Space Cadet
Regular
Always look on the bright side of life.Speaking of sanctions:
I wonder what’s the punishment for violating the spelling of our company’s name ON OUR OWN WEBSITE?
View attachment 85548
I'm Brian and so is my wife.
SC
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
I'm Brian and so is my wife.
SC
Pom down under
Top 20
I can’t see anything wrongSpeaking of sanctions:
I wonder what’s the punishment for violating the spelling of our company’s name ON OUR OWN WEBSITE?
View attachment 85548
Baron Von Ricta
Regular
Bravo
If ARM was an arm, BRN would be its biceps💪!
Nice work NaNose!
Nanose Medical won first place in the startup competition at the Bynet Data Communications, powered by NVIDIA!
In regards to BrainChip's ongoing involvement, I stumbled upon @Deena's post dated 14 November 2023. I'm unsure if anyone has heard anything more recent by way of confirmation of involvement or otherwise?
Last edited:
Bravo
If ARM was an arm, BRN would be its biceps💪!
It's plausible that Nanose are utilizing one of NVIDIA's Jetson modules, which means the device won't have the ultra low power energy efficiency that Akida can offer.
Given the complementary strengths of Akida and NVIDIA's GPU-based platforms, it's conceivable that both technologies could be integrated into future iterations of NaNose Medical's devices but without official confirmation, we just won't know.
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.
Pom down under
Top 20
Last edited:
smoothsailing18
Regular
Isn't it Akida that specifically is what helps Nanose sniff partials out or is Jetson able to also do this as well ?.
Bravo
If ARM was an arm, BRN would be its biceps💪!
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
- 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.
- 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.
- 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.
- 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.
Labsy
Regular
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
Regular
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.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....
SC
This is why Nanose originally chose BRN: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.
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
- 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.
- 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.
- 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.
- 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.
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).
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.
" 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
"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
smoothsailing18
Regular
Thanks Bravo, so hopefully the two ( jetson and Akida ) are integrated into the nanose which would make sense imo.
Last edited:
Space Cadet
Regular
Already haveHow about 70 of us on this forum purchase a syndicate ticket in next Tuesday's $70 million OZ Lotto draw?
SC
Similar threads
