alwaysgreen
Top 20
Let's hope we get some sort of announcement this week with some revenue attached before the half yearly drops.
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
chapman89
Founding Member
Luke Winchester has forgotten that just between Renesas and Megachips alone we would have 1%, but no mention of those companies or the fact that Renesas are currently taping out chips containing akida IP.
With the rise of ChatGPT and AI sentiment flying, where does BrainChip fit in? - Stockhead
There's big bucks to be made in the AI space for whoever can reduce processing costs - like BrainChip's Akida chip promises to do.stockhead.com.au
As the say.. matter of opinions but it is always good to see different views.
So yes, he is right in saying whoever can create low power solutions will be very lucrative
Rise from the ashes
Regular
I think this is the first time this company has mentioned "and others" I only recall them ever only mentioning Loihi before
Dozzaman1977
Regular
THIS IS NEW . FROM THE BLOG ON BRN WEBSITE. INTERESTING STUFF!!!!!!!!!!!!!!!!!!!!!!!
FEB 21st 2023
So neuromorphic hardware is exciting! However, it is very difficult to develop and deploy current state-of-the-art solutions onto neuromorphic hardware. It’s also extremely limiting to use existing convolutional neural networks (CNNs) based on these platform models. The difficulty primarily stems from the assumption that neuromorphic hardware is analog, and they only run advanced algorithms with SNNs, which are currently in short supply. Therefore, the production models of today —typically accelerated by traditional Deep Learning Accelerators (DLAs) as a safe path to commercialization—are not supported by neuromorphic hardware. But BrainChip Akida TM is changing the game.
Akida is a fully digital, synthesizable and thus process-independent, and silicon-proven neuromorphic technology. It is designed to be scalable and portable across foundries and architected to be embedded into low-power edge devices. It fully supports acceleration for feed-forward CNNs and accelerates other neural networks like Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs) and more, while providing the efficiency benefits of a neuromorphic design. It removes risks and simplifies.
BrainChip promotes neuromorphic technology with proven silicon, like AKD1000, but also focuses on enabling end users to use the benefits of this technology with little to no knowledge of neuromorphic science. There are three ways to leverage Akida technology (refer to Figure 2) and deploy complex models:
1. Through BrainChip MetaTF™ framework: It is a unique and free robust ML framework that has Python packages for model development and conversion of TensorFlow/Keras models into Akida. It is a framework that is very popular among AI experts and custom developers. Python packages for MetaTF framework are public, and developers can access the framework here: https://doc.brainchipinc.com
2. Through Edge Impulse studio: It is a unique platform that provides end-to-end development and deployment of Machine Learning models on targeted technology with little to no-code AI expertise. Core functions of BrainChip MetaTF framework are embedded into Edge Impulse studio to deploy models onto Akida targeted silicon, such as AKD1000 SoC. To learn more about how to develop using Edge Impulse, click here or visit https://www.edgeimpulse.com
3. Through Solutions Partners of BrainChip such as NVISO: BrainChip has partnered with solutions providers and enabled them to create complex models using MetaTF and build applications for specific and most common AI use cases such as Human Monitoring solutions. This allows for faster time to market solutions using Akida technology. To learn more about BrainChip Solutions Partners, contact us at sales@brainchip.com.
These avenues provide an opportunity to create and develop a functioning model that is suitable for running on Akida technology. The models are converted using MetaTF and are saved into a serialized byte file. These models can be evaluated offline by running simulations using the Software Runtime provided with MetaTF or can be evaluated on AKD1000 mini PCIe development board using Hardware backend as shown in Figure 3a. Once through the evaluation stage, these models can be deployed into production on any target device with Akida technology. Akida Runtime library, which is a low-level library that is OS agnostic, is used to compile the saved model and inference on any target device that has Akida technology. Customers who license Akida technology for their device are able to compile this Akida
Runtime library with any of their application software and host OS, as shown in Figure 3b.
To learn more about how you can harness the power of AI, request a demo or visit BrainChip.com.
Nikunj Kotecha is a Machine Learning Solutions Architect at BrainChip. With many years of experience and a strong programming background, Kotecha brings a passion for AI-driven solutions to the BrainChip team, with a unique eye for data visualization and analysis. He develops neural networks for neuromorphic hardware and event-based processors and optimizes CNN-based networks for conversion to SNN. Nikunj has an MS in Computer Science from Rochester Institute of Technology.
FEB 21st 2023
Developing CNNs for Neuromorphic Hardware
(Been There! Done That!)
By Nikunj Kotecha
Often, we hear that neuromorphic technology is cool, classy, low power, next-gen hardware for AI and the most suitable technology for edge devices. Neuromorphic technology mimics the brain, the most efficient computation engine known, to create a computing and natural learning paradigm for devices. Neuromorphic design is complemented with Spiking Neural Networks (SNNs) which emulate how neurons fire and hence only compute when absolutely necessary. This is unlike today’s “MAC monsters" engines -ones that execute lots of MACs (Multiply Accumulate operations which are the basis of most AI computation) in parallel, many of which often get discarded.So neuromorphic hardware is exciting! However, it is very difficult to develop and deploy current state-of-the-art solutions onto neuromorphic hardware. It’s also extremely limiting to use existing convolutional neural networks (CNNs) based on these platform models. The difficulty primarily stems from the assumption that neuromorphic hardware is analog, and they only run advanced algorithms with SNNs, which are currently in short supply. Therefore, the production models of today —typically accelerated by traditional Deep Learning Accelerators (DLAs) as a safe path to commercialization—are not supported by neuromorphic hardware. But BrainChip Akida TM is changing the game.
Akida is a fully digital, synthesizable and thus process-independent, and silicon-proven neuromorphic technology. It is designed to be scalable and portable across foundries and architected to be embedded into low-power edge devices. It fully supports acceleration for feed-forward CNNs and accelerates other neural networks like Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs) and more, while providing the efficiency benefits of a neuromorphic design. It removes risks and simplifies.
Figure 1. Akida Tech Foundations. Fundamentally different and extremely efficient.
At BrainChip, our mission is to Unlock the future of AI. We believe we can do this by enabling Edge devices with Akida, next-generation technology to advance the growth and smartness of these devices and ultimately provide end users with a sense of privacy and security, energy and cost savings while having access to new features. We realize to achieve our mission, we must make it easy for our end users (who may be experts or non-experts in the field of AI) to use our technology and support current solutions. BrainChip provides development boards of their reference chip AKD1000 for anybody in the community to use and build prototype modules. For commercial use, BrainChip provides licenses of the technology to get it integrated into a custom ASIC, board, or a module that can be used in millions of edge devices.BrainChip promotes neuromorphic technology with proven silicon, like AKD1000, but also focuses on enabling end users to use the benefits of this technology with little to no knowledge of neuromorphic science. There are three ways to leverage Akida technology (refer to Figure 2) and deploy complex models:
Figure 2. BrainChip development ecosystem and access to deployment of solutions to Akida technology
1. Through BrainChip MetaTF™ framework: It is a unique and free robust ML framework that has Python packages for model development and conversion of TensorFlow/Keras models into Akida. It is a framework that is very popular among AI experts and custom developers. Python packages for MetaTF framework are public, and developers can access the framework here: https://doc.brainchipinc.com
2. Through Edge Impulse studio: It is a unique platform that provides end-to-end development and deployment of Machine Learning models on targeted technology with little to no-code AI expertise. Core functions of BrainChip MetaTF framework are embedded into Edge Impulse studio to deploy models onto Akida targeted silicon, such as AKD1000 SoC. To learn more about how to develop using Edge Impulse, click here or visit https://www.edgeimpulse.com
3. Through Solutions Partners of BrainChip such as NVISO: BrainChip has partnered with solutions providers and enabled them to create complex models using MetaTF and build applications for specific and most common AI use cases such as Human Monitoring solutions. This allows for faster time to market solutions using Akida technology. To learn more about BrainChip Solutions Partners, contact us at sales@brainchip.com.
These avenues provide an opportunity to create and develop a functioning model that is suitable for running on Akida technology. The models are converted using MetaTF and are saved into a serialized byte file. These models can be evaluated offline by running simulations using the Software Runtime provided with MetaTF or can be evaluated on AKD1000 mini PCIe development board using Hardware backend as shown in Figure 3a. Once through the evaluation stage, these models can be deployed into production on any target device with Akida technology. Akida Runtime library, which is a low-level library that is OS agnostic, is used to compile the saved model and inference on any target device that has Akida technology. Customers who license Akida technology for their device are able to compile this Akida
Runtime library with any of their application software and host OS, as shown in Figure 3b.
Figure 3a. Using MetaTF Software backend for simulations and Hardware backend for model deployment on AKD1000 mini PCIe development board
Figure 3b. Using low-level Akida Runtime Library for production deployment of models in target devices with Akida technology
BrainChip is very excited about the ecosystem that is available for our end users to use, develop, and deploy complex AI models on Akida neuromorphic technology. Expert AI developers who are familiar with CNN architectures can use BrainChip MetaTF framework to deploy familiar models on Akida. Developers with little to no code experience can use Edge Impulse studio to deploy models on Akida technology and users who want faster time to market can work with Solutions Partners such as NVISO.To learn more about how you can harness the power of AI, request a demo or visit BrainChip.com.
Nikunj Kotecha is a Machine Learning Solutions Architect at BrainChip. With many years of experience and a strong programming background, Kotecha brings a passion for AI-driven solutions to the BrainChip team, with a unique eye for data visualization and analysis. He develops neural networks for neuromorphic hardware and event-based processors and optimizes CNN-based networks for conversion to SNN. Nikunj has an MS in Computer Science from Rochester Institute of Technology.
Last edited:
alwaysgreen
Top 20
There won't be any surprises ie meaningful revenue.
We've signed no licenses.
Licenses through a third party will only bare fruit once products are released and royalties roll in.
Last edited:
Techinvestor17
Regular
I don’t this contains AKIDA. They are “shipping” models, ie the software. More digging on their website also shows that their vision model is a DNN.
Evermont
Stealth Mode
Mercedes-Benz Media
Exklusive Einblicke und individuelle Angebote: Erleben Sie mit Mercedes-Benz das Maximum aus digitaler Live-PR. Exclusive insights and individual offers: Experience the maximum of digital live PR with Mercedes-Benz.media.mercedes-benz.com
Great pick-up @Vanman1100
Operating System strategy update coming from MB in less than a day. Might be interesting.
Mercedes-Benz Media
Exklusive Einblicke und individuelle Angebote: Erleben Sie mit Mercedes-Benz das Maximum aus digitaler Live-PR. Exclusive insights and individual offers: Experience the maximum of digital live PR with Mercedes-Benz.
jtardif999
Regular
Peter also talked a little about the 1500 architecture whereby he described an SNN core surrounded by a CNN wrapper (or CNN higher layers). I don’t remember AKD1000 being described this way? Could it be that in AKD1500 the CNN2SNN structure has been remodelled?
KMuzza
Mad Scientist
Hi Damo-With the rise of ChatGPT and AI sentiment flying, where does BrainChip fit in? - Stockhead
There's big bucks to be made in the AI space for whoever can reduce processing costs - like BrainChip's Akida chip promises to do.
As the say.. matter of opinions but it is always good to see different views.
Yes - the article is at least giving Brainchip and AKIDA 1500 some exposure,- BUT - not that i expect it as they are WANCA's that need to also learn about -the JAST SYSTEM and the PATENTS that protect Brainchip.
i reckon the PATENTS are the reason why after throwing so many dollars into Research - we are now "working " in "partnership" with the likes of INTEL - and others .
SO on a lighter note- give him time and we might be able to say-
BY JOVE-I THINK HE'S GOT IT - the rain in Spain fall mainly on the Plane - (type of visual giffy. from My Fair Lady)
AKIDA BALLISTA UBQTS.
jtardif999
Regular
Licences through a third party via Megachips will show as revenue in the annual report.
alwaysgreen
Top 20
Will it?
My understanding is that even if a licence is through a third party, we would still be obligated to disclose it to the ASX as a price sensitive announcement?
Happy to be corrected if I am wrong.
Rise from the ashes
Regular
Now that's a good supposedly easy question to get answered from BRN seen this one pop up a few times . Would be nice to just get that sorted with a quick email. Anyone up for it?
We have a new technology that can turn a dumb sensor into a device that can make perceptions.
We have a high profile in the industry.
Yet the company is running on radio silence.
How to explain this? (an event camera looking at our company would say nothing).
Either something very big is about to drop or we have no prospects at all in the near future.
We have a high profile in the industry.
Yet the company is running on radio silence.
How to explain this? (an event camera looking at our company would say nothing).
Either something very big is about to drop or we have no prospects at all in the near future.
supersonic001
Regular
Great blog by our very own Nikunj Kotecha - Developing CNNs for Neuromorphic Hardware | BrainChip
Great blog by our very own Nikunj Kotecha - Developing CNNs for Neuromorphic Hardware (Been There! Done That!) - Check out the blog here: https://lnkd.in/gT-f-6_f #neuromorphic #AI
buena suerte :-)
BOB Bank of Brainchip
(A)Either something very big is about to drop .......... (B)
I'll go with option (A)
HopalongPetrovski
I'm Spartacus!
I have always found both Fact Finder and Bacon Lover to be honest and intelligent contributors here who bring great value with their insight, experience and wisdom.
I have also found them to be both champions and advocates of Brainchip.
I am hopeful that they can be reconciled as we are stronger together than divided.
I find suppositions on their respective motives dubious themselves and wonder at the motivations of those posters.
Shit stirring is a favourite Australian pastime, but sometimes its less than helpful, particularly when already under duress.
I would ask all to double check their sources before posting accusations as it can be easy to be carried away on flights of fancy.
This place has been a good mutual resource and refuge from the divisive model promoted and encouraged over on the crapper.
Let's not let this place become contaminated with the same vibe.
GLTAH
I have also found them to be both champions and advocates of Brainchip.
I am hopeful that they can be reconciled as we are stronger together than divided.
I find suppositions on their respective motives dubious themselves and wonder at the motivations of those posters.
Shit stirring is a favourite Australian pastime, but sometimes its less than helpful, particularly when already under duress.
I would ask all to double check their sources before posting accusations as it can be easy to be carried away on flights of fancy.
This place has been a good mutual resource and refuge from the divisive model promoted and encouraged over on the crapper.
Let's not let this place become contaminated with the same vibe.
GLTAH
I believe that Mercedes is having an event tomorrow about the new MB.os.(A)Either something very big is about to drop .......... (B)or we have no prospects at all in the near future.
I'll go with option (A)
buena suerte :-)
BOB Bank of Brainchip
Hi Glen... do you have any more info on the event? thanks
ndefries
Regular
If someone uses BRN IP through a relationship with MegaChip we would not need to disclose that. BRN may not be aware of it till further down the product development lifecycle based on NDA with MegaChip and their client.
We have an agreement we have annouced to the market with MegaChip and that comes with (not seen by us) commercial terms for royalty as events trigger these payment. As shareholders unless a client shares this information we just need to look at the financials.
so yes the upcoming report could well have surprises but i dont have expectations here in this report.
I do keep coming back to PVDM comments around MegaChip. That the deal is transformational for BRN and the market does not as yet understand this. i have to think he knows and thinks before making such a statement. For example if he had a very good inclination that this would lead to BRN IP being in every future nintendo device in several years this is exactly what i would say to share my enthusiam with the restrictions of not being able to say everything i wanted to say.
What we do know is that MegaChip is pivoting their business to edge AI capabilities and have chosen BRN as their main technology in working with their customers to being new advanced products to market. https://www.theregister.com/2022/04/26/megachips_ai_partner_program/
Similar threads
