mover Advantage​

• Implication: BRN could become the default platform for edge AI requiring fast adaptation, similar to how NVIDIA became dominant in GPU-accelerated AI.
• Outcome: Increased licensing deals, design wins in ASICs, and OEM partnerships, especially in automotive, defense, and finance.

---

2. Dominance in Edge AI Markets​

• Use Cases:
  • Wearables adapting to user behavior
  • Industrial IoT detecting anomalies in unseen environments
  • Autonomous vehicles identifying rare road scenarios
• Outcome: Akida becomes embedded in a wide range of smart devices needing intelligent, low-power, real-time decision-making.

---

3. Financial Upside​

• Short term: Stock could surge on early contracts and announcements.
• Medium term: Revenue growth from IP licensing, chips, and developer tools.
• Long term: Potential acquisition target for larger semiconductor or AI firms (e.g., Qualcomm, Intel, Apple).

---

4. Defensive Moat via Patents​

• Benefit: Early leadership allows BRN to file key patents around ZSL on neuromorphic hardware, creating barriers for competitors.
• Outcome: A strong IP portfolio could ensure royalties and licensing fees for years.

---

5. Risks Remain​

• Market adoption of neuromorphic chips is still early-stage
• Competitors like Intel (Loihi), SynSense, and IBM (TrueNorth) could catch up
• ZSL performance must be provably reliable in critical applications

---

Bottom Line:​

If BRN delivers and proves real-world ZSL performance at scale, it could become the ARM of neuromorphic AI—licensing essential IP across industries.

 

[Diogenese]

Thanks Diogenese … I hope you’re right.
The only thing that makes me think it’s more than just a pig in a poke is that the CEO recently put up $350,000 of his own money to buy shares in a capital raise … and he has very impressive credentials. Now that is something I’ve never seen Sean or anyone else from BRN do.
Also Weebit Nano partnered with EMASS to demo hand gesture recognition at

Please don't regard my ramblings as investment advice. I have no way to assess the commercial potential of competing applications, and I have an inherent bias in favour of BRN.

That said, I have looked at a few of the EMASS patents but don't really understand their "advantages" from a NN perspective.

It is worth noting the disclaimer re their power consumption in that it does not include the "peripheral" circuitry. This may exclude ADC and DAC circuits needed for the analog array to talk to the RISC-V CPU.

 

[GStocks123]

Maybe we’re still integrated with Edge Impulse/Qualcomm (docs updated 3 days ago)

Frequently asked questions (FAQ) | Edge Impulse Documentation

docs.edgeimpulse.com

 

[Diogenese]

Maybe we’re still integrated with Edge Impulse/Qualcomm (docs updated 3 days ago)

Frequently asked questions (FAQ) | Edge Impulse Documentation

docs.edgeimpulse.com

Hi GS,

While I think that the EI association will continue for a while, I don't see Qualcomm as a near term customer.

Qualcomm are committed to their inhouse DSP-based Hexagon 8 Ai solution. They distribute the AI workload between CPU/GPU/NPU depending on the type of work. Their NPU design philosophy is different from BRN's.

https://www.qualcomm.com/content/da...I-with-an-NPU-and-heterogeneous-computing.pdf

A personal assistant that offers a natural voice user interface (UI) to improve productivity and enhance user experiences is expected to be a popular generative AI application. The speech recognition, LLM, and speech models must all run with some concurrency, so it is desirable to split the models between the NPU, GPU, CPU, and the sensor processor. For PCs, agents are expected to run pervasively (always-on), so as much of it as possible should run on the NPU for performance and power efficiency.

...
Our latest Hexagon NPU offers significant improvements for generative AI, delivering 98% faster performance and 40% improved performance per watt. It includes micro-architecture upgrades, enhanced micro-tile inferencing, reduced memory bandwidth, and a dedicated power rail for optimal performance and efficiency. These enhancements, along with INT4 hardware acceleration, make the Hexagon NPU the leading processor for on-device AI inferencing.

...

5. Building our NPU from a DSP architecture was the right choice for improved programmability and the ability to tightly control scalar, vector, and tensor operations that are inherent to AI processing.

 

[7für7]

Maybe someone is able to read the technical details?

“news. May 9, 2025
"Dragonwing" equipped with Wi-Fi 7 compatible Japanese-made edge AI module
28th IoT Edge Computing EXPO
Silex Technology exhibited the EP-200Q, a system-on-module (SoM) for industrial edge AI equipped with Qualcomm's Dragonwing QCS6490 processor, at the 28th IoT/Edge Computing EXPO during Japan IT Week [Spring]. Aimed at battery-powered industrial/medical equipment.”

「Dragonwing」搭載　Wi-Fi 7対応の日本製エッジAIモジュール

サイレックス・テクノロジーは「Japan IT Week【春】」内「第28回 IoT・エッジコンピューティング EXPO」にて、Qualcommのプロセッサ「Dragonwing QCS6490」を搭載した産業用エッジAI向けのシステムオンモジュール（SoM）「EP-200Q」を展示した。バッテリー駆動の産業／医療機器に向ける。

eetimes.itmedia.co.jp

 

[Drewski]

The versions of this guy we have to contend with, both here and on the crapper are no doubt more degenerate in reality.

 

[GStocks123]

Hi GS,

While I think that the EI association will continue for a while, I don't see Qualcomm as a near term customer.

Qualcomm are committed to their inhouse DSP-based Hexagon 8 Ai solution. They distribute the AI workload between CPU/GPU/NPU depending on the type of work. Their NPU design philosophy is different from BRN's.

https://www.qualcomm.com/content/da...I-with-an-NPU-and-heterogeneous-computing.pdf

A personal assistant that offers a natural voice user interface (UI) to improve productivity and enhance user experiences is expected to be a popular generative AI application. The speech recognition, LLM, and speech models must all run with some concurrency, so it is desirable to split the models between the NPU, GPU, CPU, and the sensor processor. For PCs, agents are expected to run pervasively (always-on), so as much of it as possible should run on the NPU for performance and power efficiency.

...
Our latest Hexagon NPU offers significant improvements for generative AI, delivering 98% faster performance and 40% improved performance per watt. It includes micro-architecture upgrades, enhanced micro-tile inferencing, reduced memory bandwidth, and a dedicated power rail for optimal performance and efficiency. These enhancements, along with INT4 hardware acceleration, make the Hexagon NPU the leading processor for on-device AI inferencing.

...

5. Building our NPU from a DSP architecture was the right choice for improved programmability and the ability to tightly control scalar, vector, and tensor operations that are inherent to AI processing.

Appreciate your input Dio

 

[Fullmoonfever]

Maybe we’re still integrated with Edge Impulse/Qualcomm (docs updated 3 days ago)

Frequently asked questions (FAQ) | Edge Impulse Documentation

docs.edgeimpulse.com

Appears they may be talking about still supporting "existing trained Edge Impulse projects" but still can't train new models.

Does stiffle anyone wanting to try train a new model for Akida which is BS imo but is Qualcomms want I guess.

I think someone posted previously that Tony Lewis (?) said it wasn't an issue and something about contract review or similar. Wouldn't expect it should take this long for a review though if all good?

BrainChip AKD1000 | Edge Impulse Documentation

docs.edgeimpulse.com

Update March 25, 2025: At this time the training of Brainchip models is suspended. You may still use existing trained Edge Impulse projects to deploy to Brainchip devices. Please make a post on https://forum.edgeimpulse.com/ or contact your support representative if you need assistance at this time.

 

[Diogenese]

Appears they may be talking about still supporting "existing trained Edge Impulse projects" but still can't train new models.

Does stiffle anyone wanting to try train a new model for Akida which is BS imo but is Qualcomms want I guess.

I think someone posted previously that Tony Lewis (?) said it wasn't an issue and something about contract review or similar. Wouldn't expect it should take this long for a review though if all good?

BrainChip AKD1000 | Edge Impulse Documentation

docs.edgeimpulse.com

Update March 25, 2025: At this time the training of Brainchip models is suspended. You may still use existing trained Edge Impulse projects to deploy to Brainchip devices. Please make a post on https://forum.edgeimpulse.com/ or contact your support representative if you need assistance at this time.

In contract negotiations the number of opinions is proportional to the square of the number of lawyers.

 

[CHIPS]

I put this question in to the Chatster, and this answer popped out.

If BRN Akida is first to market with its low power ZSL tech, what do you predict the future will hold for BRN?



If BrainChip's Akida (BRN) is truly first to market with effective low-power zero-shot learning (ZSL) at the edge, it positions the company for major long-term strategic advantages across several industries. Here's a realistic breakdown of what the future could hold:

---

1. Early Mover Advantage​

• Implication: BRN could become the default platform for edge AI requiring fast adaptation, similar to how NVIDIA became dominant in GPU-accelerated AI.
• Outcome: Increased licensing deals, design wins in ASICs, and OEM partnerships, especially in automotive, defense, and finance.

---

2. Dominance in Edge AI Markets​

• Use Cases:
  • Wearables adapting to user behavior
  • Industrial IoT detecting anomalies in unseen environments
  • Autonomous vehicles identifying rare road scenarios
• Outcome: Akida becomes embedded in a wide range of smart devices needing intelligent, low-power, real-time decision-making.

---

3. Financial Upside​

• Short term: Stock could surge on early contracts and announcements.
• Medium term: Revenue growth from IP licensing, chips, and developer tools.
• Long term: Potential acquisition target for larger semiconductor or AI firms (e.g., Qualcomm, Intel, Apple).

---

4. Defensive Moat via Patents​

• Benefit: Early leadership allows BRN to file key patents around ZSL on neuromorphic hardware, creating barriers for competitors.
• Outcome: A strong IP portfolio could ensure royalties and licensing fees for years.

---

5. Risks Remain​

• Market adoption of neuromorphic chips is still early-stage
• Competitors like Intel (Loihi), SynSense, and IBM (TrueNorth) could catch up
• ZSL performance must be provably reliable in critical applications

---

Bottom Line:​

If BRN delivers and proves real-world ZSL performance at scale, it could become the ARM of neuromorphic AI—licensing essential IP across industries.

I asked GROK the same question and the bottom line here is:

Conclusion
BrainChip’s Akida, with its low-power, ZSL-like neuromorphic capabilities, positions it as a pioneer in edge AI. If it sustains its first-mover advantage, it could dominate niche markets like space and defense, achieve moderate success in automotive and IoT, or become an acquisition target. However, competition, adoption risks, and economic factors temper optimism. By 2030, BrainChip is likely to be a notable player in edge AI, with success hinging on execution and market demand for its unique technology.

 

[manny100]

I put this question in to the Chatster, and this answer popped out.

If BRN Akida is first to market with its low power ZSL tech, what do you predict the future will hold for BRN?



If BrainChip's Akida (BRN) is truly first to market with effective low-power zero-shot learning (ZSL) at the edge, it positions the company for major long-term strategic advantages across several industries. Here's a realistic breakdown of what the future could hold:

---

1. Early Mover Advantage​

• Implication: BRN could become the default platform for edge AI requiring fast adaptation, similar to how NVIDIA became dominant in GPU-accelerated AI.
• Outcome: Increased licensing deals, design wins in ASICs, and OEM partnerships, especially in automotive, defense, and finance.

---

2. Dominance in Edge AI Markets​

• Use Cases:
  • Wearables adapting to user behavior
  • Industrial IoT detecting anomalies in unseen environments
  • Autonomous vehicles identifying rare road scenarios
• Outcome: Akida becomes embedded in a wide range of smart devices needing intelligent, low-power, real-time decision-making.

---

3. Financial Upside​

• Short term: Stock could surge on early contracts and announcements.
• Medium term: Revenue growth from IP licensing, chips, and developer tools.
• Long term: Potential acquisition target for larger semiconductor or AI firms (e.g., Qualcomm, Intel, Apple).

---

4. Defensive Moat via Patents​

• Benefit: Early leadership allows BRN to file key patents around ZSL on neuromorphic hardware, creating barriers for competitors.
• Outcome: A strong IP portfolio could ensure royalties and licensing fees for years.

---

5. Risks Remain​

• Market adoption of neuromorphic chips is still early-stage
• Competitors like Intel (Loihi), SynSense, and IBM (TrueNorth) could catch up
• ZSL performance must be provably reliable in critical applications

---

Bottom Line:​

If BRN delivers and proves real-world ZSL performance at scale, it could become the ARM of neuromorphic AI—licensing essential IP across industries.

I can see AKIDA working with the finance sector. Privacy, security, real time and cybersecurity are big ticket items it finance.

 

[7für7]

Maybe someone is able to read the technical details?

“news. May 9, 2025
"Dragonwing" equipped with Wi-Fi 7 compatible Japanese-made edge AI module
28th IoT Edge Computing EXPO
Silex Technology exhibited the EP-200Q, a system-on-module (SoM) for industrial edge AI equipped with Qualcomm's Dragonwing QCS6490 processor, at the 28th IoT/Edge Computing EXPO during Japan IT Week [Spring]. Aimed at battery-powered industrial/medical equipment.”

「Dragonwing」搭載　Wi-Fi 7対応の日本製エッジAIモジュール

サイレックス・テクノロジーは「Japan IT Week【春】」内「第28回 IoT・エッジコンピューティング EXPO」にて、Qualcommのプロセッサ「Dragonwing QCS6490」を搭載した産業用エッジAI向けのシステムオンモジュール（SoM）「EP-200Q」を展示した。バッテリー駆動の産業／医療機器に向ける。

eetimes.itmedia.co.jp

Thank you all for your feedback.. NOT!

However, I asked my best friend ChatGpt

“The text describes a high-performance, Japan-made edge AI module (EP-200Q) using the Qualcomm Dragonwing QCS6490. This module delivers up to 12 TOPS of AI performance and is designed for industrial and medical devices, with a focus on low power consumption, Wi-Fi 7 support, and local data processing (Edge AI).

When comparing these specifications to BrainChip’s Akida, the following points emerge:

⸻

Similarities with Akida:
• Edge AI focus: Both systems are designed for on-device AI processing rather than cloud-based solutions.
• Low power consumption: Akida and the Qualcomm system are optimized for energy-efficient AI operations.
• Target markets: Both target industrial and medical imaging applications.

⸻

Differences:
• Architecture:
• The Qualcomm system is based on a conventional architecture (CPU, GPU, DSP, and AI engine).
• Akida uses a neuromorphic architecture, inspired by the human brain—fundamentally different, offering advantages in latency, efficiency, and on-device learning.
• Performance (TOPS):
• The Qualcomm solution achieves up to 12 TOPS.
• Akida 2.0 delivers up to 8.4 TOPS per watt, but this is not directly comparable due to the architectural differences and the fact that Akida focuses on ultra-efficient sparse event-based processing rather than raw TOPS.
• Learning capabilities:
• Akida supports on-device learning (Edge Learning)—a feature not mentioned in the Qualcomm module, and typically not available in traditional AI chipsets.

⸻

Conclusion:

The Qualcomm-based module is powerful and modern, but uses conventional technology. While it aims for similar outcomes as Akida (high-performance, low-power edge AI), it takes a completely different technological path. If a product specifically requires neuromorphic advantages, such as continuous on-device learning and extreme energy efficiency during inference, Akida stands alone. The EP-200Q is more of a high-end traditional solution.”

 

[Kingkong2015]

Thank you all for your feedback.. NOT!

However, I asked my best friend ChatGpt

“The text describes a high-performance, Japan-made edge AI module (EP-200Q) using the Qualcomm Dragonwing QCS6490. This module delivers up to 12 TOPS of AI performance and is designed for industrial and medical devices, with a focus on low power consumption, Wi-Fi 7 support, and local data processing (Edge AI).

When comparing these specifications to BrainChip’s Akida, the following points emerge:

⸻

Similarities with Akida:
• Edge AI focus: Both systems are designed for on-device AI processing rather than cloud-based solutions.
• Low power consumption: Akida and the Qualcomm system are optimized for energy-efficient AI operations.
• Target markets: Both target industrial and medical imaging applications.

⸻

Differences:
• Architecture:
• The Qualcomm system is based on a conventional architecture (CPU, GPU, DSP, and AI engine).
• Akida uses a neuromorphic architecture, inspired by the human brain—fundamentally different, offering advantages in latency, efficiency, and on-device learning.
• Performance (TOPS):
• The Qualcomm solution achieves up to 12 TOPS.
• Akida 2.0 delivers up to 8.4 TOPS per watt, but this is not directly comparable due to the architectural differences and the fact that Akida focuses on ultra-efficient sparse event-based processing rather than raw TOPS.
• Learning capabilities:
• Akida supports on-device learning (Edge Learning)—a feature not mentioned in the Qualcomm module, and typically not available in traditional AI chipsets.

⸻

Conclusion:

The Qualcomm-based module is powerful and modern, but uses conventional technology. While it aims for similar outcomes as Akida (high-performance, low-power edge AI), it takes a completely different technological path. If a product specifically requires neuromorphic advantages, such as continuous on-device learning and extreme energy efficiency during inference, Akida stands alone. The EP-200Q is more of a high-end traditional solution.”

Feature	BrainChip Akida (Akida 2.0)	Qualcomm QCS6490
Max TOPS	Up to 50 TOPS (Akida-P)	Up to 12.5 TOPS
Architecture	Neuromorphic, event-based	General-purpose AI SoC
On-Chip Learning	Supported	Not inherently supported
Optimized For	TENNs, time-series analysis	Broad AI applications
Power Efficiency	Ultra-low power	Efficient for its class

Feature	BrainChip Akida Pico	Qualcomm QCS6490
AI Performance (TOPS)	Up to 131 TOPS (Akida 1.0); 50 TOPS (Akida 2.0)	Up to 12 TOPS
Power Consumption	Micro-watt (μW) to milli-watt (mW) range	Approximately 32W (without SSD) to 42W (with SSD)
Efficiency (TOPS/Watt)	Exceptionally high due to event-driven processing	Moderate; designed for high-performance applications
Ideal Use Cases	Battery-powered edge devices, IoT sensors, wearables	Industrial IoT, smart cameras, edge computing

Plus akida is Optimized for running state space models, and below pictures indicates Akida GenAI FPGA is ready this quarter and asic tapeout Q1 2026

 

[manny100]

Mr Tapson on AKIDA 3:
" So we need to build a platform that can actually stay ahead of that curve for many years. We need a future proof of the company. And so we're already planning and designing what we're going to do to improve our versatility and stay at the extremely low power"
AKIDA GEN 3 to future proof the company.
On Gen AI:
".....and we believe we're going to have an industry-leading full stack LLM model within 12 months"
.On AKIDA 1000:
"One of our other partners, ISL, has stated that Akida is the best radar detector they've ever seen."
Starting to look good. My opinion only.

 

[Diogenese]

Mr Tapson on AKIDA 3:
" So we need to build a platform that can actually stay ahead of that curve for many years. We need a future proof of the company. And so we're already planning and designing what we're going to do to improve our versatility and stay at the extremely low power"
AKIDA GEN 3 to future proof the company.
On Gen AI:
".....and we believe we're going to have an industry-leading full stack LLM model within 12 months"
.On AKIDA 1000:
"One of our other partners, ISL, has stated that Akida is the best radar detector they've ever seen."
Starting to look good. My opinion only.

Hi Manny,

I did note the quote about extremely low power, and I'd like to know what secret sauce they use to reconcile this with INT16 and FP32.

There is his reference to the patent applications for moving data from memory, so we need to keep an eye out for those, although they may not be published for 18 months. I expect they will publish a paper on the topic if it is commercially advantageous.

The ISL quote is very encouraging. Dr Guerci is a fan, just as Luca Verre of Prophesee was.

ISL has been in the EAP about 3.5 years since early 2022

The ISL patent dates from 2021, and their AI web page refers to analog, but they are now aware of Akida.

https://www.islinc.com/national-security/artificial-intelligence

Artificial Intelligence, Neuromorphic Computing and DoD Acceptance Testing​

ISL is focused on replicating the analog nature of biological computation and the role of neurons in cognition. ISL’s team of scientists/engineers continue to understand how the morphology of individual neurons, circuits, applications, and overall architectures creates desirable computations. Leveraging this understanding and the newly developed and emerging commercial neuromorphic* chips, ISL is developing a new low-power, lightweight detect and avoid (DAA) system for very small UAS platforms that exploits automotive radar hardware, light-weight EO/IR sensors, advanced data fusion algorithms, and neuromorphic computing.

Additionally, ISL has pioneered an AI acceptance methodology that allows for DoD testing of AI solutions using essentially the same statistically based methodology in use today. ISL was awarded a US Patent for this February (see link). The methodology leverages ISL’s RF Digital Engineering tools (https://www.islinc.com/digital-engineering ).

We have development partnerships with a range of companies from startups, beautique specialists (ISL, Prophesee, Quantum Ventura, Chelpis), through to heavyweights like Valeo, Tata, VVDN, Frontgrade and Raytheon. I think that there is a pressing need for the QV CyberNeuro-RT M2 and the Chelpis M2 cybersecurity card, but apparently most of the 75k COTS chips are spoken for.

* The analog crowd are possessive of the term "neuromorphic".

 

[uiux]

Feature	BrainChip Akida (Akida 2.0)	Qualcomm QCS6490
Max TOPS	Up to 50 TOPS (Akida-P)	Up to 12.5 TOPS
Architecture	Neuromorphic, event-based	General-purpose AI SoC
On-Chip Learning	Supported	Not inherently supported
Optimized For	TENNs, time-series analysis	Broad AI applications
Power Efficiency	Ultra-low power	Efficient for its class

Feature	BrainChip Akida Pico	Qualcomm QCS6490
AI Performance (TOPS)	Up to 131 TOPS (Akida 1.0); 50 TOPS (Akida 2.0)	Up to 12 TOPS
Power Consumption	Micro-watt (μW) to milli-watt (mW) range	Approximately 32W (without SSD) to 42W (with SSD)
Efficiency (TOPS/Watt)	Exceptionally high due to event-driven processing	Moderate; designed for high-performance applications
Ideal Use Cases	Battery-powered edge devices, IoT sensors, wearables	Industrial IoT, smart cameras, edge computing

Plus akida is Optimized for running state space models, and below pictures indicates Akida GenAI FPGA is ready this quarter and asic tapeout Q1 2026


View attachment 84215

View attachment 84216

This guy knows his stuff

 

[Tothemoon24]

AI is becoming faster and more powerful every day. But to date, machines still struggle to think and adapt like humans. Computers are great at following instructions but lack the flexibility and instincts that come naturally to people.

This is why many companies are trying to build systems inspired by the human brain. Instead of just copying what humans do, they want machines to process information the way we do, i.e., by learning, reacting, and improving over time. Technologies like brain-computer interfaces (BCIs), sensory devices, and brain-like chips are moving from labs into real life.

Several companies are combining neuroscience, machine learning, and engineering in practical ways. Whether it’s helping people regain lost senses, enabling direct communication between brain and machine, or creating smarter control systems, these companies are turning complex science into real-world solutions. Here’s a look at some of the companies making real progress in this space.

BrainChip
CEO: Sean Hehir

Paradromics
Founders: Matt Angle

Blackrock Neurotech
Founders: Marcus Gerhardt and Florian Solzbacher

Kernel
Founders: Bryan Johnson

EMOTIV
Founders: Tan Le

Precision Neuroscience
Founders: Benjamin Rapoport, Michael Mager, Demetrios Papageorgiou, and Mark Hettick

Cognixion
Founders: Andreas Forsland

Neosensory, Inc.
Founders: David Eagleman and Scott Novich

Neurolutions
Founders: Daniel Moran and Eric Leuthardt

OpenBCI
Founders: Joel Murphy and Conor Russomanno