BRN Discussion Ongoing

[Foxdog]

A lazy million shares picked up at 4.47pm…

Congrats

 

[Damo4]

Great contribution you useless twat

View attachment 44196

Great post

 

[DK6161]

View attachment 44196

Great post

Not sure if that was a dig at me, but I will let that one pass through to the keeper. Patience is always needed around here

 

[Cartagena]

Nothing we didn't really know about but PR just the same.

Next phase for neuromorphic IP - News

Our selection of industry specific magazines cover a large range of topics.

siliconsemiconductor.net

Next phase for neuromorphic IP​

Wednesday 6th September 2023

BrainChip Holdings has received its first shipment of AKD1500 chips in silicon from GlobalFoundries to advance the company’s IP into the next phase of development.

Leveraging GlobalFoundries’ advanced 22nm fully depleted silicon-on-insulator (FD-SOI) 22FDX® technology, the AKD1500 is fully functional at first silicon and furthers the growth of neuromorphic computing at the edge and highlights the portability of BrainChip’s Akida™ architecture. This has been made possible by the close partnership with GlobalFoundries and their streamlined engagement processes and reflects the maturity and the ease of using the GF 22FDX processes.

The AKD1500 demonstrates the benefits of Akida’s pure digital, extremely energy-efficient, event-based AI computation for at-sensor or sensor-balanced solutions for AIoT, industrial and consumer markets. Matched with GlobalFoundries’ proprietary FDX™ process technology platform, AKD1500 delivers cost-effective performance for connected and low-power embedded applications and makes it an ideal option for prototyping and proof-of-concept engagements as well as module development and deployment.

“GlobalFoundries is at the forefront enabling the innovation of AI at the edge. Our 22nm FDX technology is ideally suited for extremely low power, low leakage applications at sensor and intelligent edge computing,” said Mike Hogan, Chief Business Unit Officer at GlobalFoundries. “Partnering with trendsetters like BrainChip will drive the future of intelligent computing utilizing GlobalFoundries’ technology offerings.”

“This is the latest milestone in BrainChip’s continued focus on execution to simplify the integration and proliferation of neuromorphic technology for scaling AIoT,” said Sean Hehir, Chief Executive Officer at BrainChip. “The AKD1500 in the GlobalFoundries’ process demonstrates the synergy of our digital IP with the low leakage 22nm FDX process for compelling edge AI devices and we look forward to more partners integrating Akida IP into their innovative AI applications.”

Along with the delivery of chips in silicon, BrainChip will be offering AKD1500 development boards in the following quarters as it continues to build out its product portfolio. To request a demonstration of the technology and be notified when the development boards are available, interested parties can visit https://brainchip.com/contact/.

1. Srila LaRochelle celebrates this
   
   Arm
   407,563 followers
   4mo
   
   Today we are pleased to announce a multi-year agreement with Intel Foundry Services, allowing chip designers to build low-power compute systems-on-chips on Intel 18A process technology, which delivers improved power and performance. Our collaboration with Intel Corporation enables IFS as a critical foundry partner for our customers as we deliver the next generation of world-class products built #onArm. https://bit.ly/3KwjxVd
   …more
   
   

   Intel Foundry and Arm Announce Multigeneration Collaboration on Leading-Edge SoC Design​

   arm.com​

   
   2,387

Srila LaRochelle​

Vice President, North America Business Development, Intel CorporationFlorida Institute of Technology Intel CorporationSanta Clara, California, United States 500+ connections
FollowMessage

Such a strong partnership only means a positive thing for Brainchip that partners with both Intel and ARM.

Intel and ARM announce multigeneration collaboration on" leading edge SoC design"

 

[Damo4]

They other guy posting his opinion and all bin boy can come up with us a trolling postt which is 95 percent of his responses to posts big difference
He's is mentally retardead or just a pure wanker
Actually that would be insulting mentally challenged people so I'll go with wanker

Brother, if you want to be reported so your account is deleted its not going to work.

 

[Rise from the ashes]

Brother, if you want to be reported so your account is deleted its not going to work.

Just stating my opinion of the content of his posting.. I'm waiting on zee to delete my account
Why heck can't people just be nice here

 

[Foxdog]

Just stating my opinion of the content of his posting.. I'm waiting on zee to delete my account
Why heck can't people just be nice here

Correct Rise, unfortunately TSEx has become very much like the Crapper. Quality posts are few and far between. If only we had an option to converse on a platform that required an invite, you know like a vetting process to weed out the trolls and, wait a minute.......

 

[Makeme 2020]

View attachment 44196

Great post

FAMOUS BURNING BIN BOY.
LOVE YOUR PICTURES.

 

[Bravo]

I'm sorely tempted to apply for this position but I can't leave Australia because of my cat and my partner. Also I'm not a Software Engineer which may be problematic.

Machine Learning Software Engineer - Tools in Cambridge at Arm

Learn more about and apply for the Machine Learning Software Engineer - Tools job in Cambridge at Arm

careers.arm.com

 

[Cartagena]

Just stating my opinion of the content of his posting.. I'm waiting on zee to delete my account
Why heck can't people just be nice here

Don't leave us amigo. Only known you a short time here but your content, passion about the company and great contributions are very valuable and appreciated. Like the saying goes if you ain't got anything nice to say, don't say it at all peace and Brainchip will rule the AI world. Soon.

 

[Bravo]

I think this research abstract is really interesting when you consider that BrainChip has successfully integrated Akida with Arm Cortex-M85.

A Brief Review of Deep Neural Network Implementations for ARM Cortex-M Processor - August 2022​

https://www.researchgate.net/publication/362700811_A_Brief_Review_of_Deep_Neural_Network_Implementations_for_ARM_Cortex-M_Processor

 

[Earlyrelease]

Just posing a question for those with more experience. Should Intel have adopted Akida (big if) would it not be that at our current share price and our obvious superiority (if they adopt we must be extremely capable) they for such a huge company, would be crazy to not have bought us out before releasing what’s in their new chip.
So I am thinking purely on a logical business brain we arnt but what are they then releasing and is it cute language and still inferior to what we could offer.

 

[Rise from the ashes]

Don't leave us amigo. Only known you a short time here but your content, passion about the company and great contributions are very valuable and appreciated. Like the saying goes if you ain't got anything nice to say, don't say it at all peace and Brainchip will rule the AI world. Soon.

Thank you for your kinds word Cartagena
That miscreant has ruined this place single handedly he's driven several excellent contributors away from this site.from his childish trollish behavior. Truly a waste of pixels on a screen.
And in the short time you have been here has been very educational and enlightening another great asset to this forum you are and I've appreciated every post you have graced us with it's a pleasure to read your posts and you have such a wonderful demeanour. Here in the main thread and in dm's.
You are a kind hearted person with a lot to give. And I thank you for being such a wonderful person who must have been brought up with ideals of respect and understanding and thoughtfulness.

 

[Cartagena]

Thank you for your kinds word Cartagena
That miscreant has ruined this place single handedly he's driven several excellent contributors away from this site.from his childish trollish behavior. Truly a waste of pixels on a screen.
And in the short time you have been here has been very educational and enlightening another great asset to this forum you are and I've appreciated ever post you have graced us with it's a pleasure to read your posts and you have such a wonderful demeanour. Here in the main thread and in dm's.
You are a kind hearted person with a lot to give. And I thank you for being such a wonderful person who must have been brought up with ideas of respect and understanding and thoughtfulness.

I'm really humbled by that.. thank you amigo. My parents brought me up to appreciate and respect people, and it's just easier to be kind than not. I'm glad to contribute anything of substance, we all here for one purpose and that is the sharing of quality research and knowledge. I'm sure we will talk on and off this forum and maybe at the BRN $3 party in Cartagena or Barbados Salute...

 

[DingoBorat]

Just posing a question for those with more experience. Should Intel have adopted Akida (big if) would it not be that at our current share price and our obvious superiority (if they adopt we must be extremely capable) they for such a huge company, would be crazy to not have bought us out before releasing what’s in their new chip.
So I am thinking purely on a logical business brain we arnt but what are they then releasing and is it cute language and still inferior to what we could offer.

There was a time when Brainchip wanted to be bought out.

It was actually in Louis DiNardo's original job description, before he was hired as CEO, to lead the Company to first significant sales, or buyout.

Things have changed.

I don't think the Company wants to be bought out any longer, probably for quite a time now and it would absolutely be up to the Company, whether to entertain such an offer.

They know the potential value of Brainchip and you couldn't just put an offer on the table, at current valuation.

That's my opinion anyway..

And remember, Intel are actually a bit scroogy with their offers..

Intel's Attempt to Acquire SiFive for $2 Billion Fell Apart, Report Claims

$2 billion is not enough.

www.tomshardware.com

They tried to buy out SiFive for 2 billion US and they told them to stick it..

 

[Fullmoonfever]

I see Booze Allen Hamilton seem to think there is something on neuromorphic

Heather Via
Associate at Booz Allen Hamilton
1mo

In comparison to the brain, with artificial intelligence, there is no awareness, just computation. Machine learning is a subset of AI which uses algorithms and data sets to simulate human intelligence. In 2021, investment in AI reached $93.5 billion... and this trend will only continue to grow. Seek out opportunities to explore AI, machine learning and neuromorphic processing now - failing to do so inevitably means falling behind.


Booz Allen Hamilton
626,929 followers
1mo
There are three questions #AI leaders should consider when thinking about the future of AI ethics. Here they are: https://lnkd.in/egkJMUa2

 

[Frangipani]

Nandan Nayampally will be one of the speakers at tinyML Asia 2023 in Seoul:

Thursday November 16, 2023
9:00 am to 9:15 am

Opening / Welcome​

9:15 am to 10:00 am

Keynote - TBA​

10:00 am to 10:20 am

Solutions and Applications​

Brainchip’s Specialized Akida Architecture for Low Power Edge Inference with HW Spatiotemporal Acceleration and On-chip Learning​

​

Nandan NAYAMPALLY, CMO, Brainchip
Abstract (English)

Brainchip’s Innovative Akida v2.0 Architecture​

• Event-based, neuromorphic processing
• Extremely efficient computation only processes and communicates on events resulting in minimal latency and power consumption. Hardware accelerates event domain convolutions, temporal convolutions, and vision transformers while consuming very low power for battery-operated devices.
• At-memory compute
• Low-latency and low-power computation via parallel execution of events propagating through a mesh-connected array of Neural Processing Units (NPUs) each with a dedicated SRAM memory.
• Quantized parameters and activations
• Supports 8, 4, 2, 1-bit parameters and activations on layer-by-layer basis for model implementations tailored for optimum accuracy versus size, power, and latency.
• Accelerates Traditional AI models
• The MetaTF software stack quantizes and converts models in Keras/TensorFlow and Pytorch/ONNX to Akida event-driven models.
• Fully-digital Implementation
• Portable across process technology with standard synthesis design flow.
• Plus Novel Architectural Features below …

Select Architectural Highlights​

• Temporal Event-based Neural Networks (TENNs)
• Radically reduces number of parameters and operations by an order of magnitude or more for spatiotemporal computations with 2D streaming input such as video and 1D streaming input such as raw audio. Easily trained with back propagation like a CNN and inferences like a RNN. Extracts 2D spatial and temporal 1D kernels for 3D input and extracts temporal 1D kernels for 1D input.
• Vision Transformers (ViTs)
• Multi-head attention included in hardware implementation of Transformer Encoder block with configurations from 2 to 12 nodes. A two-node configuration at 800 MHz executes TinyViT at 30 fps (224x224x3).
• On-device learning

Brainchip’s patented algorithm for homeostatic Spike Time Dependent Plasticity (STDP) enables on-device learning. AI applications can implement incremental learning so that models can adapt to changes in the field. On-device learning can add new classes to a model while leveraging features learned in its original, off-line training.

Model Development Methodologies​

• No-code Model Development and Deployment with Edge Impulse Users with limited AI expertise can develop and deploy optimized Akida models.
• Build-Your-Own-Model with Brainchip’s MetaTF Experienced AI users can build and optimize custom Akida models.

Results​

• Video Benchmarks
• Audio and Medical Vital Signs Benchmarks
• Image Benchmarks

 

[charles2]

Nandan Nayampally will be one of the speakers at tinyML Asia 2023 in Seoul:


View attachment 44221

Thursday November 16, 2023
9:00 am to 9:15 am

Opening / Welcome​

9:15 am to 10:00 am

Keynote - TBA​

10:00 am to 10:20 am

Solutions and Applications​

Brainchip’s Specialized Akida Architecture for Low Power Edge Inference with HW Spatiotemporal Acceleration and On-chip Learning​

​

Nandan NAYAMPALLY, CMO, Brainchip
Abstract (English)

Brainchip’s Innovative Akida v2.0 Architecture​

• Event-based, neuromorphic processing
• Extremely efficient computation only processes and communicates on events resulting in minimal latency and power consumption. Hardware accelerates event domain convolutions, temporal convolutions, and vision transformers while consuming very low power for battery-operated devices.
• At-memory compute
• Low-latency and low-power computation via parallel execution of events propagating through a mesh-connected array of Neural Processing Units (NPUs) each with a dedicated SRAM memory.
• Quantized parameters and activations
• Supports 8, 4, 2, 1-bit parameters and activations on layer-by-layer basis for model implementations tailored for optimum accuracy versus size, power, and latency.
• Accelerates Traditional AI models
• The MetaTF software stack quantizes and converts models in Keras/TensorFlow and Pytorch/ONNX to Akida event-driven models.
• Fully-digital Implementation
• Portable across process technology with standard synthesis design flow.
• Plus Novel Architectural Features below …

Select Architectural Highlights​

• Temporal Event-based Neural Networks (TENNs)
• Radically reduces number of parameters and operations by an order of magnitude or more for spatiotemporal computations with 2D streaming input such as video and 1D streaming input such as raw audio. Easily trained with back propagation like a CNN and inferences like a RNN. Extracts 2D spatial and temporal 1D kernels for 3D input and extracts temporal 1D kernels for 1D input.
• Vision Transformers (ViTs)
• Multi-head attention included in hardware implementation of Transformer Encoder block with configurations from 2 to 12 nodes. A two-node configuration at 800 MHz executes TinyViT at 30 fps (224x224x3).
• On-device learning

Brainchip’s patented algorithm for homeostatic Spike Time Dependent Plasticity (STDP) enables on-device learning. AI applications can implement incremental learning so that models can adapt to changes in the field. On-device learning can add new classes to a model while leveraging features learned in its original, off-line training.

Model Development Methodologies​

• No-code Model Development and Deployment with Edge Impulse Users with limited AI expertise can develop and deploy optimized Akida models.
• Build-Your-Own-Model with Brainchip’s MetaTF Experienced AI users can build and optimize custom Akida models.

Results​

• Video Benchmarks
• Audio and Medical Vital Signs Benchmarks
• Image Benchmarks

And this presumably after the ARM IPO.

Emphasis on this: (Availability of v2.0)

Brainchip’s Innovative Akida v2.0 Architecture​

 

[Frangipani]

According to Google, it looks as if the below update was uploaded to the Brainchip website two days ago.
Can’t be long now until Akida 2.0 will become generally available (plus there are only three weeks left in Q3/2023 ):

Overview — Akida Examples documentation

doc.brainchipinc.com

Upgrading to Akida 2.0 — Akida Examples documentation

doc.brainchipinc.com