BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Apologies if already posted
"Akida is particularly good at conserving energy and can be used in various applications, from smart cars to industrial IoT, where it excels in tasks like incremental learning and fast decision-making."
New partnership to offer next-gen tech to students
The University of Western Australia has announced a cutting-edge collaboration with tech company BrainChip to equip students with the tools and resources they n
www.uwa.edu.au
"Akida is particularly good at conserving energy and can be used in various applications, from smart cars to industrial IoT, where it excels in tasks like incremental learning and fast decision-making."
Tothemoon24
Top 20
Frangipani
Regular
He maybe is just a guest of brainchip…
No way! You need to carefully reread Frontgrade Gaisler’s LinkedIn post (which is not about embedded world 2024, by the way, just in case you missed that).
It literally says:
“Dr. Jonathan Tapson from BrainChip visited our booth at Space Symposium to discuss neuromorphic processing for space applications. They have been developing and continuously improving their technology for extremely efficient AI inference and learning.”
Do you really believe our company would send someone who doesn’t work for them (in what capacity remains to be seen) to a Colorado Springs conference they are not involved with in order to discuss serious business matters with a Swedish company that we know is planning on integrating our IP into their hardware very soon and possibly also discuss our disruptive tech with interested third parties that are paying the Frontgrade Gaisler booth a visit?!
Just because he is an expert on neuromorphic hardware, happens to have known our CTO for years and conveniently lives in the same US state the Space Symposium is currently taking place (I suppose living 300 miles away from the venue counts as “just around the corner” within the Universe scheme of things
)? Think about it: Alf Kuchenbuch, our Munich-based VP of Sales EMEA could hop on a short flight to Gothenburg any time to talk to Sandi Habinc or someone else from Frontgrade Gaisler in person.
Jonathan Tapson’s lanyard says “Visitor” as he was neither an attendee nor a speaker at the Space Symposium, and BrainChip isn’t an exhibitor either (whereas Frontgrade Gaisler has a booth). I scrolled through the Space Symposium’s Flickr photostream and picked out two pictures to demonstrate what I mean (the conference coincided with the eclipse on April 8).
If you ask me, the Frontgrade Gaisler LinkedIn post’s wording and accompanying photo are unambiguous. All that’s missing is some sort of confirmation by BrainChip or Jonathan Tapson himself.
Frangipani
Regular
Meanwhile at the embedded world 2024 in Nuremberg / Nürnberg:
Sean seems to be pursuing the famous invisible tablecloth strategy now!
Sean seems to be pursuing the famous invisible tablecloth strategy now!
Last edited:
Frangipani
Regular
Just came across this awesome article about Brainchip on Medium, written by someone with the moniker NeuroCortex.AI - and a follow-up is already in the works!
BrainChip’s Akida: Neuromorphic Processor Bringing AI to the Edge
NeuroCortex.AI
·
Follow
8 min read
·
6 hours ago
As our regular readers you might recall we have covered the basics of Neuromorphic computing a blog series last year and are now pursuing further research into its implementation. One of the blockers in the real time implementation of Spiking neural networks (SNNs) is availability of an actual Neuromorphic chip(s) to run SNN algorithms.
Thus we started connecting with various industry professionals who were connected to developing neuromorphic chips. Soon enough we connected with BrainChip US operations team (based in California) and started talking about potential collaboration. They were kind enough to help us out and agreed to send BrainChip Akida chips our way.
Before we start with implementing SNN models onto Akida let us tell you about BrainChip the company, Akida chipset and why its useful for us.
Akida by BrainChip, mimics the human brain to analyze only essential sensor inputs at the point of acquisition, processing data with unparalleled efficiency, precision, and economy of energy consumption.
BrainChip is an Australian company that specializes in edge artificial intelligence (AI) on-chip processing and learning. They are the worldwide leader in edge AI on-chip processing and learning, offering solutions that bring common sense to the processing of sensor data, enabling machines to do more with less. BrainChip has a global presence with engineering teams located in California, Toulouse France, Hyderabad India, and Perth Australia.
BrainChip’s flagship product, Akida™, is a fully digital, event-based AI processor that mimics the human brain, analyzing essential sensor inputs at the point of acquisition with high efficiency, precision, and energy economy. This technology allows for edge learning local to the chip, reducing latency, improving privacy, and enhancing data security. Akida, Greek for ‘spike,’ is a neuromorphic SoC that implements a spiking neural network. In many ways, it’s similar to some of the well-known research projects that were presented over the past several years such as IBM’s TrueNorth, SpiNNaker, and Intel Loihi. With Akida, BrainChip is attempting to seize this early market opportunity with one of the first commercial products. BrainChip is targeting a wide range of markets from the sub-1W edge applications to higher power and performance applications in the data center.
Timeline (BrainChip)
Here’s a breakdown of what Akida is all about:
- Inspired by the Brain and Benefits of a Brain-Inspired Approach: Unlike traditional processors that rely on complex clock cycles, Akida uses event-based processing, similar to how neurons fire in the brain. It utilizes neuromorphic computing, mimicking the human brain’s structure and function. This means Akida processes information in a more efficient way, similar to how neurons fire and communicate This allows it to focus on essential information and reduce power consumption.
- High Performance, Low Power Consumption: BrainChip claims that Akida offers superior performance per watt compared to other solutions. This makes it suitable for edge AI applications where power efficiency is crucial. Akida’s event-based processing focuses on essential information, significantly reducing energy use. This makes it perfect for edge AI applications where battery life is a constraint. Don’t be fooled by the low power consumption. Akida delivers exceptional performance per watt, making it suitable for real-time AI tasks at the network’s edge.
- On-Chip Learning: Akida can perform some level of learning on the device itself, reducing reliance on cloud-based training and processing. Akida can perform some machine learning tasks directly on the chip, reducing reliance on cloud-based training and processing. This improves privacy and reduces latency.
- Anomaly Detection: Akida can be trained to identify unusual patterns in data, making it ideal for security and fraud detection
- Sensor Processing: From analyzing data from cameras and microphones to interpreting readings from industrial sensors, Akida can handle various sensor data streams.
- Autonomous Systems: Akida’s low power consumption and real-time processing capabilities make it suitable for autonomous systems like drones and robots.
- Supported Neural Networks: Akida is designed to accelerate various neural networks directly in hardware, including Convolutional Neural Networks (CNNs) commonly used for image recognition, Recurrent Neural Networks (RNNs) for sequence analysis, and even custom Temporal Event-based Nets (TENNs) optimized for processing complex time-series data.
- Akida Development Environment: BrainChip offers a complete development environment called MetaTF for seamless creation, training, and testing of neural networks specifically designed for the Akida platform. This includes tools for simulating models and integrating them with Python-based machine learning frameworks for easier development.
Akida NSoC Architecture
The Akida NSoC neuron fabric is comprised of cores that are organized in groups of four to create nodes, which are mesh networked. The cores can be implemented for either convolutional layers or fully-connected layers. This flexibility allows users to develop networks with ultra-low power Event-Based Convolution as well as Incremental Learning. The nodes also can be used to implement multiple networks on a single device.
Akida Development environment
The development environment looks similar to any machine learning framework. Users describe their SNN model which is stored in the model zoo. The chip will come with three pre-created models (CIFAR, Imagenet and MNIST) or they can create their own architecture. A Python script can be used to specify data location, model type, and this is shipped off to the Akida execution engine with the Akida neuron model and training methodology with conversions (from pixel to spikes, etc.). It goes into training mode or inference mode depending on user settings. The Akida NSoC uses a pure CMOS logic process, ensuring high yields and low cost. Spiking neural networks (SNNs) are inherently lower power than traditional convolutional neural networks (CNNs), as they replace the math-intensive convolutions and back-propagation training methods with biologically inspired neuron functions and feed-forward training methodologies.
Brainchip’s claim is that while a convolutional approach is more akin to modeling the neuron as a large filter with weights, the iterative linear algebra matrix multiplication on data within an activation layer and associated memory and MAC units yields a power hungrier chip. Instead of this convolutional approach, an SNN models the neuron function with synapses and neurons with spikes between the neurons. The networks learn through reinforcement and inhibition of these spikes (repeating spikes are reinforcement).
The ability to change the firing threshold of the neuron itself and the sensitivity to those spikes is a different and more efficient way to train, albeit within complexity limitations. This means way less memory (there are 6MB per neural core) and a more efficient end result. Neurons learn through selective reinforcement or inhibition of synapses. The Akida NSoC has a neuron fabric comprised of 1.2 million neurons and 10 billion synapses.
Akida Neuron Fabric
The “Akida” device has an on-chip processor complex for system and data management and is also used to tell the neuron fabric (more on that in a moment) to be in training or inference modes. This is a matter of setting the thresholds in the neuron fabric. The real key is the data to spike converter, however, especially in areas like computer vision where pixel data needs to be transformed into spikes. This is not a computationally expensive problem from an efficiency perspective, but it does add some compiler and software footwork. There are audio, pixel, and fintech converters for now with their own dedicated place on-chip. The Akida NSoC is designed for use as a stand-alone embedded accelerator or as a co-processor. It includes sensor interfaces for traditional pixel-based imaging, dynamic vision sensors (DVS), Lidar, audio, and analog signals. It also has high-speed data interfaces such as PCI-Express, USB, and Ethernet. Embedded in the NSoC are data-to-spike converters designed to optimally convert popular data formats into spikes to train and be processed by the Akida Neuron Fabric.
The PCIe links allow for data-center deployments and can scale with the multi-chip expansion port, which is a basic high speed serial interface to send spikes to different neural processing cores — expandable to 1024 devices for very large spiking neural networks. The Akida neuron fabric shown below has its own 6MB on-chip memory and the ability to interface with flash and DDR.
The “Akida” device has an on-chip processor complex for system and data management and is also used to tell the neuron fabric (more on that in a moment) to be in training or inference modes. This is a matter of setting the thresholds in the neuron fabric. The real key is the data to spike converter, however, especially in areas like computer vision where pixel data needs to be transformed into spikes. This is not a computationally expensive problem from an efficiency perspective, but it does add some compiler and software footwork. There are audio, pixel, and fintech converters for now with their own dedicated place on-chip.
The CIFAR 10 benchmark they are rating their performance and efficiency
Brainchip’s “Akida” chip is aimed at both datacenter and training and inference. This includes vision systems in particular but also financial tech applications where users cannot tolerate intermittent connectivity or latency from cloud.
BrainChip’s Commitment to Development
BrainChip is actively developing Akida, with the second generation offering improved capabilities for handling complex neural networks. They are also working on a comprehensive development environment called MetaTF, which simplifies the creation and deployment of neural networks specifically designed for Akida.
The Future of AI is Neuromorphic
The Akida neuromorphic processor represents a significant leap forward in AI technology. With its efficient processing, on-chip learning capabilities, and wide range of applications, Akida is poised to revolutionize the way AI is used at the edge. As BrainChip continues to develop Akida, we can expect even more exciting possibilities to emerge in the future of AI.
Conclusion
In essence, the Akida Neuromorphic Processor is a powerful yet energy-efficient AI processor designed to bring intelligence to the edge of networks by mimicking the human brain’s processing style. Its unique features make it a promising solution for various applications requiring real-time and low-power AI capabilities. Akida is still under development, with BrainChip working on newer generations to address the growing intelligence chip market. Overall, BrainChip is a company at the forefront of neuromorphic computing, aiming to revolutionize AI processing with brain-inspired hardware.
A good news we actually received 2x Akida chips few days back thanks to BrainChip. Soon we are publishing a detailed write-up as how to install and run AI models on top of it. Stay tuned. !!
The two Akida chips we received from BrainChip
References
[1] https://brainchip.com/akida-neural-processor-soc/
[2] https://brainchip.com/akida-generations/
[3] https://brainchip.com/what-is-the-akida-event-domain-neural-processor-2/
[4] https://www.design-reuse.com/news/54941/brainchip-akida-platform-ai.html
[5]
[6] https://www.sharesinvalue.com.au/brainchip-an-unrivalled-neural-network-processing-technology/
[7] https://www.edge-ai-vision.com/resources/technologies/processors/
[8] https://brainchip.com/technology/
I just found out who is behind this excellent article!
[Can’t open the link to the website https://www.neurodynamic.ai, though - it says the server could not be found… Maybe AGI has taken over already and blocked it from public view…
]The talented blog author, Tamal Acharya, works for both Tata Consultancy Services and NeuroCortex.AI:
Attachments
Last edited:
Anil backin it up with a two fa....
View attachment 60572
Qualcomm Acquires foundries.io, Announces Products For IoT, Edge
The announcements come at a time when Qualcomm plans to expand the portfolio of its current IoT offerings.www.electronicsb2b.com
"88% lower power per data transfer than previous generations"
Qualcomm readies 'micro-power' Wi-Fi system and 'AI-ready' IoT platforms
Qualcomm said it will also expand its portfolio to address safety and other requirements for industrial grade solutions.
Intel Vision 2024 | LinkedIn
See how AI everywhere is changing everything at the premier event for business and tech leaders. Learn about the latest AI solutions and gain insights on business transformation from Intel partners and execs. Livestream Pat Gelsinger’s keynote on April 9 at 8:30am PT! #IntelVision
Intel Corporation on LinkedIn: 3 Laws of the Edge- Intel Vision 2024 Did you catch the 3 Laws of the Edge…
Did you catch the 3 Laws of the Edge from Pat Gelsinger's #IntelVision keynote? They’re why we’re announcing new Intel #edge #AI products for enterprises to…
Watch the speech in the video, he starts at about 1h 37min, I'm already grinning by 1hr 33min........
1h 27min analysing data better at the edge
Accenture Chief ai officer talks from 1hr 15min
BrainChip Talks AI Innovation with Accenture’s Managing Director and Global Chief Technology Officer of Accenture Applied Intelligence Jean-Luc Chatelain
BrainChip engages in AI innovation discussions with Accenture's Jean-Luc Chatelain, exploring transformative advancements across industries.
brainchip.com
Xeon 6 announced from 1hr 10min
Sierra forest going into production this qtr, 2.5 x better performance / watt.......
Wasted on prem data from 1hr 6min
From 1hr 5min he essentially talks about new architecture types
About 1hr 3min gelsing mentions an mx alliance with nvidia, Qualcommand arm, to bring new standardise training and inferencing
Head of tech at SuperMicro 52min
Arizona state uni president from 39min
BOSCH from 35min
Michael Dell talks from 22min
BrainChip Talks with Rob Lincourt of Dell Technologies in Latest Monthly Podcast
BrainChip talks Edge devices, neuromorphic computing, beneficial AI + MORE in sixth ep of ‘This is our Mission’ podcast series
brainchip.com
16min GAUDI 3
Closing notes 7min
Attachments
Last edited:
Pat Gunslinger ,
Three Laws of EDGE,
1, Economics....There is not enough physical cash , bullion & loose diamonds globally to purchase BrainChip outright.
2 , Physics... the logistics of physically distributing the above loot to BrainChip holders would take some time.
3, Land.... There are not enough tropical islands globaly to satiate every BrainChip holder.
Pat forgot the forth...
4, Due to the above constraints , companys engaged in the business of Edge should just pay Brainchip for a Licence & Royalties there after.
Regards,
Esq.
Three Laws of EDGE,
1, Economics....There is not enough physical cash , bullion & loose diamonds globally to purchase BrainChip outright.
2 , Physics... the logistics of physically distributing the above loot to BrainChip holders would take some time.
3, Land.... There are not enough tropical islands globaly to satiate every BrainChip holder.
Pat forgot the forth...
4, Due to the above constraints , companys engaged in the business of Edge should just pay Brainchip for a Licence & Royalties there after.
Regards,
Esq.
This timeline is closing fast...within the next 14 business days, shipment dates will be confirmed.
It's the feedback from users, that's what will be key moving forward with this side operation, hopefully opening up
doors to much bigger things throughout 2025 and beyond, we are way overdue for some "real solid revenue type news"
Still, Brainchip remains firmly in the drivers seat, holding NUMBER 1 POLE POSITION ON THE GRID
$799.00
Purchasing greater than 10 Edge boxes?
Contact sales@brainchip.com
Product pre-orders are available. Click here to see the terms.
Shipments are expected to commence by mid-year 2024. BrainChip will communicate specific shipment dates by Apr. 30th 2024.
It's the feedback from users, that's what will be key moving forward with this side operation, hopefully opening up
doors to much bigger things throughout 2025 and beyond, we are way overdue for some "real solid revenue type news"
Still, Brainchip remains firmly in the drivers seat, holding NUMBER 1 POLE POSITION ON THE GRID
Akida™ Edge AI Box
$799.00
Purchasing greater than 10 Edge boxes?
Contact sales@brainchip.com
Product pre-orders are available. Click here to see the terms.
Shipments are expected to commence by mid-year 2024. BrainChip will communicate specific shipment dates by Apr. 30th 2024.
Ok, Maybe “Brainchip” is a unown city somewhere in this world?? Think about it … he said “from” brainchip not “working at brainchip” 🫵No way! You need to carefully reread Frontgrade Gaisler’s LinkedIn post (which is not about embedded world 2024, by the way, just in case you missed that).
It literally says:
“Dr. Jonathan Tapson from BrainChip visited our booth at Space Symposium to discuss neuromorphic processing for space applications. They have been developing and continuously improving their technology for extremely efficient AI inference and learning.”
View attachment 60632
Do you really believe our company would send someone who doesn’t work for them (in what capacity remains to be seen) to a Colorado Springs conference they are not involved with in order to discuss serious business matters with a Swedish company that we know is planning on integrating our IP into their hardware very soon and possibly also discuss our disruptive tech with interested third parties that are paying the Frontgrade Gaisler booth a visit?!
Just because he is an expert on neuromorphic hardware, happens to have known our CTO for years and conveniently lives in the same US state the Space Symposium is currently taking place (I suppose living 300 miles away from the venue counts as “just around the corner” within the Universe scheme of things
Think about it: Alf Kuchenbuch, our Munich-based VP of Sales EMEA could hop on a short flight to Gothenburg any time to talk to Sandi Habinc or someone else from Frontgrade Gaisler in person.
Jonathan Tapson’s lanyard says “Visitor” as he was neither an attendee nor a speaker at the Space Symposium, and BrainChip isn’t an exhibitor either (whereas Frontgrade Gaisler has a booth). I scrolled through the Space Symposium’s Flickr photostream and picked out two pictures to demonstrate what I mean (the conference coincided with the eclipse on April 8).
View attachment 60633
View attachment 60634
If you ask me, the Frontgrade Gaisler LinkedIn post’s wording and accompanying photo are unambiguous. All that’s missing is some sort of confirmation by BrainChip or Jonathan Tapson himself.
Just kidding you’re right! It’s possible! I was yesterday just a quick checking the thread here and in the German forum. And I thought the user there had a good point regarding “brainchip guest” . Thanks for your clarifying!
Terroni2105
Founding Member
ISC West is held annually in Las Vegas, it is the largest converged security trade event in USA.
VVDN is there and their area has a huge video screen running and brainchip is up on there under the heading Platform Experience.
The post is on X (twitter) and LinkedIn.
This is a screenshop I grabbed through the video.
www.linkedin.com
VVDN is there and their area has a huge video screen running and brainchip is up on there under the heading Platform Experience.
The post is on X (twitter) and LinkedIn.
This is a screenshop I grabbed through the video.
VVDN Technologies on LinkedIn: #vvdnatiscwest #iscwest2024 #iscwest #lasvegas #securitysurviellance…
We're here and live at ISC West 2024 & all set to connect & innovate! The countdown to ISC West is over and team VVDN is all geared up to showcase the latest…
Did someone post this already?
Rob likes it!
www.linkedin.com
Rob likes it!
TEAL on LinkedIn: XPONENTIAL 2024 - BOOK A MEETING - Cellular IoT Connectivity | True eSIM…
Are you ready to amplify your drone operations and soar beyond the limits? Join TEAL at XPONENTIAL Show 2024, the most influential event for drones and the…
Jefwilto
Regular
Morning Chippers ,
TSMC kicking goals.
TECH
Arjun Kharpal@ARJUNKHARPAL
SHAREShare Article via FacebookShare Article via TwitterShare Article via LinkedInShare Article via Email
KEY POINTS
Follow your favorite stocksCREATE FREE ACCOUNT
TSMC displayed on a phone screen and microchip and are seen in this illustration photo taken in Krakow, Poland on July 19, 2023
Jakub Porzycki | Nurphoto | Getty Images
Taiwan Semiconductor Manufacturing Co. (TSMC), posted a surge in monthly revenue in March, as it cashed in on a continuing artificial intelligence boom powered by high-end chips.
TSMC said March revenue came in at 195.2 billion new Taiwan dollars ($6.1 billion), up 34.3% year-on-year — marking the fastest pace of growth since November 2022.
The company’s first-quarter revenue totaled 592.6 billion new Taiwan dollars, up 16.5% year-on-year.
TSMC is the world’s largest contract semiconductor manufacturer, which makes chips for companies from Apple to Nvidia.
The company is currently riding the AI boom. Semiconductors, such as those designed by Nvidia, have underpinned the development of AI applications.
Competition has been rising in the market. AMD launched a rival chip to Nvidia last year, while Intel on Tuesday took the wraps off its latest AI offering.
A number of startups are also developing AI chips, which TSMC manufactures for some companies.
TSMC shares are up just under 40% this year to date, as investors bet on the continued demand for AI chips.
In January, the company said that its AI revenue is growing 50% on an annual basis. Analysts expect TSMC to post a 23.7% rise in total revenue this year, according to LSEG consensus estimates, after a decline in 2023.
Esq.
TSMC kicking goals.
TECH
TSMC posts fastest monthly revenue growth since 2022 on AI chip boom
PUBLISHED WED, APR 10 20242:51 AM EDTUPDATED 2 HOURS AGO
Arjun Kharpal@ARJUNKHARPAL
SHAREShare Article via FacebookShare Article via TwitterShare Article via LinkedInShare Article via Email
KEY POINTS
- TSMC said March revenue came in at 195.2 billion new Taiwan dollars ($6.1 billion), up 34.3% year-on-year. that’s the fastest pace of growth since Nov. 2022.
- TSMC is the world’s largest contract semiconductor manufacturer. It makes chips for companies from Apple to Nvidia.
- The company is currently riding the AI boom. Semiconductors, such as those designed by Nvidia, have been underpinning the development of AI applications.
Follow your favorite stocksCREATE FREE ACCOUNT
TSMC displayed on a phone screen and microchip and are seen in this illustration photo taken in Krakow, Poland on July 19, 2023
Jakub Porzycki | Nurphoto | Getty Images
Taiwan Semiconductor Manufacturing Co. (TSMC), posted a surge in monthly revenue in March, as it cashed in on a continuing artificial intelligence boom powered by high-end chips.
TSMC said March revenue came in at 195.2 billion new Taiwan dollars ($6.1 billion), up 34.3% year-on-year — marking the fastest pace of growth since November 2022.
The company’s first-quarter revenue totaled 592.6 billion new Taiwan dollars, up 16.5% year-on-year.
TSMC is the world’s largest contract semiconductor manufacturer, which makes chips for companies from Apple to Nvidia.
The company is currently riding the AI boom. Semiconductors, such as those designed by Nvidia, have underpinned the development of AI applications.
Competition has been rising in the market. AMD launched a rival chip to Nvidia last year, while Intel on Tuesday took the wraps off its latest AI offering.
A number of startups are also developing AI chips, which TSMC manufactures for some companies.
TSMC shares are up just under 40% this year to date, as investors bet on the continued demand for AI chips.
In January, the company said that its AI revenue is growing 50% on an annual basis. Analysts expect TSMC to post a 23.7% rise in total revenue this year, according to LSEG consensus estimates, after a decline in 2023.
Esq.
Taproot
Regular
Looks like the world's first neuromorphic edge box sitting on the desk.ISC West is held annually in Las Vegas, it is the largest converged security trade event in USA.
VVDN is there and their area has a huge video screen running and brainchip is up on there under the heading Platform Experience.
The post is on X (twitter) and LinkedIn.
This is a screenshop I grabbed through the video.
View attachment 60654
VVDN Technologies on LinkedIn: #vvdnatiscwest #iscwest2024 #iscwest #lasvegas #securitysurviellance…
We're here and live at ISC West 2024 & all set to connect & innovate! The countdown to ISC West is over and team VVDN is all geared up to showcase the latest…
Attachments
HopalongPetrovski
I'm Spartacus!
I wonder if Coby and Sean wink, sneer or growl at each other in passing?
Similar threads
