BRN Discussion Ongoing

[DK6161]

Charts been looking crap for sometime and your comment is a typical hot crapper comment

View attachment 85493

R U OK Pom?
You sounds bitter, old mate. I thought you're going to keep accumulating and be greedy in times like this.
C'mon then, show us the buy order old chap!
I am just stating what the charts are showing.
And remember, we are on the same boat so I share your frustrations.
Not advice

 

[manny100]

R U OK Pom?
You sounds bitter, old mate. I thought you're going to keep accumulating and be greedy in times like this.
C'mon then, show us the buy order old chap!
I am just stating what the charts are showing.
And remember, we are on the same boat so I share your frustrations.
Not advice

BRN chart wise has been in a long range/base since around September 2023.
Its generally accepted that Neuromorphic AI at the Edge will experience exponential growth.
BRN is generally accepted as the leader of Neuromorphic AI.
At this stage of the cycle those who believe the above is true will accumulate patiently.
The role of good news:
If you believe the above is true then really good news will be the catalyst to break the equilibrium of the range/base and attract new buyers to the extent we will see higher highs and higher lows confirming a sustained uptrend.
Once the trend is established we will then see momentum investing.
Generally, a long base at lows followed by really good news on volume is a classic technical pattern for identifying potential significant price increases.

 

[7für7]

Yeeeehaa record braking! Already 2 announcements this week… will we see 3 or 4???

 

[Pom down under]

R U OK Pom?
You sounds bitter, old mate. I thought you're going to keep accumulating and be greedy in times like this.
C'mon then, show us the buy order old chap!
I am just stating what the charts are showing.
And remember, we are on the same boat so I share your frustrations.
Not advice

Never bitter just playing games with all the weasels from hot crapper

 

[smoothsailing18]

Isn't it Akida that specifically is what helps Nanose sniff partials out or is Jetson able to also do this as well ?.

 

[Bravo]

Isn't it Akida that specifically is what helps Nanose sniff partials out or is Jetson able to also do this as well ?.

Could NVIDIA's Jeston series sniff out the VOC particles with the same accuracy as BrainChip's Akida in relation to Nanose?

ChatGPT said:​

The short answer is: not directly — NVIDIA Jetson modules and BrainChip’s Akida neuromorphic processor operate on fundamentally different architectures and processing models. While both can process data from an e-nose (electronic nose) sensor array, Akida has specific advantages for low-power, real-time inference of volatile organic compounds (VOCs) due to its neuromorphic design.

---

Breakdown: Jetson vs. Akida for VOC Detection (e.g., in NaNose)​

Feature	BrainChip Akida	NVIDIA Jetson (e.g., Xavier NX, Orin)
Architecture	Neuromorphic (Spiking Neural Network)	GPU-accelerated (deep learning, CNNs, LSTMs)
Data Model	Event-based / spike-encoded	Frame-based / dense tensor processing
VOC Sensor Interface	Optimized for real-time spiking data (e.g., AERO encoding)	Can interface but needs preprocessing
Latency	Ultra-low (milliseconds)	Higher (requires buffer + batch inference)
Power Efficiency	Micro-watt to milli-watt range	Several watts to tens of watts
Accuracy with NaNose	Demonstrated 97%+ accuracy using spike-based classification	Potentially similar, but with higher power cost and latency
Training Approach	Online/on-device continual learning	Typically pre-trained and updated via cloud or edge inference
Scalability	Excellent for embedded sensors	Better for multi-modal, compute-heavy scenarios

---

Why Akida May Be Better Suited for VOC Detection in NaNose-Type Devices​

1. Real-Time Spike-Based Classification
   • VOCs generate dynamic, time-dependent signals. Akida processes them directly as spikes, which mimics the biological olfactory system.
   • Jetson would require conversion of VOC sensor data into tensors, potentially losing time-domain resolution and increasing preprocessing complexity.
2. On-Device Learning
   • Akida supports on-chip continual learning, useful for adapting to new users, environments, or sensor drift.
   • Jetson typically relies on cloud-based retraining or large local models with fixed parameters.
3. Power Budget
   • NaNose aims for handheld, portable diagnostics — environments where Jetson’s 10–15W draw (or more) is impractical compared to Akida’s sub-1W footprint.
4. Biological Relevance
   • Akida’s neuromorphic design is inspired by the human olfactory cortex, making it intrinsically well-suited to VOC processing.
   • Jetson is general-purpose AI hardware — very powerful but not biologically inspired or VOC-specialized.

---

Could They Be Used Together?​

Yes. It's theoretically feasible for a hybrid system:

• Akida could perform first-pass classification or anomaly detection from e-nose input.
• Jetson could handle broader context processing, GUI, connectivity, or integration with other modalities (e.g., image + breath analysis).

---

Conclusion​

While Jetson modules are powerful general-purpose AI edge processors, BrainChip’s Akida is purpose-built for ultra-low-power, spike-based sensory tasks like VOC detection. In a medical e-nose like NaNose, Akida is likely more efficient, biologically aligned, and better suited to the task, especially where power, latency, and real-time accuracy are critical.






ChatGPT can make mistakes. Check important info.

 

[Diogenese]

Anastasi Nvidia Huawei Spray Tan

Looks like Anastasi was standing downwind of Donald’s morning application.



China's HUGE AI Chip Breakthrough: NVIDIA is out?

 

[Labsy]

BRN chart wise has been in a long range/base since around September 2023.
Its generally accepted that Neuromorphic AI at the Edge will experience exponential growth.
BRN is generally accepted as the leader of Neuromorphic AI.
At this stage of the cycle those who believe the above is true will accumulate patiently.
The role of good news:
If you believe the above is true then really good news will be the catalyst to break the equilibrium of the range/base and attract new buyers to the extent we will see higher highs and higher lows confirming a sustained uptrend.
Once the trend is established we will then see momentum investing.
Generally, a long base at lows followed by really good news on volume is a classic technical pattern for identifying potential significant price increases.

I call upon the omnipotent power of the universe to grant us a "Trading halt" followed by news of a significant partnership by big tech or/and an offer to buy us out for 5 dollars a share....

 

[Space Cadet]

I call upon the omnipotent power of the universe to grant us a "Trading halt" followed by news of a significant partnership by big tech or/and an offer to buy us out for 5 dollars a share....

Followed by counter offers from other big tech competitors ending up at $14 a share. One can dream but if you have an offer you want more than one interested.

SC

 

[manny100]

Could NVIDIA's Jeston series sniff out the VOC particles with the same accuracy as BrainChip's Akida in relation to Nanose?

ChatGPT said:​

The short answer is: not directly — NVIDIA Jetson modules and BrainChip’s Akida neuromorphic processor operate on fundamentally different architectures and processing models. While both can process data from an e-nose (electronic nose) sensor array, Akida has specific advantages for low-power, real-time inference of volatile organic compounds (VOCs) due to its neuromorphic design.

---

Breakdown: Jetson vs. Akida for VOC Detection (e.g., in NaNose)​

Feature	BrainChip Akida	NVIDIA Jetson (e.g., Xavier NX, Orin)
Architecture	Neuromorphic (Spiking Neural Network)	GPU-accelerated (deep learning, CNNs, LSTMs)
Data Model	Event-based / spike-encoded	Frame-based / dense tensor processing
VOC Sensor Interface	Optimized for real-time spiking data (e.g., AERO encoding)	Can interface but needs preprocessing
Latency	Ultra-low (milliseconds)	Higher (requires buffer + batch inference)
Power Efficiency	Micro-watt to milli-watt range	Several watts to tens of watts
Accuracy with NaNose	Demonstrated 97%+ accuracy using spike-based classification	Potentially similar, but with higher power cost and latency
Training Approach	Online/on-device continual learning	Typically pre-trained and updated via cloud or edge inference
Scalability	Excellent for embedded sensors	Better for multi-modal, compute-heavy scenarios

---

Why Akida May Be Better Suited for VOC Detection in NaNose-Type Devices​

1. Real-Time Spike-Based Classification
   • VOCs generate dynamic, time-dependent signals. Akida processes them directly as spikes, which mimics the biological olfactory system.
   • Jetson would require conversion of VOC sensor data into tensors, potentially losing time-domain resolution and increasing preprocessing complexity.
2. On-Device Learning
   • Akida supports on-chip continual learning, useful for adapting to new users, environments, or sensor drift.
   • Jetson typically relies on cloud-based retraining or large local models with fixed parameters.
3. Power Budget
   • NaNose aims for handheld, portable diagnostics — environments where Jetson’s 10–15W draw (or more) is impractical compared to Akida’s sub-1W footprint.
4. Biological Relevance
   • Akida’s neuromorphic design is inspired by the human olfactory cortex, making it intrinsically well-suited to VOC processing.
   • Jetson is general-purpose AI hardware — very powerful but not biologically inspired or VOC-specialized.

---

Could They Be Used Together?​

Yes. It's theoretically feasible for a hybrid system:

• Akida could perform first-pass classification or anomaly detection from e-nose input.
• Jetson could handle broader context processing, GUI, connectivity, or integration with other modalities (e.g., image + breath analysis).

---

Conclusion​

While Jetson modules are powerful general-purpose AI edge processors, BrainChip’s Akida is purpose-built for ultra-low-power, spike-based sensory tasks like VOC detection. In a medical e-nose like NaNose, Akida is likely more efficient, biologically aligned, and better suited to the task, especially where power, latency, and real-time accuracy are critical.






ChatGPT can make mistakes. Check important info.

This is why Nanose originally chose BRN:
" Because Akida’s “Edge AI” is a complete neural processor that does not require an external CPU, memory, or Deep Learning Accelerator (DLA), and because it is ultra-low power, it offers a realistic opportunity for an inexpensive hand-held diagnostic testing tool akin to a breathalyzer."

BrainChip Inc. and NaNose Medical Successfully Detect COVID-19 in Exhaled Breath with Fast High-Accuracy Results

BrainChip announces progress in testing with the NaNose where patients’ exhaled breath samples were tested for COVID-19.

brainchip.com

 

[Humble Genius]

Followed by counter offers from other big tech competitors ending up at $14 a share. One can dream but if you have an offer you want more than one interested.

SC

How about 70 of us on this forum purchase a syndicate ticket in next Tuesday's $70 million OZ Lotto draw?

 

[manny100]

"BrainChip Eyes Edge AI Market Dominance"​

" After acknowledging past inflexibility, BrainChip has overhauled its product offering, now boasting a suite of products designed to adapt to changing market conditions. The company has seen more engagements in the past five months than ever before, driving confidence in future bookings."
" CEO Sean Hehir highlighted the increasing demand for Edge AI solutions, fueled by the transition of Generative AI from data centers. BrainChip is focusing on State-Space Models (SSMs), particularly Temporal Event-based Neural Networks (TENNs), to establish leadership in Edge applications."

BrainChip Eyes Edge AI Market Dominance - Sharecafe

BrainChip Holdings Ltd (ASX:BRN) is strategically positioning itself to become a dominant force in the Edge AI market. At the Annual General Meeting, Chairman Antonio Viana and CEO Sean Hehir outlined the company's ambitious plans for 2025 and beyond, emphasizing a robust product roadmap...

www.sharecafe.com.au

 

[Slade]

Soon

 

[smoothsailing18]

Thanks Bravo, so hopefully the two ( jetson and Akida ) are integrated into the nanose which would make sense imo.

 

[Space Cadet]

How about 70 of us on this forum purchase a syndicate ticket in next Tuesday's $70 million OZ Lotto draw?

Already have

SC

 

[Jacob Kiraz]

Yeeeehaa record braking! Already 2 announcements this week… will we see 3 or 4???

We're they official on the ASX

 

[Deadpool]

Anastasi Nvidia Huawei Spray Tan

Looks like Anastasi was standing downwind of Donald’s morning application.



China's HUGE AI Chip Breakthrough: NVIDIA is out?

She's still a horn bag my friend (so I've been told by my female friends) although her feet may be a bit a sketchy.
I think I may have started that feet rumor back in the day. LOL Bravo

 

[Frangipani]

The EDGX DPU, based on an NVIDIA Jetson Orin NX and designed for LEO (Low Earth Orbit) missions, can now be sourced through https://satsearch.co/ - with an optional neuromorphic BrainChip Akida add-on:

Happy to welcome EDGX as a satsearch trusted supplier. Introducing the… | Narayan Prasad

Happy to welcome EDGX as a satsearch trusted supplier. Introducing the EDGX DPU, a compact, powerful and modular AI processing system purpose-built for smallsats — and hardened for space. 🔹 Powered by NVIDIA Jetson Orin NX, this DPU delivers 157 TOPS of AI compute in a <1 kg, 0.5U form...

www.linkedin.com

View attachment 84896

EDGX DPU - Onboard AI Compute powered by NVIDIA | satsearch

The EDGX DPU is the most optimal earth-like AI processing system hardened to scale in space. Powered by NVIDIA Jetson Orin NX technology, this DPU is designed for powerful, energy-efficient and scalable onboard AI computing for smallsats.

satsearch.co

View attachment 84897 View attachment 84898


View attachment 84899 View attachment 84900

the global marketplace for the space industry | satsearch

The global marketplace for space, satsearch features space products, sub-systems, components, software, and services from suppliers around the world.

satsearch.co

View attachment 84901

The EDGX team recently presented their EDGX DPU to the Belgian Federal Minister for Public Enterprises, Civil Service, State Building Management, Digitalization and Science Policy & her entourage, which also included a Programme Manager from the Belgian Science Policy Office (BELSPO):

#sciencepolicy #ai #newspace #earthobservation #satcom #ssa… | EDGX

🇧🇪 We had the honour of welcoming Federal Minister Vanessa Matz responsible for Public Enterprises, Civil Service, State Building Management, Digitalization and #SciencePolicy, along with Matthias P. from BELSPO - Belgian Science Policy Office to the EDGX headquarters 🚀 It was a great...

www.linkedin.com

View attachment 84902

View attachment 84905


By the looks, EDGX are counting down to a launch in Q1/2026:

View attachment 84903


As LinkedIn doesn’t provide the exact date of the post, I checked out the Minister’s Instagram profile for any clues - et voilà!

Besides finding out that her visit in Ghent must have been on 16 April itself or a couple of days earlier at most (although the lack of time adverbs such as ‘yesterday‘ or ‘last week’ suggest it was likely a same-day post), I also spotted a BrainChip sticker at the EDGX headquarters in Ghent.

So the launch must be scheduled for no later than 1 March 2026, then.

View attachment 84904

Our Belgian space-tech partner EDGX just unveiled their new logo with the catchphrase “Sky-high Intelligence” at SmallSat Europe 2025 in Amsterdam, where they’re showcasing their EDGX DPU that was “designed to enable real-time in-orbit edge computing for next-gen missions in Earth Observation, Satcom and In-Orbit Servicing”. It runs on an NVIDIA Jetson Orin NX and comes with an optional neuromorphic Akida module for ultra-low-power applications:

#edgx #smallsateurope #aiinspace #onboardprocessing #edgeai #satcom… | EDGX

🚀 Heading off at SmallSat Europe 2025! 🇪🇺 EDGX will be exhibiting at SmallSat Europe next week in Amsterdam! Join us at our booth where we will showcase our AI-based data processing unit – designed to enable real-time in-orbit edge computing for next-gen missions in Earth Observation, Satcom and...

www.linkedin.com

#edgx #smallsateurope #amsterdam #aiinspace #edgecomputing #spacetech… | EDGX

🚀 Live from SmallSat Europe in Amsterdam! We’re on-site with our brand-new EDGX booth and for the first time, we’re revealing our new logo and visual identity to the world! 🔥 👀 Swing by if you’re around, we’re showing: 🚀 High-performance onboard AI with NVIDIA Orin 🚀 Real-world use cases for...

www.linkedin.com

They also appear to have freshened up their website (which still has the old logo, though): https://www.edgx.space/

 

[Diogenese]

This video is about NASA/DARPA/Lockheed updated AI Warthog:

 

[Baneino]

Es folgten Gegenangebote anderer großer Tech-Konkurrenten, die bei 14 Dollar pro Aktie endeten. Man kann zwar träumen, aber bei einem Angebot möchte man mehr als nur einen Interessenten.

SC

45$