BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
IMAGINE 2025
AKIDA 2.0 FPGA @ 25 MHz
www.linkedin.com
We’re excited to join the global edge AI community at Imagine 2025, hosted by Edge Impulse (a Qualcomm company), on October 1st at the Computer History Museum in Mountain View, California, and live online
This year marks the 5th anniversary of Imagine, the premier edge AI conference bringing together innovators, researchers, and industry leaders to showcase real-world breakthroughs, hands-on demos, and the future of edge AI development.
We’ll be on-site at our booth
Stop by to see a live demo of our Akida IP running anomaly detection with FOMO-AD from Edge Impulse. It’s your chance to experience Akida in action and talk with our team about how neuromorphic technology is redefining performance, efficiency, and possibilities at the edge
See you at Imagine 2025!
Event details: October 1, 2025 | 10:00 AM – 5:00 PM PDT | Mountain View, CA + Livestream
Livestream link: https://lnkd.in/g8kCWY46
More information: edgeimpulse.com/imagine
AKIDA 2.0 FPGA @ 25 MHz
#edgeai #embeddedsystems #embeddedai #edgeml #imagine2025 #mlops #aiops #machinelearning #ai #embeddedml | BrainChip
We’re excited to join the global edge AI community at Imagine 2025, hosted by Edge Impulse (a Qualcomm company), on October 1st at the Computer History Museum in Mountain View, California, and live online This year marks the 5th anniversary of Imagine, the premier edge AI conference bringing...
We’re excited to join the global edge AI community at Imagine 2025, hosted by Edge Impulse (a Qualcomm company), on October 1st at the Computer History Museum in Mountain View, California, and live online
This year marks the 5th anniversary of Imagine, the premier edge AI conference bringing together innovators, researchers, and industry leaders to showcase real-world breakthroughs, hands-on demos, and the future of edge AI development.
We’ll be on-site at our booth
Stop by to see a live demo of our Akida IP running anomaly detection with FOMO-AD from Edge Impulse. It’s your chance to experience Akida in action and talk with our team about how neuromorphic technology is redefining performance, efficiency, and possibilities at the edgeSee you at Imagine 2025!
Event details: October 1, 2025 | 10:00 AM – 5:00 PM PDT | Mountain View, CA + Livestream
Livestream link: https://lnkd.in/g8kCWY46
More information: edgeimpulse.com/imagine
Last edited:
In this episode, we spoke with Sean Hehir, CEO, and Jonathan Tapson, Chief Development Officer, of BrainChip about neuromorphic computing for edge AI. We covered why event-based processing and… | IoT ONE
In this episode, we spoke with Sean Hehir, CEO, and Jonathan Tapson, Chief Development Officer, of BrainChip about neuromorphic computing for edge AI. We covered why event-based processing and sparsity let devices skip 99% of useless sensor data, why joules per inference is a more honest metric...
+ IoT ONE Podcast Page: https://lnkd.in/dK6f6mxK
+ Apple Podcasts: https://lnkd.in/fF27x-6
+ Spotify Podcasts: https://lnkd.in/gDN22fV
In this episode, we spoke with Sean Hehir, CEO, and Jonathan Tapson, Chief Development Officer, of BrainChip about neuromorphic computing for edge AI. We covered why event-based processing and sparsity let devices skip 99% of useless sensor data, why joules per inference is a more honest metric than TOPS, how PPA (power, performance, area) guides on-device design, and what it will take to run a compact billion-parameter LLM entirely on device.
We also discussed practical use cases like seizure-prediction eyewear, drones for beach safety, and efficiency upgrades in vehicles, plus BrainChip’s adoption path via MetaTF and its IP-licensing business model.
Key insights:
• Neuromorphic efficiency. Event-based compute minimizes data transfer and optimizes for joules per inference, enabling low-power, real-time applications in medical, defense, industrial IoT, and automotive.
• LLMs at the edge. Compact silicon and state-based designs are pushing billion-parameter models onto devices, achieving useful performance at much lower power.
• Adoption is designed to be straightforward. Models built in standard frameworks can be mapped to BrainChip’s Akida platform using MetaTF, with PPA guiding silicon optimization and early evaluation possible through simulation and dev kits.
• Compelling use cases. Examples include seizure-prediction smart glasses aiming for all-day battery life in a tiny form factor and drones scanning beaches for distressed swimmers. Most current engagements are pure on-edge, with hybrid edge-plus-cloud possible when appropriate.
Yoda
Regular
I feel the same way Tech, you've summed it up perfectly.Despite the dismal share price, there is plenty going on, we are ALL being tested, and as the years have continued to tick by with many I'd suggest haven fallen by the wayside, I will admit that I'm rusted on until the fruit is delivered, either delicious or rotten..I simply say, ask yourself these questions, has the technology continued to grow ? has any other company really excelled at the edge with regards revenue to date ? has our patent fence been breached ?
If you listened to Dr. JT in that recent 6 man panel he talked about the paranoid behaviours being very common amongst companies sharing code etc with 3rd parties in their persuit of assessing if another companies tech is a good fit for their product roadmap moving forward, even admitting that we, Brainchip are just as paranoid in protecting our technology.
OpenAI seems to have gained and is gaining a bigger foothold in this market that is clearly advancing so rapidly that players haven't yet established the right protocol's within their own business modelling to cope, which was suggested was the cause of what appears to be companies caught up in quicksand, as in delays to clearly commit because of the rapid change being witnessed at the coalface.
Regarding staff movements, or being told to walk the plank, the Ethics that Brainchip has committed to are very clear, especially the Code of Conduct that all staff must abide by, it's available for any shareholder to read and absorb.
The final comment tonight is this:
THE CLOCK IS TICKING
Tech
White Horse
Regular
Hi All, we have passed the 33,000 followers.
And this was posted a few hours ago.
https://www.linkedin.com/company/br...gship3_company_posts;lWX/9XODQ+WLBFDzN5ZOYQ==
And this was posted a few hours ago.
https://www.linkedin.com/company/br...gship3_company_posts;lWX/9XODQ+WLBFDzN5ZOYQ==
The link is not working or they deleted itHi All, we have passed the 33,000 followers.
And this was posted a few hours ago.
https://www.linkedin.com/company/brainchip-holdings-limited/posts?lipi=urn:liage:d_flagship3_company_posts;lWX/9XODQ+WLBFDzN5ZOYQ==
It's working for me?
LinkedIn Login, Sign in | LinkedIn
Login to LinkedIn to keep in touch with people you know, share ideas, and build your career.
Food4 thought
Regular
Looks like BrainChip’s coming to this event
We’re thrilled to reveal the incredible line up of panel speakers coming to Semiconductor Australia 2025.
Three feature panels will bring together some of the most influential voices across defence, aerospace, chips, investment, and quantum to tackle the big issues shaping Australia’s sovereign capability and strategic future.
Our feature panel ‘Leading from the Front: tech sovereignty, strategic deterrence, and building Australia’s innovation arsenal’, will examine local success stories and Australia's rising sovereign capability in defence and dual-use technologies.
As global tensions reshape supply chains and strategic alliances, the panel will ask the hard questions: how do we leverage sovereign technologies to strengthen deterrence, attract strategic capital, and integrate cutting-edge innovations into defence and industry?
Moderated by Bell Potter Securities’s James Berman, the discussion will explore how Australia can lead from the front in building an innovation arsenal that keeps pace with the world’s fastest-moving competitors.
The panel includes Defence Council’s Dr Jens Goennemann, DroneShield Angus Bean, Hypersonix Inc. Matt A. Hill, Visionary Machines Sonny Foster, and Wrays | Intellectual Property Paula Adamson.
We’re thrilled to reveal the incredible line up of panel speakers coming to Semiconductor Australia 2025.
Three feature panels will bring together some of the most influential voices across defence, aerospace, chips, investment, and quantum to tackle the big issues shaping Australia’s sovereign capability and strategic future.
Our feature panel ‘Leading from the Front: tech sovereignty, strategic deterrence, and building Australia’s innovation arsenal’, will examine local success stories and Australia's rising sovereign capability in defence and dual-use technologies.
As global tensions reshape supply chains and strategic alliances, the panel will ask the hard questions: how do we leverage sovereign technologies to strengthen deterrence, attract strategic capital, and integrate cutting-edge innovations into defence and industry?
Moderated by Bell Potter Securities’s James Berman, the discussion will explore how Australia can lead from the front in building an innovation arsenal that keeps pace with the world’s fastest-moving competitors.
The panel includes Defence Council’s Dr Jens Goennemann, DroneShield Angus Bean, Hypersonix Inc. Matt A. Hill, Visionary Machines Sonny Foster, and Wrays | Intellectual Property Paula Adamson.
Interested to hear some opinions on this. Highlighted below is a snippet of JT talking about akida tech on the latest podcast.
He goes on to describe akida as working on silicon "OR IN OTHER COMPUTING TECHNOLOGIES"?
Now he could just be referring to software, but it would be an odd way to describe it
I am wondering if he's perhaps referring to things like graphine etc??
Intriguing imo
asiagrowthpartners.com
He goes on to describe akida as working on silicon "OR IN OTHER COMPUTING TECHNOLOGIES"?
Now he could just be referring to software, but it would be an odd way to describe it
I am wondering if he's perhaps referring to things like graphine etc??
Intriguing imo
IoT Spotlight - EP 226 - Neuromorphic for LLMs on the Edge - Sean Hehir, CEO, BrainChip | Asia Growth Partners
EP 226 - Neuromorphic for LLMs on the Edge - Sean Hehir, CEO, BrainChip - In this episode, we spoke with Sean Hehir, CEO, and
HopalongPetrovski
I'm Spartacus!
Good podcast with some probing and intelligent questions.New podcast
View attachment 91653
View attachment 91654
IoT Spotlight - EP 226 - Neuromorphic for LLMs on the Edge - Sean Hehir, CEO, BrainChip | Asia Growth Partners
EP 226 - Neuromorphic for LLMs on the Edge - Sean Hehir, CEO, BrainChip - In this episode, we spoke with Sean Hehir, CEO, and
I thought both Sean and Jonathon acquitted themselves well and it was good to hear Jonathon mention a product by the end of the year.
"Jonathan: Yeah, sure. There's a kind of threshold with LLMs, for example, that if you have less than a billion parameters, you just don't get a really human kind of response. It's not grammatical. It's not logical. It's words, but it's word salad. And above a billion, suddenly, there's almost like a phase change. You get a human quality response. And so our ability to put a model above that billion-parameter threshold on the edge with no web connection or cloud connection is transformative. I think that's the most exciting thing that we see coming along in the next two or three years. And again, to Sean's point, I mean, these models got bigger at a rate of four or five times per year. So that's 125 times in three years if you compound it, so to speak. We really have seen that growth and been able to keep pace with it. I've got to be able to deliver at that scale, which is great.
Sean: I would say one thing, Erik, if I could. This company, the vast majority — I don't know the percentage here in front of me. The vast majority of this company is nothing but scientists and engineers. We have world-class scientists that are doing nothing about keeping abreast and leading model advancements and world-class engineers building the best silicon and software stack. That's all we do. We're thinking about this night and day, about how to get these models around exceptionally well on the edge.
Erik: So, Jonathan, it sounds like LLM on the edge is not quite here yet, but you're expecting it within one or two years to be capable. Can you explain?
Jonathan: Yeah, I would say less than that. We've demonstrated it, and we expect to have a product by the end of the year."
Beyond that Sean sounded both confident and enthusiastic which is of course expected from him, but, it just feels a bit more real this time around.
Well worth a listen.
It's been a long haul to here, but hopefully we are getting towards the pointy end now.
Bring It, BrainChip!
Hi Hoppy,
3 months ago in the Roadmap, JT said that GenAI was available as FPGA and they expected silicon (ASIC) within 12 months. Either that was conservative, or GenAI has been prioritized.
To make GenAI semi-autonomous wrt the cloud, it may use RAG (Retrieval Augmented Generation) with a lot of auxiliary memory.
They talk about 1 billion parameters as a yardstick. Given that this could be up to FP32, that's quite a lot of memory for an edge device.
But, apart from that, the nodes will probably still be the TENNs 128 MAC arrays requiring (comparatively) very little adjustment to the tapeout. That said, I suppose that the MACs will need to be adjusted to handle FP32, and maybe that's where the ISA (Instruction Set Architecture) comes in. SO, ok, there will be a lot of tapeout work required*.
* I'm submitting this to Guinnes for the fastest self-contradiction ...
3 months ago in the Roadmap, JT said that GenAI was available as FPGA and they expected silicon (ASIC) within 12 months. Either that was conservative, or GenAI has been prioritized.
To make GenAI semi-autonomous wrt the cloud, it may use RAG (Retrieval Augmented Generation) with a lot of auxiliary memory.
They talk about 1 billion parameters as a yardstick. Given that this could be up to FP32, that's quite a lot of memory for an edge device.
But, apart from that, the nodes will probably still be the TENNs 128 MAC arrays requiring (comparatively) very little adjustment to the tapeout. That said, I suppose that the MACs will need to be adjusted to handle FP32, and maybe that's where the ISA (Instruction Set Architecture) comes in. SO, ok, there will be a lot of tapeout work required*.
* I'm submitting this to Guinnes for the fastest self-contradiction ...
Tothemoon24
Top 20
BrainChip and Edge Impulse Inc. have maintained a strategic collaboration since 2021. The collaboration involves integrations of BrainChip’s Akida neuromorphic processors with Edge Impulse’s machine learning platform. The combination of the Edge Impulse platform and BrainChip’s hardware enables developers to easily build, train and deploy advanced AI/ML models for the edge. For example, the Raspberry Pi is an ideal, low-cost platform for ML developers to demonstrate edge AI use cases in real-time using the BrainChip Akida AKD1000 AI accelerator chip. Use cases like anomaly detection and visual object classification are supported out-of-the-box with example projects on Edge Impulse. The two companies continue to work together to make available new AI use cases using BrainChip’s MetaTF software on Edge Impulse for training and deploying additional edge AI models to the BrainChip-supported platforms.
Edge Impulse offers an engaged and dynamic developer ecosystem, and our collaboration reflects BrainChip’s mission to enable AI at the edge," said Sean Hehir, CEO of BrainChip. "Using BrainChip’s off-the-shelf hardware platforms with the Edge Impulse platform ensures easy development and deployment of AI/ML models. The combined solution can be used to create advanced real-time, streaming use cases for a wide variety of applications in industrial, consumer, medical and mobility markets."
The conference features leaders from across the edge AI landscape who will discuss the latest industry innovations and partnerships. Speaking at the event is Zach Shelby, VP Product Management, Qualcomm Finland RFFE Oy. Shelby has joined the BrainChip podcast on multiple occasions to discuss a wide range of AI-related industry topics. Also speaking at the event is Nakul Duggal, Group General Manager, Automotive and Industrial & Embedded IoT, at Qualcomm Technologies, Inc.
The Imagine 2025 conference by Edge Impulse will be held in person on October 1st, 2025 at the Computer History Museum in Mountain View, California.
For more information on BrainChip and Edge Impulse, visit our website: BrainChip - Edge Impulse.
Attachments
This man 7fur7, just makes himself look so stupid with most of his comments, I wish that
he would just read the comments and make no comments, he just makes a complete Fool
of himself, it really would be great for him to sell and disappear, it would make a lot of people
here on this Forum very Happy.
Mccabe84
Regular
Neuromorphic Brain Chip in NVIDIA Jetson | AI Cowboys + UT San Antonio Rewire Edge AI
The AI Cowboys fused neuromorphic computing with NVIDIA Jetson at UT San Antonio. Cutting AI energy use by 90%. Explore spiking neural networks, case studies, market growth, and why this breakthrough could reshape sustainability, defense, and accessibility.
www.theaicowboys.com
smoothsailing18
Regular
Neuromorphic Brain Chip in NVIDIA Jetson | AI Cowboys + UT San Antonio Rewire Edge AI
The AI Cowboys fused neuromorphic computing with NVIDIA Jetson at UT San Antonio. Cutting AI energy use by 90%. Explore spiking neural networks, case studies, market growth, and why this breakthrough could reshape sustainability, defense, and accessibility.
www.theaicowboys.com
From the link you provided.Neuromorphic Brain Chip in NVIDIA Jetson | AI Cowboys + UT San Antonio Rewire Edge AI
The AI Cowboys fused neuromorphic computing with NVIDIA Jetson at UT San Antonio. Cutting AI energy use by 90%. Explore spiking neural networks, case studies, market growth, and why this breakthrough could reshape sustainability, defense, and accessibility.
View attachment 91673
Quote:
Case Study: Jetson + Akida vs. Conventional AI
At the National Security Collaboration Center inside UT San Antonio's San Pedro I building, the AI Cowboys tested a hybrid system combining the NVIDIA Jetson Orin AGX with a BrainChip Akida PCIe Board.
- Traditional Jetson-only workload: Continuous anomaly detection on video streams at 120 watts.
- Jetson + Akida neuromorphic hybrid: The same workload, the same accuracy—at just 9 watts.
It is certainly interesting and could benefit BRN.
About Us
Texas’s top AI startup company delivering innovative AI, machine learning, EduTech, and quantum solutions for government, research, and startups.
www.theaicowboys.com
Rob Telson a few years ago stated that we could compliment and not necessarily have to compete in this space with NVIDIA!Neuromorphic Brain Chip in NVIDIA Jetson | AI Cowboys + UT San Antonio Rewire Edge AI
The AI Cowboys fused neuromorphic computing with NVIDIA Jetson at UT San Antonio. Cutting AI energy use by 90%. Explore spiking neural networks, case studies, market growth, and why this breakthrough could reshape sustainability, defense, and accessibility.
View attachment 91673
Come on cogs, start turning. Bring it on!
Evening Mccabe84 & Fellow Chippers ,Neuromorphic Brain Chip in NVIDIA Jetson | AI Cowboys + UT San Antonio Rewire Edge AI
The AI Cowboys fused neuromorphic computing with NVIDIA Jetson at UT San Antonio. Cutting AI energy use by 90%. Explore spiking neural networks, case studies, market growth, and why this breakthrough could reshape sustainability, defense, and accessibility.
View attachment 91673
Nice find
. Just saw this ........ Mentions Neuromorphic..... if only there was a company which dabbled in Neuromorphic Compute...
Pushing the Boundaries of Memory:What’s New with Weebit and AI | Weebit | A Quantum Leap In Data Storage
Blog article: ReRAM scales to advanced nodes, cuts power and cost, and lays the foundation for the next generation of AI, from in-memory-compute to neuromorphic systems.
www.weebit-nano.com
Regards,
Esq.
TheDrooben
Pretty Pretty Pretty Pretty Good
Larry has been out camping since last Friday on very limited internet.........great to see we are back in Larry's buy zone again (not everyone will agree). Catching up on some great posts but we will get the 4C by the end of the month......9M in "bookings" Sean by the next AGM......Larry is watching and waiting
.
.
Similar threads
