BRN Discussion Ongoing

Bravo

If ARM was an arm, BRN would be its biceps💪!
Looks like we have some more competition on the horizon...3 years away though, so time is on our side.



US Air Force wants to develop smarter mini-drones powered by brain-inspired AI chips​

Published 14 hours ago
Plans are underway to create new AI-powered drones that can fly for much longer than current designs.


FPV kamikaze drones flying in the sky.

Although neuromorphic computing was first proposed by scientist Carver Mead in the late 1980s, it is a field of computer design theory that is still in development.

Scientists are developing an artificial intelligence (AI) chip the size of a grain of rice that can mimic human brains — and they plan to use it in miniature drones.

Although AI can automate monotonous functions, it is resource-intensive and requires large amounts of energy to operate. Drones also require energy for propulsion, navigation, sensing, stabilization and communication.

Larger drones can better compensate for AI's energy demands by using an engine, but smaller drones rely on battery power — meaning AI energy demands can reduce flying time from 45 minutes to just four.
But this may not be a problem forever., Suin Yi and his team at the University of Texas have been awarded funding by the 2025 Air Force Office of Scientific Research Young Investigator Program (part of the Air Force Office of Scientific Research) to develop an energy-efficient AI for drones. Their goal is to build a chip the size of a grain of rice with various AI capabilities — including autonomous piloting and object recognition — within three years.

AI-powered miniature drones​

To build a more energy-efficient AI chip, the scientists propose using conducting polymer thin films. These are (so far) an underused aspect of neuromorphic computing; this is a computer system that mimics the brain’s structure to enable highly efficient information processing.

The researchers intend to replicate how neurons learn and make decisions, thereby saving energy by only being used when required, similar to how a human brain uses different parts for different functions.
Although neuromorphic computing was first proposed by scientist Carver Mead in the late 1980s, it is a field of computer design theory that is still in development. In 2024, Intel unveiled their Hala Point neuromorphic computer, which is powered by more than 1,000 new AI chips and performs 50 times faster than conventional computing systems.

Meanwhile, the Joint Artificial Intelligence Center develops AI software and neuromorphic hardware. Their particular focus is on developing systems for sharing all sensor information with every member of a network of neuromorphic-enabled units. This technology could allow for greater situational awareness, with applications so far including headsets and robotics.
Using technology developed through this research, drones could become more intelligent by integrating conducting polymer material systems that can function like neurons in a brain.
If Yi’s research project is successful, miniature drones could become increasingly intelligent. An AI system using neuromorphic computing could allow smaller and smarter automated drones to be developed to provide remote monitoring in confined locations, with a much longer flying time.


 
  • Like
  • Love
  • Thinking
Reactions: 16 users

manny100

Top 20
Oooopsies! SpiNNaker overheated after its cooling system failed.

I asked ChatGPT if BrainChip's technology could help address such overheating challenges and the response was very interesting.


View attachment 83942



Brain-inspired neuromorphic computer SpiNNaker overheated when coolers lost their chill​


Too much hot air brings down Manchester Uni based neural network project​


Tue 6 May 2025 // 11:29 UTC

Exclusive The brain-inspired SpiNNaker machine at Manchester University in England suffered an overheating incident over the Easter weekend that will send a chill down the spines of datacenter administrators.

According to Professor Steve Furber, now retired (although he told El Reg "SpiNNaker is still seen as my baby!"), a failure with the cooling on April 20 led to a rise in temperatures until the servers were manually shut down the following day.
The SpiNNaker (Spiking Neural Network Architecture) project is all about simulating a brain by connecting hundreds of thousands of Arm cores. While a human brain presents a huge challenge, Furber, one of the designers of the original Arm processor, reckoned a mouse brain was possible.
During a talk earlier this month to celebrate the 40th anniversary of the switch-on of the first Arm processor, Furber told the audience that the hope was to model "one whole mouse" at the required level of detail.
Assuming the hardware survived its baking.
"SpiNNaker," he told The Register, "is hosted in the Kilburn Building, which was completed in 1972 as a purpose-built computer building and, as such, has a plant room that supplies chilled water as a utility to all the central machine rooms.

"The SpiNNaker room was built to house the machine in 2016 in what used to be the mechanical workshop, and is cooled by circulating hot air from the back of the cabinets through a plenum chamber into chillers at either end that blow the air through a cooling system using the building's chilled water."
The problem was with the chilled water supply. Furber said, "If the chilled water isn't actually chilled, the chiller fans are adding to the problem rather than helping solve it."
And so the temperatures began to rise inexorably. Without an automatic shutdown, the servers struggled on. Furber told us that he believed there was an automatic over-temperature shutdown on the individual SpiNNaker boards, and said, "This may have protected the SpiNNaker hardware from damage," but even with the hard-to-replace boards off, the network switches and power supplies remained powered up.

The latter two component types suffered some damage, and without them, the SpiNNaker boards cannot all be tested, "so there may be more issues hidden behind the ones we know about."
Furber added, "We have had a few issues with the cooling system in the nine years that the machine has been operational, but these have not previously led to any damage." He reckoned that the long Easter weekend (in the UK, where Easter Friday and Easter Monday are both public holidays) might have contributed to the length of time it took to contain the temperature rise.
"We are looking into ways to fully automate the shutdown process in the future!"
As for the system's current state, Furber told us, "The machine is back up for internal users at around 80 percent of full capacity but still undergoing tests."
The good news is that the software is designed to work around partial hardware failures. The bad news is that replacing the failed parts will likely require further shutdowns. ®



In this exclusive it describes how the brain-inspired SpiNNaker machine at Manchester University in England suffered an overheating incident over the Easter weekend that will send a chill down the spines of datacenter administrators. What are the implications of this and could BrainChip's neuromorphic technology be utlitized to help reduce heating or else alert to over-heating before damage occurs?

ChatGPT said:​

https://www.researchgate.net/publication/357791842/figure/fig9/AS%3A1111647913545732%401642048924066/The-million-core-SpiNNaker-machine-at-the-University-of-Manchester-occupying-10-rack.png

https://www.microcontrollertips.com/wp-content/uploads/2018/09/BrainChip-Akida-1.jpg

https://i2.wp.com/marketbusinessnews.com/wp-content/uploads/2018/11/SpiNNaker-machine-thumbnail.jpg?fit=1041%2C700&ssl=1

https://brainchip.com/wp-content/uploads/2020/10/Screen-Shot-2020-10-12-at-2.18.37-PM.png

The overheating incident involving the SpiNNaker supercomputer at the University of Manchester underscores the critical importance of thermal management in large-scale neuromorphic systems. SpiNNaker, designed to emulate the parallel processing of the human brain using over a million ARM cores, operates with significant power demands. Any failure in its cooling infrastructure can lead to substantial operational disruptions and potential hardware damage.Research Explorer+1scieng.manchester.ac.uk+1

Implications of the Overheating Incident​

This event highlights several key considerations for neuromorphic computing systems:
  • Thermal Management: Even systems designed for energy efficiency, like SpiNNaker, can experience overheating if cooling systems fail or are inadequate.
  • System Reliability: Overheating can compromise the reliability and longevity of hardware components, leading to increased maintenance costs and downtime.
  • Monitoring and Alerts: The necessity for real-time monitoring systems that can detect and respond to thermal anomalies before they escalate.

Potential Role of BrainChip's Neuromorphic Technology​

BrainChip's Akida™ neuromorphic processor offers features that could be instrumental in addressing such challenges:Wevolver
  • Low Power Consumption: Akida operates with ultra-low power requirements, reducing the thermal output and the burden on cooling systems.
  • On-Chip Learning: Its ability to learn and adapt in real-time allows for the development of intelligent thermal management systems that can predict and mitigate overheating risks.
  • Event-Based Processing: Akida's architecture processes data only when necessary, further conserving energy and minimizing heat generation.
Integrating Akida into data center infrastructure could enhance thermal monitoring and management, providing early warnings and adaptive responses to potential overheating scenarios.

Conclusion​

The SpiNNaker incident serves as a cautionary tale about the vulnerabilities of high-performance computing systems to thermal issues. Leveraging advanced neuromorphic technologies like BrainChip's Akida could offer viable solutions to enhance system resilience through improved energy efficiency and intelligent thermal management.
Thanks, early warnings and adaptive responses via AKIDA could save their brand name plus a lot of $$.
 
  • Like
  • Fire
Reactions: 5 users

Deadpool

Did someone say KFC
Looks like we have some more competition on the horizon...3 years away though, so time is on our side.



US Air Force wants to develop smarter mini-drones powered by brain-inspired AI chips​

Published 14 hours ago
Plans are underway to create new AI-powered drones that can fly for much longer than current designs.


FPV kamikaze drones flying in the sky.

Although neuromorphic computing was first proposed by scientist Carver Mead in the late 1980s, it is a field of computer design theory that is still in development.

Scientists are developing an artificial intelligence (AI) chip the size of a grain of rice that can mimic human brains — and they plan to use it in miniature drones.

Although AI can automate monotonous functions, it is resource-intensive and requires large amounts of energy to operate. Drones also require energy for propulsion, navigation, sensing, stabilization and communication.

Larger drones can better compensate for AI's energy demands by using an engine, but smaller drones rely on battery power — meaning AI energy demands can reduce flying time from 45 minutes to just four.
But this may not be a problem forever., Suin Yi and his team at the University of Texas have been awarded funding by the 2025 Air Force Office of Scientific Research Young Investigator Program (part of the Air Force Office of Scientific Research) to develop an energy-efficient AI for drones. Their goal is to build a chip the size of a grain of rice with various AI capabilities — including autonomous piloting and object recognition — within three years.

AI-powered miniature drones​

To build a more energy-efficient AI chip, the scientists propose using conducting polymer thin films. These are (so far) an underused aspect of neuromorphic computing; this is a computer system that mimics the brain’s structure to enable highly efficient information processing.

The researchers intend to replicate how neurons learn and make decisions, thereby saving energy by only being used when required, similar to how a human brain uses different parts for different functions.
Although neuromorphic computing was first proposed by scientist Carver Mead in the late 1980s, it is a field of computer design theory that is still in development. In 2024, Intel unveiled their Hala Point neuromorphic computer, which is powered by more than 1,000 new AI chips and performs 50 times faster than conventional computing systems.

Meanwhile, the Joint Artificial Intelligence Center develops AI software and neuromorphic hardware. Their particular focus is on developing systems for sharing all sensor information with every member of a network of neuromorphic-enabled units. This technology could allow for greater situational awareness, with applications so far including headsets and robotics.
Using technology developed through this research, drones could become more intelligent by integrating conducting polymer material systems that can function like neurons in a brain.
If Yi’s research project is successful, miniature drones could become increasingly intelligent. An AI system using neuromorphic computing could allow smaller and smarter automated drones to be developed to provide remote monitoring in confined locations, with a much longer flying time.


Isn't this where Pico comes into the fold?
 
  • Like
  • Fire
  • Love
Reactions: 12 users

manny100

Top 20
It would be nice to know what their targets were in the 5 year plan.

We are putting 5 years of faith into them without knowing if we are on track.
Yes, obviously an internal document that they do not want to release maybe to avoid microscopic scrutiny?
The ecosystem stage of development, tech advances, the significant increase in client events of late and the news about bookings and engagements at the AGM implies we are on track.
Full commercial ann Jan'22.
The BODs primary duty is to the entity.
If they were not on track with the 5 year plan they would have/should have taken remedial action.
If client activity continues to accelerate this year then that will give comfort.
 
  • Like
Reactions: 5 users
It would be nice to know what their targets were in the 5 year plan.

We are putting 5 years of faith into them without knowing if we are on track.
100% correct,
I am selling no I'm not,however the next 12 to 18 months will determine the real truth in and around our product and company,
Deals need to be established if our roadmap has now put us in the race to compete now and in the future,
I've heard alot of spin it's now time to deliver
 
  • Like
  • Love
Reactions: 2 users

IloveLamp

Top 20
  • Like
  • Fire
Reactions: 14 users

7für7

Top 20
Looks like we have some more competition on the horizon...3 years away though, so time is on our side.



US Air Force wants to develop smarter mini-drones powered by brain-inspired AI chips​

Published 14 hours ago
Plans are underway to create new AI-powered drones that can fly for much longer than current designs.


FPV kamikaze drones flying in the sky.

Although neuromorphic computing was first proposed by scientist Carver Mead in the late 1980s, it is a field of computer design theory that is still in development.

Scientists are developing an artificial intelligence (AI) chip the size of a grain of rice that can mimic human brains — and they plan to use it in miniature drones.

Although AI can automate monotonous functions, it is resource-intensive and requires large amounts of energy to operate. Drones also require energy for propulsion, navigation, sensing, stabilization and communication.

Larger drones can better compensate for AI's energy demands by using an engine, but smaller drones rely on battery power — meaning AI energy demands can reduce flying time from 45 minutes to just four.
But this may not be a problem forever., Suin Yi and his team at the University of Texas have been awarded funding by the 2025 Air Force Office of Scientific Research Young Investigator Program (part of the Air Force Office of Scientific Research) to develop an energy-efficient AI for drones. Their goal is to build a chip the size of a grain of rice with various AI capabilities — including autonomous piloting and object recognition — within three years.

AI-powered miniature drones​

To build a more energy-efficient AI chip, the scientists propose using conducting polymer thin films. These are (so far) an underused aspect of neuromorphic computing; this is a computer system that mimics the brain’s structure to enable highly efficient information processing.

The researchers intend to replicate how neurons learn and make decisions, thereby saving energy by only being used when required, similar to how a human brain uses different parts for different functions.
Although neuromorphic computing was first proposed by scientist Carver Mead in the late 1980s, it is a field of computer design theory that is still in development. In 2024, Intel unveiled their Hala Point neuromorphic computer, which is powered by more than 1,000 new AI chips and performs 50 times faster than conventional computing systems.

Meanwhile, the Joint Artificial Intelligence Center develops AI software and neuromorphic hardware. Their particular focus is on developing systems for sharing all sensor information with every member of a network of neuromorphic-enabled units. This technology could allow for greater situational awareness, with applications so far including headsets and robotics.
Using technology developed through this research, drones could become more intelligent by integrating conducting polymer material systems that can function like neurons in a brain.
If Yi’s research project is successful, miniature drones could become increasingly intelligent. An AI system using neuromorphic computing could allow smaller and smarter automated drones to be developed to provide remote monitoring in confined locations, with a much longer flying time.




-“OK… THIS IS THE SITUATION… WE HAVE BRAINCHIPS AKIDA..NEUROMORPHIC CHIP MIMICKING THE HUMAN BRAIN!! SERGEANT…..CAN WE DO IT SMALLER?? SOMETHING LIKE A GRAIN OF SAND?”

-“NO SIR SIR NO! MORE LIKE A GRAIN OF RICE SIR”

-“WHEN WILL WE SEE FIRST RESULTS?”

-“SIR, BRAINCHIP IS THREE YEARS AHEAD… WITH MY TEAM WE CAN DO IT IN 1 AND 1/2 YEARS SIR!”

-“I GIVE YOU 6 MONTHS”

-“SIR THANK YOU SIR”

 
  • Haha
  • Like
Reactions: 5 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
View attachment 83944


Interesting @IloveLamp.

By the way, I thought it was likely to have been Intel that Sean was referring to as being the multinational company that was considering licensing Akida but had to pull back due to various factors, including challenges and market conditions in the last 12 months, such as its stock falling 60%.

It's the 60% that caught my ear, since Intel's stock did indeed experience a significant decline in 2024, dropping approximately 60% over the course of the year. Just a mere coincidence? Methinks not.
 
Last edited:
  • Like
  • Love
  • Thinking
Reactions: 36 users

IloveLamp

Top 20
Interesting @IloveLamp.

By the way, I thought it was likely to have been Intel that Sean was referring to as being the multinational company that was considering licensing Akida but had to pull back due to various factors, including challenges and market conditions, such as its stock falling 60%.

It's the 60% that caught my ear, since Intel's stock did indeed experience a significant decline in 2024, dropping approximately 60% over the course of the year. Just a mere coincidence? Methinks not.
You could be right bravo, obviously there is still a relationship there of some kind.

Any relationship with intel is a good one imo, despite their recent struggles, they will forge ahead no doubt and hopefully take us with them...

🤞
 
Last edited:
  • Like
Reactions: 11 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Isn't this where Pico comes into the fold?


Hi @Deadpool,

Both the Air Force's prospective chip and the Akida Pico prioritize low power consumption to extend operational time in small drones.

Whereas Pico is tailored for applications like speech, audio processing and vital sign monitoring, the Air Force's chip is expected to handle more complex tasks such as autonomous navigation and real-time decision-making in dynamic environments, as well as being teeny-weeny!

The Air Force's chip is still in the research and development phase, so whether it ever succeeds in becoming a commercially available solution remains to be seen.

Obviously Pico is commercially available and can be integrated into various devices, including these drones hopefully, if the "grain-of-rice-sized" chip fails for whever reason, I suppose?
 
  • Like
  • Fire
Reactions: 8 users

Deadpool

Did someone say KFC
Nice headline.
 
  • Like
  • Love
  • Fire
Reactions: 20 users

Mccabe84

Regular
What's with the share price? It's now green and almost double the number of buyers as sellers
 
  • Like
  • Fire
  • Wow
Reactions: 10 users

Cardpro

Regular
  • Like
Reactions: 2 users

Cardpro

Regular
What's with the share price? It's now green and almost double the number of buyers as sellers
Well we were nearly hitting 30c but fall to 20c in a few days... so..
 
  • Like
Reactions: 1 users

White Horse

Regular
Hi @Deadpool,

Both the Air Force's prospective chip and the Akida Pico prioritize low power consumption to extend operational time in small drones.

Whereas Pico is tailored for applications like speech, audio processing and vital sign monitoring, the Air Force's chip is expected to handle more complex tasks such as autonomous navigation and real-time decision-making in dynamic environments, as well as being teeny-weeny!

The Air Force's chip is still in the research and development phase, so whether it ever succeeds in becoming a commercially available solution remains to be seen.

Obviously Pico is commercially available and can be integrated into various devices, including these drones hopefully, if the "grain-of-rice-sized" chip fails for whever reason, I suppose?
Hi Bravo,
We can probably achieve the same thing as Uni of Texas, and probably quicker.
Just reduce our 28nm chip to 2 or 3nm.
It would raise costs considerably because of the process, but they will have the same costs.
We can already do the rest, as has been proved by Bascom Hunter.
When you look at what we can do, they are wasting their time.
 
  • Like
  • Fire
Reactions: 13 users
No one asked that’s why.
With the commentary regarding this last 5 months being the best period for lead generation in the companies history. Its a great story. I'd like to think this translates to the company has needed to put on new staff to cover the number of inbound queries, and not the other option which is replacing or backfilling staff who have left. 🤔
 
  • Like
Reactions: 5 users

mcm

Regular
As a matter of interest ... does anyone know anything about Nanoveu?

Looking at their presentation released today it sure seems to be competition for Akida


The following was posted on the crapper this morning. NVU certainly managed to secure the services of a top level CEO ... who also put in $350,000 to participate in the company's recent CR.

"Mark Goranson's CV is extraordinary. Just look at the MC's of the companies he held senior positions with prior to accepting the CEO position at NVU ... huge!

o TE Connectivity (NYSE: US$46.17B Market Cap1): Most recently, Mark served as Vice President of Global Operations for the Sensors Division, managing worldwide sensor operations of wafer fab, silicon foundry and assembly test operations producing a multitude of different sensor technologies and semiconductor sense elements.
o ON Semiconductor (NASDAQ: US$23.21B Market Cap2): Senior Vice President of Global Operations, where he managed worldwide wafer fab, silicon foundry and assembly test operations for producing analog mixed signal ASICs, discretes and numerous other semiconductors.
o Freescale Semiconductor (NYSE: US$11.37B Market Cap3): As Vice President of Fab Operations, Mark directed operations across six facilities worldwide, leading 4,800 team members in production of analog, microprocessors, microcontrollers, and semiconductors
o Intel Corporation (NASDAQ: US$89.84B Market Cap4): Mark previously held numerous roles at Intel over a period of 18-years, where he built state-of-the-art wafer fabrication and assembly/test facilities across the globe which allowed Intel to meet soaring global demand.

The fact Mark chose to head-up NVU with it's tiny MC of only around $27M (and that's AUD not USD) and even throw in $350,000 of his own money to buy shares in the recent CR is all I need to know that he very much likes what he sees in Emass and that there is only one way for the SP to go from here! What do they say? ... follow the smart money! Anyone hoping to buy NVU cheaper going forward might end up being extremely disappointed."

Hey Bravo ... could you perhaps ask Chat GPT for an analysis between the two?
 
  • Like
  • Love
Reactions: 4 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
As a matter of interest ... does anyone know anything about Nanoveu?

Looking at their presentation released today it sure seems to be competition for Akida


The following was posted on the crapper this morning. NVU certainly managed to secure the services of a top level CEO ... who also put in $350,000 to participate in the company's recent CR.

"Mark Goranson's CV is extraordinary. Just look at the MC's of the companies he held senior positions with prior to accepting the CEO position at NVU ... huge!

o TE Connectivity (NYSE: US$46.17B Market Cap1): Most recently, Mark served as Vice President of Global Operations for the Sensors Division, managing worldwide sensor operations of wafer fab, silicon foundry and assembly test operations producing a multitude of different sensor technologies and semiconductor sense elements.
o ON Semiconductor (NASDAQ: US$23.21B Market Cap2): Senior Vice President of Global Operations, where he managed worldwide wafer fab, silicon foundry and assembly test operations for producing analog mixed signal ASICs, discretes and numerous other semiconductors.
o Freescale Semiconductor (NYSE: US$11.37B Market Cap3): As Vice President of Fab Operations, Mark directed operations across six facilities worldwide, leading 4,800 team members in production of analog, microprocessors, microcontrollers, and semiconductors
o Intel Corporation (NASDAQ: US$89.84B Market Cap4): Mark previously held numerous roles at Intel over a period of 18-years, where he built state-of-the-art wafer fabrication and assembly/test facilities across the globe which allowed Intel to meet soaring global demand.

The fact Mark chose to head-up NVU with it's tiny MC of only around $27M (and that's AUD not USD) and even throw in $350,000 of his own money to buy shares in the recent CR is all I need to know that he very much likes what he sees in Emass and that there is only one way for the SP to go from here! What do they say? ... follow the smart money! Anyone hoping to buy NVU cheaper going forward might end up being extremely disappointed."

Hey Bravo ... could you perhaps ask Chat GPT for an analysis between the two?


No worries @mcm!

Here's Chatgpt's reponse.

Nanoveu has collaborated with Weebit Nano through its acquisition of Embedded AI Systems (EMASS).

In March 2025, Weebit Nano and EMASS announced a collaboration to integrate Weebit's Resistive RAM (ReRAM) technology into EMASS's ultra-low-power AI system-on-chip (SoC) at a 22nm process node. This integration aims to enhance energy efficiency, reduce power consumption, and enable instant system wake-up for AI-driven applications, thereby unlocking new capabilities in edge computing.

Nanoveu, having acquired EMASS, is directly involved in this collaboration. The combined solution of Weebit's ReRAM and EMASS's AI SoC is designed to deliver unprecedented performance and efficiency for smart edge-enabled devices.

This partnership was showcased at the Embedded World 2025 Conference & Exhibition, where a live demonstration highlighted the advantages of ReRAM-powered edge AI computing.

In summary, through its acquisition of EMASS, Nanoveu is actively collaborating with Weebit Nano to develop advanced, energy-efficient AI solutions for edge computing applications.


At this stage, Nanoveu is not yet a threatening competitor to BrainChip, but it is emerging as a potentially relevant player in the ultra-low-power edge AI space — especially with its acquisition of Embedded AI Systems (EMASS) and subsequent collaboration with Weebit Nano.

Here’s a breakdown of how they compare and whether Nanoveu poses a strategic threat to BrainChip:


⚖️ Nanoveu vs BrainChip – Comparative Analysis

AspectNanoveu (via EMASS + Weebit)BrainChip (Akida)
Core TechnologyAI SoC integrating ultra-low power MCUs + Weebit ReRAMNeuromorphic AI (event-based spiking neural networks)
Learning CapabilityInference-only (currently); no native on-chip learningSupports on-chip learning and personalization
Memory InnovationReRAM – low-power, non-volatile, embedded memoryInternal memory for event-based processing
Power EfficiencyExtremely low due to ReRAM and architecture designAmong the lowest in market for intelligent compute
Commercial ReadinessEarly-stage, proof-of-concept at Embedded World 2025Commercially shipping (Akida 1000, Akida Pico)
Target MarketsEdge AI: Smart IoT, sensors, wearablesBroader: IoT, automotive, defense, robotics
AI Model ComplexityLikely limited to small-scale ML models (e.g. keyword spotting)Handles more complex SNN and CNN pipelines
IP Maturity / EcosystemVery early development phaseMature SDK, global patents, AI ecosystem partnerships
 
  • Like
  • Fire
  • Love
Reactions: 20 users

mcm

Regular
No worries @mcm!

Here's Chatgpt's reponse.

Nanoveu has collaborated with Weebit Nano through its acquisition of Embedded AI Systems (EMASS).

In March 2025, Weebit Nano and EMASS announced a collaboration to integrate Weebit's Resistive RAM (ReRAM) technology into EMASS's ultra-low-power AI system-on-chip (SoC) at a 22nm process node. This integration aims to enhance energy efficiency, reduce power consumption, and enable instant system wake-up for AI-driven applications, thereby unlocking new capabilities in edge computing.

Nanoveu, having acquired EMASS, is directly involved in this collaboration. The combined solution of Weebit's ReRAM and EMASS's AI SoC is designed to deliver unprecedented performance and efficiency for smart edge-enabled devices.

This partnership was showcased at the Embedded World 2025 Conference & Exhibition, where a live demonstration highlighted the advantages of ReRAM-powered edge AI computing.

In summary, through its acquisition of EMASS, Nanoveu is actively collaborating with Weebit Nano to develop advanced, energy-efficient AI solutions for edge computing applications.



At this stage, Nanoveu is not yet a threatening competitor to BrainChip, but it is emerging as a potentially relevant player in the ultra-low-power edge AI space — especially with its acquisition of Embedded AI Systems (EMASS) and subsequent collaboration with Weebit Nano.

Here’s a breakdown of how they compare and whether Nanoveu poses a strategic threat to BrainChip:


⚖️ Nanoveu vs BrainChip – Comparative Analysis

AspectNanoveu (via EMASS + Weebit)BrainChip (Akida)
Core TechnologyAI SoC integrating ultra-low power MCUs + Weebit ReRAMNeuromorphic AI (event-based spiking neural networks)
Learning CapabilityInference-only (currently); no native on-chip learningSupports on-chip learning and personalization
Memory InnovationReRAM – low-power, non-volatile, embedded memoryInternal memory for event-based processing
Power EfficiencyExtremely low due to ReRAM and architecture designAmong the lowest in market for intelligent compute
Commercial ReadinessEarly-stage, proof-of-concept at Embedded World 2025Commercially shipping (Akida 1000, Akida Pico)
Target MarketsEdge AI: Smart IoT, sensors, wearablesBroader: IoT, automotive, defense, robotics
AI Model ComplexityLikely limited to small-scale ML models (e.g. keyword spotting)Handles more complex SNN and CNN pipelines
IP Maturity / EcosystemVery early development phaseMature SDK, global patents, AI ecosystem partnerships
Thanks so much Bravo!

Sure seems Akida is way more sophisticated however Nanovue might be competition for the simpler applications. I checked on their collaboration with Weebit ... it was a demo involving hand gestures recognition. See below excerpt from WBT recent quarterly report:

Live demonstration of ReRAM and edge AI at Embedded World

At the Embedded World Conference & Exhibition in Germany in March, Nanoveu’s (ASX: NVU) EMASS, a provider

of ultra-low-power AI computing, demonstrated their gesture recognition chip working with Weebit ReRAM.

The combination of Weebit ReRAM with EMASS’ ultra-low power AI system-on-a-chip (SoC), both at a 22nm

process node, enhances energy efficiency, reduces power consumption, and enables cost effective edge AI
 
  • Like
Reactions: 7 users
Thanks so much Bravo!

Sure seems Akida is way more sophisticated however Nanovue might be competition for the simpler applications. I checked on their collaboration with Weebit ... it was a demo involving hand gestures recognition. See below excerpt from WBT recent quarterly report:

Live demonstration of ReRAM and edge AI at Embedded World

At the Embedded World Conference & Exhibition in Germany in March, Nanoveu’s (ASX: NVU) EMASS, a provider

of ultra-low-power AI computing, demonstrated their gesture recognition chip working with Weebit ReRAM.

The combination of Weebit ReRAM with EMASS’ ultra-low power AI system-on-a-chip (SoC), both at a 22nm

process node, enhances energy efficiency, reduces power consumption, and enables cost effective edge AI
I love this competition thread , We have no runs on the board until we get IP'S and Revenue
 
  • Like
Reactions: 1 users
Top Bottom