This is the most insightful post that I have read and I very much appreciate you taking the time to write it.
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Bravo
If ARM was an arm, BRN would be its biceps💪!
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.
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. ®
www.theregister.com
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?
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
I asked ChatGPT if BrainChip's technology could help address such overheating challenges and the response was very interesting.
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. ®
Brain-inspired neuromorphic computer SpiNNaker overheats
Exclusive: Too much hot air brings down Manchester Uni based neural network project
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:
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.
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.perceptron
Regular
A positive roadmap and AGM, I congratulate the team for their efforts over the past year (and the many more before). It seems the Akida offering is now robust and set for future iterations, which is welcomed. Further, looking back at the achievements of Akida 1000 in radar, space neural network architecture, sensor analysis, cybersecurity and the many more use cases that I am sure have been discovered has been astonishing. I prefer that many smaller companies are reviewing Akida. It means there are more computer/data scientists and engineers working with our technology. A kind of massive parallel research effort is underway. Sure, it is taking time, however, our technology is slightly more advanced than a micro controller and requires equally skilled and talented people to make it a game changer. Moreover, I am excited about the new developer platform that will be offered later this year. Hoping this will integrate all of the Akida IP and models in one central location and have an active community attached.
FiveBucks
Regular
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.
Baron Von Ricta
Regular
Hey Doc,
Something along these lines.
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.
Plans are underway to create new AI-powered drones that can fly for much longer than current designs.
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.
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.
www.livescience.com
US Air Force wants to develop smarter mini-drones powered by brain-inspired AI chips
Published 14 hours agoPlans are underway to create new AI-powered drones that can fly for much longer than current designs.
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.
US Air Force wants to develop smarter mini-drones powered by brain-inspired AI chips
Plans are underway to create new AI-powered drones that can fly for much longer than current designs.
Thanks, early warnings and adaptive responses via AKIDA could save their brand name plus a lot of $$.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. ®
Brain-inspired neuromorphic computer SpiNNaker overheats
Exclusive: Too much hot air brings down Manchester Uni based neural network project
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:
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
Integrating Akida into data center infrastructure could enhance thermal monitoring and management, providing early warnings and adaptive responses to potential overheating scenarios.
- 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.
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.
Deadpool
Did someone say KFC
Isn't this where Pico comes into the fold?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.
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.
US Air Force wants to develop smarter mini-drones powered by brain-inspired AI chips
Plans are underway to create new AI-powered drones that can fly for much longer than current designs.
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.
Jacob Kiraz
Emerged
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
#directconnect #intelfoundry | Intel Foundry
Intel is undergoing a culture shift - and the priority is earning back customer trust. "We want to make sure customers are winning with us. We want to listen." More from Intel Foundry Tech and Manufacturing Head Naga Chandrasekaran at #DirectConnect 2025 👇 https://intel.ly/3Z05ZJl...
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.
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.
US Air Force wants to develop smarter mini-drones powered by brain-inspired AI chips
Plans are underway to create new AI-powered drones that can fly for much longer than current designs.
-“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”
Bravo
If ARM was an arm, BRN would be its biceps💪!
View attachment 83944
#directconnect #intelfoundry | Intel Foundry
Intel is undergoing a culture shift - and the priority is earning back customer trust. "We want to make sure customers are winning with us. We want to listen." More from Intel Foundry Tech and Manufacturing Head Naga Chandrasekaran at #DirectConnect 2025 👇 https://intel.ly/3Z05ZJl...www.linkedin.com
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:
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:
Bravo
If ARM was an arm, BRN would be its biceps💪!
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?
Deadpool
Did someone say KFC
Nice headline.
www.sharecafe.com.au
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
I thought he was referring to royalties not revenue
Well we were nearly hitting 30c but fall to 20c in a few days... so..
White Horse
Regular
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.
Similar threads
