BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Where Is the Pump?
(Parody of "Where Is the Love?" by The Black Eyed Peas - created by ChatGPT)
[Verse 1]
What's wrong with the market, mama?
People hypin' tech, but my shares got drama
Talkin’ 'bout chips that think like brains
Low-power dreams drivin’ hype insane
Edge AI on every headline
Neuromorphin’ like it’s sci-fi time
But every time I check my stock app
BrainChip bleeds — where’s the comeback?
[Pre-Chorus]
Innovations, publications
Conferences and celebrations
But no lift in valuation
Just flatlines and hesitation
[Chorus]
Where is the pump, the pump, the pump, the pump?
Where is the pump, the pump, the pump?
Where is the pump, the pump, the pump, the pump?
BRN's the brain, but where’s the gain?
[Verse 2]
They talk about the race for AI's soul
With chips that run fast and power-control
Big dreams from the labs to the stage
But BRN stuck in a bargain-bin cage
Analysts say it's the dawn of change
So why's this stock still lookin' strange?
ASICs flexin', GPUs fallin’
Still no one’s BRN callin’
[Bridge]
It’s not about the tech, it’s about the trust
But we need that price line to adjust
News is hot, but charts are cold
What’s the value if it won’t unfold?
[Chorus]
Where is the pump, the pump, the pump, the pump?
Where is the pump, the pump, the pump?
Where is the pump, the pump, the pump, the pump?
Neuromorph gold, but it’s undersold
Created using ChatGPT lol
Imo only
(Parody of "Where Is the Love?" by The Black Eyed Peas - created by ChatGPT)
[Verse 1]
What's wrong with the market, mama?
People hypin' tech, but my shares got drama
Talkin’ 'bout chips that think like brains
Low-power dreams drivin’ hype insane
Edge AI on every headline
Neuromorphin’ like it’s sci-fi time
But every time I check my stock app
BrainChip bleeds — where’s the comeback?
[Pre-Chorus]
Innovations, publications
Conferences and celebrations
But no lift in valuation
Just flatlines and hesitation
[Chorus]
Where is the pump, the pump, the pump, the pump?
Where is the pump, the pump, the pump?
Where is the pump, the pump, the pump, the pump?
BRN's the brain, but where’s the gain?
[Verse 2]
They talk about the race for AI's soul
With chips that run fast and power-control
Big dreams from the labs to the stage
But BRN stuck in a bargain-bin cage
Analysts say it's the dawn of change
So why's this stock still lookin' strange?
ASICs flexin', GPUs fallin’
Still no one’s BRN callin’
[Bridge]
It’s not about the tech, it’s about the trust
But we need that price line to adjust
News is hot, but charts are cold
What’s the value if it won’t unfold?
[Chorus]
Where is the pump, the pump, the pump, the pump?
Where is the pump, the pump, the pump?
Where is the pump, the pump, the pump, the pump?
Neuromorph gold, but it’s undersold
Created using ChatGPT lol
Imo only
Frangipani
Top 20
Akida is mentioned alongside other neuromorphic platforms in this not peer-reviewed pre-print published yesterday titled “Neuromorphic Modeling of Molecular Signatures in the Human Spine”, in which the US-based co-authors see huge potential for neuromorphic technology in their field of research:
Conclusions
Neuromorphic computing platforms, empowered by Recursive Temporal Attention architectures, offer a powerful paradigm for real-time, energy-efficient decoding of complex molecular events in spinal health. By closely emulating biological computation, these systems bridge the gap between high-resolution biosensing and adaptive inference, capturing temporal dynamics that traditional digital frameworks often overlook. We have demonstrated that such architectures not only improve sensitivity to transient molecular phenomena—such as cytokine fluxes and matrix remodeling kinetics—but also enable the modeling of cross-scale biological dependencies, including the epigenetic consequences of inflammatory surges.
These capabilities extend far beyond academic demonstrations. When embedded within clinical workflows, neuromorphic systems promise to enable predictive, minimally invasive diagnostics and to support closed-loop therapeutic modulation tailored to a patient’s molecular profile. The convergence of neuromorphic sensing, recursive temporal modeling, and biological pathway inference heralds a transformative shift in spinal diagnostics, with implications for preventive care, real-time intervention, and personalized treatment planning.
As neuromorphic platforms continue to evolve, their integration into implantable and wearable medical technologies will offer persistent, adaptive surveillance of spine health at unprecedented granularity. These developments position neuromorphic computing not only as a next-generation analytic tool but also as a foundational infrastructure for future clinical neuromolecular intelligence system.
One of the references [5] is to another recently published paper by NZ researchers that I shared last week, which also mentions Akida:
https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-465565
Conclusions
Neuromorphic computing platforms, empowered by Recursive Temporal Attention architectures, offer a powerful paradigm for real-time, energy-efficient decoding of complex molecular events in spinal health. By closely emulating biological computation, these systems bridge the gap between high-resolution biosensing and adaptive inference, capturing temporal dynamics that traditional digital frameworks often overlook. We have demonstrated that such architectures not only improve sensitivity to transient molecular phenomena—such as cytokine fluxes and matrix remodeling kinetics—but also enable the modeling of cross-scale biological dependencies, including the epigenetic consequences of inflammatory surges.
These capabilities extend far beyond academic demonstrations. When embedded within clinical workflows, neuromorphic systems promise to enable predictive, minimally invasive diagnostics and to support closed-loop therapeutic modulation tailored to a patient’s molecular profile. The convergence of neuromorphic sensing, recursive temporal modeling, and biological pathway inference heralds a transformative shift in spinal diagnostics, with implications for preventive care, real-time intervention, and personalized treatment planning.
As neuromorphic platforms continue to evolve, their integration into implantable and wearable medical technologies will offer persistent, adaptive surveillance of spine health at unprecedented granularity. These developments position neuromorphic computing not only as a next-generation analytic tool but also as a foundational infrastructure for future clinical neuromolecular intelligence system.
One of the references [5] is to another recently published paper by NZ researchers that I shared last week, which also mentions Akida:
https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-465565
Last edited:
Frangipani
Top 20
One sentence seems a little odd, though, given we do not know of any commercially available edge medical device that uses Akida:
What do the pre-print authors mean by “While the Akida chip is commercially used in edge medical devices…”? Would this info make it through a peer-reviewed process?
Even the Onsor NEXA glasses are still undergoing clinical trials and - provided they’ll be given the green light - are slated for release next year.
Frangipani
Top 20
Our friends at Neurobus and Coros Space will be two of five ESA BIC France startups pitching their ideas (Neuromorphic AI onboard spacecraft resp. In-Orbit Servicing) at the International Paris Air Show on 17 June:
European Space Agency - ESA will participate in the 55th edition of the International Paris Air Show, taking place from 16 to 22 June at Le Bourget airport. | ESA Commercialisation Gateway
European Space Agency - ESA will participate in the 55th edition of the International Paris Air Show, taking place from 16 to 22 June at Le Bourget airport. ESA will join Centre National d'Études Spatiales (CNES) and the aerospace industry in the newly established Paris Space Hub, an initiative...www.linkedin.com
View attachment 86904
COROS SPACE
www.coros-space.com
View attachment 86905 View attachment 86906 View attachment 86907 View attachment 86908
While Coros Space Co-Founder and CTO Iván Rodríguez Ferrández is an expert on embedded GPUs for space, I strongly suspect Akida will also play a part in their vision of future In-Orbit Servers:
Dear network, | Sanath Muret | 15 comments
Dear network, This post announces the end of an era and the beginning of a new one. For the past two years, I was a YGT in the On-Board Computers & Data Handling Section at the European Space Agency - ESA. It was, in a way, a life-changing experience. I acquired invaluable knowledge on novel...
View attachment 86909
At Coros Space, we are supporting a new era of in-orbit computing, where new processing systems unlock unmatched performance for autonomous and high-efficiency data processing in the harshest space… | Coros Space
At Coros Space, we are supporting a new era of in-orbit computing, where new processing systems unlock unmatched performance for autonomous and high-efficiency data processing in the harshest space environments. We’re proud that Iván Rodríguez Ferrández pioneered the use of embedded GPUs for...
View attachment 86910
🚀 Come Meet the Neurobus Team at the Paris Air Show! | Neurobus
🚀 Come Meet the Neurobus Team at the Paris Air Show! 🛰️ We’re excited to share that Neurobus will be at the International Paris Air Show this year! 📍 Find us at the Paris Space Hub, within the Startup Pavilion of GIFAS – Hall 2B, Booth #A28. Let’s connect and explore the future of edge...
Labsy
Regular
What We Know So Far About Anduril's 'Eagle Eye' Military XR Headset and Founder's Reunion With Meta https://share.google/a4nAPPbGZU3q9A4UW
Rejection might be your strongest signal. | Chris Tottman | 76 comments
Rejection might be your strongest signal. In new markets, the best ideas often sound “crazy” right up until they’re obvious. Traditional customer discovery doesn’t always fit. But if you’ve lived the problem and know the pain is real, early rejection can mean you're onto something. New Market...
From tinyML to the Edge of AI: Connecting AI to the Real World | Sensors Converge
www.sensorsconverge.com
We're headed to the main stage at Sensors Converge! | Syntiant Corp.
We're headed to the main stage at Sensors Converge! Join our CEO, Kurt Busch, on Thursday, June 26 at 1 p.m., for a forward-looking panel: "From tinyML to the Edge of AI: Connecting AI to the Real World." Moderated by Michael Kuptz of the EDGE AI FOUNDATION, Busch will be joined by execs from...
Tony Coles
Regular
Yeah, that 0.21 looks suspicious. I’m sick of the games being played but i do have an order at 0.205 and if it gets below 0.20 at end of financial June sale, will purchase again and that’s it. Will wait it out till end of year and hopefully by then they will start using the ASX for real announcements. Licences or what our customers are using our chips/technology in. That connection with Basscom Hunter and Onsor should have been announced at the very least.
Morning Chippers,
Smart glasses are coming thick $ fast.
Regards,
Esq.
Smart glasses are coming thick $ fast.
Regards,
Esq.
But you know? Maybe they are too busy with closing deals that’s why there a no news.. and one day, we will wake up and BOOOOM… the big announcement will pop up and everything will be forgiven! And some of us will get rich! 
#marketingman #positivity #ipraytogodiwillnotloosemymoney #gobrainchip
#marketingman #positivity #ipraytogodiwillnotloosemymoney #gobrainchip
Sorry if already posted..
shop.brainchipinc.com
AKD1000 M.2 Card E Key
Specifications Akida M.2 Card, powered by AKD1000 IC with an ARM M.4 CPU plus 20 Akida 1.0 event-based processing NPUs in a mesh. Akida M.2 AKD1000 Card accelerates CNN-based neural network models using BrainChip’s ultra energy-efficient, and purely digital, event-based processing architecture...
equanimous
Norse clairvoyant shapeshifter goddess
Hi Frangipani,
Good chance its through Tata.
Healthcare and Life Sciences Technology Solutions
Transform the healthcare & life sciences industry with advanced medical device design, digital health engineering, robotics, Gen AI, & regulatory compliance solutions.
www.tataelxsi.com
BrainChip and Tata Elxsi Partner to Provide Intelligent, Ultralow-Power Solutions
BrainChip and Tata Elxsi are teaming up to deliver cutting-edge solutions. Learn more about the partnership that's shaping the future.
brainchip.com
BrainChip and Tata Elxsi Partner to Provide Intelligent, Ultralow-Power Solutions
Tata Elxsi is a leading design and technology services provider for Automotive, Broadcast, Communications, Healthcare, and Transportation. We help customers reimagine their products and services with design thinking and digital technologies like IoT, Cloud, Mobility, VR, and AI.
www.tataelxsi.com
Enhancing intelligence with BrainChip-Tata Elxsi collaboration
BrainChip Holdings Ltd, the pioneer in producing ultra-low power, fully digital, event-based, neuromorphic AI IP, is pleased to announce Tata Elxsi, a prominent design
Akida Pico Announcement
Transform Your AI Applications with Akida Pico Ultra Low Power Core Unlock the potential of battery-powered AI with the Akida Pico Ultra Low Power Core, designed to enhance applications in speech and audio processing as well as medical vital sign monitoring. Operating efficiently in the...
brainchip.com
Medical Device Design and Engineering Service and Solutions
Medical device design and engineering services provide advanced solutions for sustainable development. Enhance clinical performance with effective design engineering and innovative services.
www.tataelxsi.com
Tata Elxsi - Digital Health Platform & Services for Future Healthcare
Digital health services & platform enhance patient care with AI-driven solutions. Enable seamless telemedicine, remote monitoring, & personalized healthcare experiences
www.tataelxsi.com
Bravo
If ARM was an arm, BRN would be its biceps💪!
I asked ChatGPT if BrainChip's AKIDA be used for the applications outlined in Meta's patent as shown below?
Meta's patent outlines biosignal monitoring in AR/smart glasses, including:
While Akida could support or enhance these use cases:
Yes, Akida is well-suited to handle many of the AI inference tasks outlined in Meta’s patent — especially anything involving continuous, energy-efficient biosignal analysis. If Meta values privacy, low power, and real-time responsiveness in their future smart glasses, a neuromorphic edge processor like Akida could be a compelling option.
Would you like a quick visual comparison of Akida vs typical ARM/Qualcomm NPUs for this type of workload?
The chart above compares BrainChip's Akida processor to a conventional NPU (e.g. Qualcomm's Hexagon) across six key criteria relevant to smart glasses and biosignal analysis:
patent.nweon.com
ChatGPT said:
Yes, a neuromorphic processor like BrainChip’s Akida could absolutely be used for many of the applications outlined in Meta’s patent — and in some ways, it may offer significant advantages over conventional processors.
Summary of Meta’s Patent Use Cases (US20230172468)
Meta's patent outlines biosignal monitoring in AR/smart glasses, including:- Heart rate and heart rate variability
- Blood pressure estimation
- Electrocardiogram (ECG) waveform analysis
- Stress or fatigue detection
- User authentication via biosignals
Why Akida Is a Good Fit
| Feature | Meta’s Needs | Akida's Strength |
|---|---|---|
| Event-driven signal processing | Intermittent or subtle biosignal changes (e.g., arrhythmia, stress response) | Akida excels at analyzing sparse, time-dependent data like ECG/PPG without constantly polling a CPU |
| Ultra-low power | Critical for all-day wear in AR/smart glasses | Akida is designed for always-on processing with minimal power draw |
| Edge inference | Requires local, private on-device processing | Akida enables AI inference directly on-device without cloud reliance |
| Time-series pattern detection | Needed for stress, fatigue, HRV anomalies | Akida supports temporal pattern recognition and can learn from evolving signal patterns using spiking neural networks |
| Personalization | Biosignal baselines vary per user | Akida supports incremental on-device learning for personalized AI models |
Example Scenarios Where Akida Could Enhance Meta’s Applications
- Stress Monitoring
→ Akida could detect deviations in heart rate variability or galvanic skin response over time and classify them as stress patterns. - Fatigue Detection for AR Use
→ By continuously analyzing subtle biosignal shifts, Akida could alert users (or apps) to attention lapses, which is crucial in AR/VR safety. - Adaptive UI/UX
→ If a user’s biometric data shows increased heart rate or agitation, the UI could adapt — dim lighting, mute notifications, etc. - On-device Personal Authentication
→ Akida could analyze a user’s unique ECG or PPG pattern to authenticate without needing facial recognition or passcodes.
Limitations
While Akida could support or enhance these use cases:- Sensor interface requirements would need to be adapted (Akida does not have native PPG/ECG analog frontend — that must be paired externally).
- Meta may already have in-house AI pipelines or use Qualcomm’s NPU, making integration dependent on broader ecosystem decisions.
Conclusion
Yes, Akida is well-suited to handle many of the AI inference tasks outlined in Meta’s patent — especially anything involving continuous, energy-efficient biosignal analysis. If Meta values privacy, low power, and real-time responsiveness in their future smart glasses, a neuromorphic edge processor like Akida could be a compelling option.Would you like a quick visual comparison of Akida vs typical ARM/Qualcomm NPUs for this type of workload?
You said:
yes pleaseChatGPT said:
Akida vs Conventional NPU for Smart Glasses AI WorkloadsThe chart above compares BrainChip's Akida processor to a conventional NPU (e.g. Qualcomm's Hexagon) across six key criteria relevant to smart glasses and biosignal analysis:
- Power Efficiency: Akida is exceptionally power-efficient due to its neuromorphic architecture, which is crucial for wearable devices with small batteries.
- Real-Time Latency: Akida's event-driven design allows for faster response times in signal detection, outperforming frame-based NPUs.
- Edge Inference Capability: Both Akida and NPUs can handle edge inference, but Akida’s architecture is optimized for on-device decision-making without preprocessing overhead.
- Adaptive Learning: Akida supports on-device learning (spiking neural networks), something traditional NPUs generally do not, making it useful for personalized biosignal monitoring.
- Privacy: Akida processes data locally, reducing the need for cloud offloading—essential for sensitive health or biometric data.
- Time-Series Signal Analysis: Akida excels in analyzing continuous data streams such as biosignals, ideal for predicting seizures or recognizing user states in smart glasses.
Meta Patent | Ppg and ecg sensors for smart glasses - Nweon Patent
patent.nweon.com
I asked ChatGPT if BrainChip's AKIDA be used for the applications outlined in Meta's patent as shown below?
View attachment 87255
ChatGPT said:
Yes, a neuromorphic processor like BrainChip’s Akida could absolutely be used for many of the applications outlined in Meta’s patent — and in some ways, it may offer significant advantages over conventional processors.
Meta's patent outlines biosignal monitoring in AR/smart glasses, including:
These involve continuous, time-series data from PPG and/or ECG sensors — which are ideal for real-time analysis with minimal latency and energy overhead.
- Heart rate and heart rate variability
- Blood pressure estimation
- Electrocardiogram (ECG) waveform analysis
- Stress or fatigue detection
- User authentication via biosignals
Feature Meta’s Needs Akida's Strength Event-driven signal processing Intermittent or subtle biosignal changes (e.g., arrhythmia, stress response) Akida excels at analyzing sparse, time-dependent data like ECG/PPG without constantly polling a CPU Ultra-low power Critical for all-day wear in AR/smart glasses Akida is designed for always-on processing with minimal power draw Edge inference Requires local, private on-device processing Akida enables AI inference directly on-device without cloud reliance Time-series pattern detection Needed for stress, fatigue, HRV anomalies Akida supports temporal pattern recognition and can learn from evolving signal patterns using spiking neural networks Personalization Biosignal baselines vary per user Akida supports incremental on-device learning for personalized AI models
- Stress Monitoring
→ Akida could detect deviations in heart rate variability or galvanic skin response over time and classify them as stress patterns.- Fatigue Detection for AR Use
→ By continuously analyzing subtle biosignal shifts, Akida could alert users (or apps) to attention lapses, which is crucial in AR/VR safety.- Adaptive UI/UX
→ If a user’s biometric data shows increased heart rate or agitation, the UI could adapt — dim lighting, mute notifications, etc.- On-device Personal Authentication
→ Akida could analyze a user’s unique ECG or PPG pattern to authenticate without needing facial recognition or passcodes.While Akida could support or enhance these use cases:
- Sensor interface requirements would need to be adapted (Akida does not have native PPG/ECG analog frontend — that must be paired externally).
- Meta may already have in-house AI pipelines or use Qualcomm’s NPU, making integration dependent on broader ecosystem decisions.
Yes, Akida is well-suited to handle many of the AI inference tasks outlined in Meta’s patent — especially anything involving continuous, energy-efficient biosignal analysis. If Meta values privacy, low power, and real-time responsiveness in their future smart glasses, a neuromorphic edge processor like Akida could be a compelling option.
Would you like a quick visual comparison of Akida vs typical ARM/Qualcomm NPUs for this type of workload?
You said:
yes please
ChatGPT said:
Akida vs Conventional NPU for Smart Glasses AI Workloads
View attachment 87254
The chart above compares BrainChip's Akida processor to a conventional NPU (e.g. Qualcomm's Hexagon) across six key criteria relevant to smart glasses and biosignal analysis:
In conclusion, Akida would be a strong fit for the kinds of biosignal-driven applications described in Meta’s patent and Onsor’s glasses.
- Power Efficiency: Akida is exceptionally power-efficient due to its neuromorphic architecture, which is crucial for wearable devices with small batteries.
- Real-Time Latency: Akida's event-driven design allows for faster response times in signal detection, outperforming frame-based NPUs.
- Edge Inference Capability: Both Akida and NPUs can handle edge inference, but Akida’s architecture is optimized for on-device decision-making without preprocessing overhead.
- Adaptive Learning: Akida supports on-device learning (spiking neural networks), something traditional NPUs generally do not, making it useful for personalized biosignal monitoring.
- Privacy: Akida processes data locally, reducing the need for cloud offloading—essential for sensitive health or biometric data.
- Time-Series Signal Analysis: Akida excels in analyzing continuous data streams such as biosignals, ideal for predicting seizures or recognizing user states in smart glasses.
Meta Patent | Ppg and ecg sensors for smart glasses - Nweon Patent
Could… Akida would fit in every device if you will… but there are some people, which are not visible, who think, it’s not a good idea… and I have the feeling, they have a lot of money and influence……..a….lot….of….money…….and , a….lot….of….influence……
(If you don’t have a logical explanation for thing, just drop some conspiracy theories lol)
Here some theories from MY ChatGPT
Conspiracy Theory #1:The Cloud Mafia Wants Your Data Brain
If devices like smartphones, VR headsets, or wearables become too smart — e.g. through Akida — they no longer need the cloud. No data uploads, no subscription models, no real-time user tracking.
That’s bad for business for:• Meta
• Amazon
• Apple (only half guilty
)The theory: They are blocking the spread of real edge AI because their business models rely on centralized control.
Local intelligence = loss of control.
⸻
️ Conspiracy Theory #2:Governments Love Dumb Devices
Smart edge devices that learn locally and don’t upload data are a problem for surveillance systems.
Imagine glasses that recognize who you are but don’t send anything to the cloud — no backdoor, no access for third parties.
So these kinds of technologies are “accidentally”:
• not standardized
• not subsidized
• not built into mainstream hardware
⸻
Conspiracy Theory #3:The Competition Fears the Biological
Akida works with spikes, like real neurons.
That’s fundamentally different from classic CPUs or GPUs.
Companies that have invested billions in conventional chips don’t want this paradigm shift — because it would mean rethinking everything from scratch.
Result: Lobbying against “exotic” architectures.
And yes – many of those decision-makers have:
A… lot… of… money… and a… lot… of… influence.
⸻
Realistic Perspective:What’s needed:
• Brave companies (startups or independent OEMs)
• Open hardware initiatives
• Pressure from developers and users who want true edge AI
Last edited:
ATTENTION!!!!! ONLY FOR LONG TERM HOLDER!!!!!
Based on ChatGPT
⸻
Current Status & Technology of BrainChip
1. Akida Platform
• Akida™ is a fully digital, event-based edge AI processor designed for ultra-low power consumption (sometimes under 1 mW) and supports on-chip learning.
• The current version (2nd generation, March 2023) supports 8-bit weights, Vision Transformers (ViT), and Temporal Event-Based Neural Networks (TENNs) – optimized for voice, radar, and vision tasks at the edge.
2. Form Factors & Products
• BrainChip already offers developer boards in M.2 format with the AKD1000 chip – plug-and-play for prototyping.
• Additional embedded products and Edge AI box ecosystems are being promoted, as seen in the “Edge AI Box Ecosystem Launch” release.
3. Strategic Partnerships
• Key partners include Frontgrade Gaisler (aerospace), MegaChips, Edge Impulse, Prophesee, SiFive, Renesas, and Intel Foundry Services, among others.
• Use cases span gesture recognition, epilepsy-monitoring smart glasses, radar-based ISR platforms, and other real-time edge applications.
⸻
Technology Roadmap & Milestones
• April 22, 2025 (AGM): CDO Dr. Jonathan Tapson presented the updated roadmap:
• Focus on more configurable IP for diverse edge applications.
• Expansion of TENNs and ViT integration; platform-based approach for commercial use cases.
• Embedded Vision Summit (May 20–22, 2025): CTO Dr. Peter Lewis demonstrated how state-space models and TENNs outperform Transformers in extreme edge conditions.
• Next steps include broader IP licensing to SoC makers and OEMs across sectors like automotive, wearables, defense, and space.
⸻
Financials & Market Overview
• Publicly traded on the ASX (BRN) and OTC markets (OTCQX: BRCHF/BCHPY).
• As of the last earnings report: moderate revenue growth, net loss around US$ 8.4M – typical for a scaling tech company, but underlines ongoing capital needs.
• Notably, major investor LDA Capital has exercised option tranches – showing institutional interest despite volatility.
⸻
Realistic Outlook for Long-Term Holders
Area Potential & Risks
Technology Event-based, ultra-low power, and on-chip learning position Akida strongly for the future of edge AI. TENNs and ViTs are a solid evolution.
Market & Use Cases Strategic partnerships open diverse markets – but real-world adoption is still in early stages. Platform strategy could take time.
Financials Losses are expected at this stage. Success depends on timely and broad IP licensing.
Timeline Key developments expected over the next 12–24 months: licensing deals, OEM integrations, and potentially first mass-market products.
⸻
Final Verdict – Why This Has Long-Term Potential
1. Technological lead in low-power edge AI through event-driven neuromorphic architecture.
2. Strong strategic alliances across key growth industries.
3. Focused roadmap with clear licensing and platform scale-up strategy.
4. Still: capital requirements and long sales cycles remain risks.
Based on ChatGPT
⸻
Current Status & Technology of BrainChip1. Akida Platform
• Akida™ is a fully digital, event-based edge AI processor designed for ultra-low power consumption (sometimes under 1 mW) and supports on-chip learning.
• The current version (2nd generation, March 2023) supports 8-bit weights, Vision Transformers (ViT), and Temporal Event-Based Neural Networks (TENNs) – optimized for voice, radar, and vision tasks at the edge.
2. Form Factors & Products
• BrainChip already offers developer boards in M.2 format with the AKD1000 chip – plug-and-play for prototyping.
• Additional embedded products and Edge AI box ecosystems are being promoted, as seen in the “Edge AI Box Ecosystem Launch” release.
3. Strategic Partnerships
• Key partners include Frontgrade Gaisler (aerospace), MegaChips, Edge Impulse, Prophesee, SiFive, Renesas, and Intel Foundry Services, among others.
• Use cases span gesture recognition, epilepsy-monitoring smart glasses, radar-based ISR platforms, and other real-time edge applications.
⸻
Technology Roadmap & Milestones• April 22, 2025 (AGM): CDO Dr. Jonathan Tapson presented the updated roadmap:
• Focus on more configurable IP for diverse edge applications.
• Expansion of TENNs and ViT integration; platform-based approach for commercial use cases.
• Embedded Vision Summit (May 20–22, 2025): CTO Dr. Peter Lewis demonstrated how state-space models and TENNs outperform Transformers in extreme edge conditions.
• Next steps include broader IP licensing to SoC makers and OEMs across sectors like automotive, wearables, defense, and space.
⸻
Financials & Market Overview• Publicly traded on the ASX (BRN) and OTC markets (OTCQX: BRCHF/BCHPY).
• As of the last earnings report: moderate revenue growth, net loss around US$ 8.4M – typical for a scaling tech company, but underlines ongoing capital needs.
• Notably, major investor LDA Capital has exercised option tranches – showing institutional interest despite volatility.
⸻
Realistic Outlook for Long-Term HoldersArea Potential & Risks
Technology Event-based, ultra-low power, and on-chip learning position Akida strongly for the future of edge AI. TENNs and ViTs are a solid evolution.
Market & Use Cases Strategic partnerships open diverse markets – but real-world adoption is still in early stages. Platform strategy could take time.
Financials Losses are expected at this stage. Success depends on timely and broad IP licensing.
Timeline Key developments expected over the next 12–24 months: licensing deals, OEM integrations, and potentially first mass-market products.
⸻
Final Verdict – Why This Has Long-Term Potential1. Technological lead in low-power edge AI through event-driven neuromorphic architecture.
2. Strong strategic alliances across key growth industries.
3. Focused roadmap with clear licensing and platform scale-up strategy.
4. Still: capital requirements and long sales cycles remain risks.
Similar threads
