BRN Discussion Ongoing

Frangipani

Regular
Researchers at UC Irvine’s Cognitive Anteater Robotics Laboratory (CARL), led by Jeffrey Krichmar, have been experimenting with AKD1000:








View attachment 67694


View attachment 67690


View attachment 67691

View attachment 67692


View attachment 67693



View attachment 67695






CE7AB531-9636-4F97-AE43-189FA9279C0D.jpeg


This is the paper I linked in my previous post, co-authored by Lars Niedermeier, a Zurich-based IT consultant, and the above-mentioned Jeff Krichmar from UC Irvine.


D99716FD-B259-443D-BF0B-F93288698EF1.jpeg


The two of them co-authored three papers in recent years, including one in 2022 with another UC Irvine professor and member of the CARL team, Nikil Dutt (https://ics.uci.edu/~dutt/) as well as Anup Das from Drexel University, whose endorsement of Akida is quoted on the BrainChip website:

F59D0CEB-A967-430B-B4BA-C5C50BD6DCFF.jpeg



7D165A19-60AB-4867-AE8A-2B99B494341D.jpeg





6EBD13C0-4F42-48E8-A9F5-DE58F4D8C22D.jpeg


Lars Niedermeier’s and Jeff Krichmar’s April 2024 publication on CARLsim++ (which does not mention Akida) ends with the following conclusion and the acknowledgement that their work was supported by the Air Force Office of Scientific Research - the funding has been going on at least since 2022 -



and a UCI Beall Applied Innovation Proof of Product Award (https://innovation.uci.edu/pop/)

and they also thank the regional NSF I-Corps (= Innovation Corps) for valuable insights.

08CDD00C-9445-429B-8D25-46652068F45B.jpeg




BD1853A6-48C6-41B3-A2B9-20F2732FF0AC.jpeg



Their use of an E-Puck robot (https://en.m.wikipedia.org/wiki/E-puck_mobile_robot) for their work reminded me of our CTO’s address at the AGM in May, during which he envisioned the following object (from 22:44 min):

“Imagine a compact device similar in size to a hockey puck that combines speech recognition, LLMs and an intelligent agent capable of controlling your home’s lighting, assisting with home repairs and much more. All without needing constant connectivity or having to worry about privacy and security concerns, a major barrier to adaptation, particularly in industrial settings.”

Possibly something in the works here?

The version the two authors were envisioning in their April 2024 paper is, however, conceptualised as being available as a cloud service:

“We plan a hybrid approach to large language models available as cloud service for processing of voice and text to speech.”


The authors gave a tutorial on CARLsim++ at NICE 2024, where our CTO Tony Lewis was also presenting. Maybe they had a fruitful discussion at that conference in La Jolla, which resulted in UC Irvine’s Cognitive Anteater Robotics Laboratory (CARL) team experimenting with AKD1000, as evidenced in the video uploaded a couple of hours ago that I shared in my previous post?





9DFCFFE4-CE8E-4C4A-B868-159E80917E23.jpeg




F077D344-7BC1-4C01-9A15-90BE02FB7F07.jpeg
 

Attachments

  • 7B351CDB-BC9C-4750-AA6A-1E383954F692.jpeg
    7B351CDB-BC9C-4750-AA6A-1E383954F692.jpeg
    393.5 KB · Views: 29
Last edited:
  • Like
  • Love
  • Fire
Reactions: 31 users

Frangipani

Regular

View attachment 67696

This is the paper I linked in my previous post, co-authored by Lars Niedermeier, a Zurich-based IT consultant, and the above-mentioned Jeff Krichmar from UC Irvine.


View attachment 67703

The two of them co-authored three papers in recent years, including one in 2022 with another UC Irvine professor and member of the CARL team, Nikil Dutt (https://ics.uci.edu/~dutt/) as well as Anup Das from Drexel University, whose endorsement of Akida is quoted on the BrainChip website:

View attachment 67702


View attachment 67700




View attachment 67701

Lars Niedermeier’s and Jeff Krichmar’s April 2024 publication on CARLsim++ (which does not mention Akida) ends with the following conclusion and the acknowledgement that their work was supported by the Air Force Office of Scientific Research - the funding has been going on at least since 2022 -



and a UCI Beall Applied Innovation Proof of Product Award (https://innovation.uci.edu/pop/)

and they also thank the regional NSF I-Corps (= Innovation Corps) for valuable insights.

View attachment 67699



View attachment 67704


Their use of an E-Puck robot (https://en.m.wikipedia.org/wiki/E-puck_mobile_robot) for their work reminded me of our CTO’s address at the AGM in May, during which he envisioned the following object (from 22:44 min):

“Imagine a compact device similar in size to a hockey puck that combines speech recognition, LLMs and an intelligent agent capable of controlling your home’s lighting, assisting with home repairs and much more. All without needing constant connectivity or having to worry about privacy and security concerns, a major barrier to adaptation, particularly in industrial settings.”

Possibly something in the works here?

The version the two authors were envisioning in their April 2024 paper is, however, conceptualised as being available as a cloud service:

“We plan a hybrid approach to large language models available as cloud service for processing of voice and text to speech.”


The authors gave a tutorial on CARLsim++ at NICE 2024, where our CTO Tony Lewis was also presenting. Maybe they had a fruitful discussion at that conference in La Jolla, which resulted in UC Irvine’s Cognitive Anteater Robotics Laboratory (CARL) team experimenting with AKD1000, as evidenced in the video uploaded a couple of hours ago that I shared in my previous post?





View attachment 67705



View attachment 67716


While I was out running errands just now, I recalled that we had some sort of connection to UCI through one of our research scientists - and bingo!

Kristofor Carlson was a postdoc at Jeff Krichmar‘s Cognitive Robotics Lab a decade ago and co-authored a number of research papers with both Jeff Krichmar and Nikil Dutt over the years, the last one published in 2019:

2DF3C75D-EFC2-4A0E-98B2-496BEF8487FC.jpeg


1C119412-21D9-401D-972E-A0F1EA6A09EB.jpeg
 
  • Like
  • Fire
  • Love
Reactions: 33 users

charles2

Regular
  • Like
  • Love
  • Fire
Reactions: 49 users

charles2

Regular
And huge capitulation on NASDAQ for BRCHF.

Over 700k on offer and sizable share dumps as low as 10 cents (US)

Usually capitulation is a good sign.....the weak hands give up at any price.

(He says wistfully).
 
  • Like
  • Wow
  • Fire
Reactions: 11 users

Diogenese

Top 20

Intel Foundry Achieves Major Milestones​

Intel 18A powered on and healthy, on track for next-gen client and server chip production next year.

View attachment 67663

View attachment 67664


BrainChip is an IP Partner of IFS. Worth reading the second link as well.

View attachment 67665



Hi Evermont,

Interesting development.

Could it be that the tapeout of Akida 2 has been delayed so it can be adapted for Intel's 18A process?


https://www.intel.com/content/www/u...ndry-achieves-major-milestones.html#gs.dahsjf

What’s New: Intel today announced that its lead products on Intel 18A, Panther Lake (AI PC client processor) and Clearwater Forest (server processor), are out of the fab and have powered-on and booted operating systems. These milestones were achieved less than two quarters after tape-out, with both products on track to start production in 2025. The company also announced that the first external customer is expected to tape out on Intel 18A in the first half of next year.
...
More on Intel 18A: In July, Intel released the 18A Process Design Kit (PDK) 1.0, design tools that enable foundry customers to harness the capabilities of RibbonFET gate-all-around transistor architecture and PowerVia backside power delivery in their designs on Intel 18A. Electronic design automation (EDA) and intellectual property (IP) partners are updating their offerings to enable customers to begin their final production designs.
...
How Customers are Involved: In gaining access to the Intel 18A PDK 1.0 last month, the company’s EDA and IP partners are updating their tools and design flows to enable external foundry customers to begin their Intel 18A chip designs. This is a critical enabling milestone for Intel’s foundry business.

The "A" in 18A is Angstrom, a measurement unit = 0.1 nm, so 18A = 1.8 nm. At these distances you're starting to get close to where parasitic quantum effects can influence the operation of the transistors, and the impedance of the connecting "wires" becomes a significant source of power loss. I would think that this will need a whole new design system. Intel are using gate-all-around transistors which are very different from our planar CMOS technology - no wonder Anil is retiring!

Akida's SNN sparsity would help overcome the connector wire impedance loss by sending electrical impulses less frequently than MACs.
 
  • Like
  • Fire
  • Love
Reactions: 36 users

CHIPS

Regular
There is new hope on the horizon!




BrainChip Appoints New CMO, Enhances Scientific Advisory Board



Laguna Hills, Calif. – August 7th, 2024BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power, fully digital, event-based, neuromorphic AI, today announced that it has hired Steven Brightfield as its new chief marketing officer and has re-envisioned its Scientific Advisory Board (SAB) by bringing on company founder Peter van der Made, Dr. Jason K. Eshraghian and Dr. André van Schaik.

Brightfield has a depth of tech industry knowledge and experience within the AI semiconductor industry. He previously led marketing at several AI focused technology companies, such as SiMa.ai, X-Silicon and Wave Computing combined with deep experience within the semiconductor sector, including executive leadership positions at LSI Logic, Qualcomm, Zoran and others. One of Brightfield’s first priorities at BrainChip will be to oversee the development of a marketing strategy for the new TENNs product, an advanced, ultra efficient neural network architecture and integrate it into the Akida technology platform.

The Scientific Advisory Board provides independent advice and expert consultation for the executive staff of Brainchip to guide the scientific and technical aspects of the company’s short-and long-term goals. The SAB also reviews and evaluates the research and development programs of BrainChip with respect to quality and scope. The re-envisioned SAB provides new perspectives from key industry leaders in AI with increasing focus under the leadership of Dr. Tony Lewis.

van der Made has been at the forefront of computer innovation for 45 years. One of the founders of BrainChip, he designed the first generations of digital neuromorphic devices on which the Akida™ chip was based. van der Made previously served as chief technology officer for BrainChip until his retirement last year. He remains a member of the company’s board of directors.

Eshraghian is an Assistant Professor with the Department of Electrical and Computer Engineering, University of California, Santa Cruz. He serves as the Secretary of the Neural Systems and Applications Technical Committee. His research interests are in large-scale neuromorphic computing. Dr. Eshraghian is the developer of snnTorch, a widely used Python library with more than 150,000 downloads used to train and model spiking neural networks, and his lab developed several high-profile language models, including SpikeGPT, and the MatMul-
Free LLM.

Van Schaik is a pioneer of the field of neuromorphic engineering. He is a professor of electrical engineering at the Western Sydney University and director of the International Centre for Neuromorphic Systems, also in Australia. His research focuses on neuromorphic engineering and computational neuroscience. Dr. Van Schaik has authored more than 300 publications, invented more than 35 patents and is a founder of four start-up companies: VAST Audio, Personal Audio, Heard Systems and Optera.

“I am pleased to add new team members with the skills, experience and credentials to advance BrainChip’s adoption in the market” said Sean Hehir, BrainChip’s CEO. “Leveraging Steve’s expertise as a technology marketer and expanding our Scientific Advisory Board with some of the keenest minds in the industry, better positions us to achieve our goals. I am eager to work closely with each of them.”
 
  • Like
  • Fire
  • Love
Reactions: 30 users

Diogenese

Top 20
Changes are being made.

Big ones


Hi Charles,

I think our new CMO should invest in a quality pair of garters because he's about to have, or probably already has had, his socks blown off. He will be doing a crash course in digital SNNs.

His earlier foray into AI marketing at Wave Computer* was based on MACs and one of his muses is Yan le Cun who is not a fan of SNNs.

US11227030B2 Matrix multiplication engine using pipelining 20190401

1723053004690.png



a matrix multiplication engine using pipelining are disclosed. A first and a second matrix are obtained for matrix multiplication. A first matrix multiply-accumulate (MAC) unit is configured, where a first matrix element and a second matrix element are presented to the MAC unit on a first cycle. A second MAC unit is configured in pipelined fashion, where the first element of the first matrix and a second element of the second matrix are presented to the second MAC unit on a second cycle, and where a second element of the first matrix and the first element of the second matrix are presented to the first MAC unit on the second cycle. Additional MAC units are further configured within the processor in pipelined fashion. Multiply-accumulate operations are executed in pipelined fashion on each of n MAC units over additional k sets of m cycles.


*WC recently emerged from Chapter 11 bankruptcy.
 
  • Like
  • Love
  • Fire
Reactions: 19 users

Frangipani

Regular
Changes are being made.

Big ones


… and small ones, too:

Merci beaucoup et au revoir, Sébastien Crouzet…

CDC5088E-4773-47C3-8E7D-A699FA5DEEF1.jpeg


07457131-C11A-48CC-BB3B-9691C2D13680.jpeg



… and welcome to another University of Washington summer intern - Justin-Pierre Tremblay!


80A3E829-2450-4C3E-8273-A9C8A630481D.jpeg



B6DB3966-BB83-4926-A39E-E52302A4CEEC.jpeg


FNU Sidharth, a Graduate Student Researcher from the University of Washington in Seattle, will be spending the summer as a Machine Learning Engineering Research Intern at BrainChip:




View attachment 66341

View attachment 66342

View attachment 66344


👆🏻Bingo! 😊 👇🏻

https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-425543

View attachment 66345
View attachment 66346
 
  • Like
  • Fire
  • Love
Reactions: 17 users

Kachoo

Regular
  • Like
Reactions: 2 users

The Pope

Regular
Changes are being made.

Big ones

Read story and also mentions Dr. Van Schaik linked to western Sydney university. About two years ago others suggested on TSE that my comments on there was a solid connection between PVDM and WSU lectures etc were generally silly. One noteable exception was FF who liked my post. I suggest this WSU connection wasn’t hard to find back then including this guy mentioned above and I recall even WSU lectures denying knowledge on BRN tech to another TSE member while attending a presentation at WSU.
Now the connection is officially reestablished between WSU and BRN let’s see what others on TSE find.
Like I said back then I saw a demonstration (by chance) from WSU that appeared to be BRN tech used (2 years ago) and when I asked questions on tech being used the presenters went quiet and I suggest started playing dumb.
Leave it as that and this is my opinion that WSU have known and experimented with BRN tech for a while ( suggest atleast 3yrs or more given the WSU demo I witnessed)

Have a good day and hopefully Sean and Co can market and sell the TENNS technology into products ASAP.

Cheers
The Pope
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 31 users

IloveLamp

Top 20
  • Like
  • Love
  • Thinking
Reactions: 17 users

DK6161

Regular
Good morning fellow chippers!
What a great news to wake up to.
New CMO. Looks like big changes are being made! Great move Sean and co!
OMG how exciting! This will surely work for us👍

Can't help to think that if I recall correctly, our previous CMO Nandan had a lot of experience. He was Ex-ARM and came from Amazon. He was touted as the one we need to drive our product marketing globally through his connections. This was 2 years ago and got a lot of share holders excited. Then he left quietly.

I'd give this new guy 2-3 years top.

GLTAH
Not advice
 
  • Like
Reactions: 1 users

Evermont

Stealth Mode
Hi Evermont,

Interesting development.

Could it be that the tapeout of Akida 2 has been delayed so it can be adapted for Intel's 18A process?


https://www.intel.com/content/www/u...ndry-achieves-major-milestones.html#gs.dahsjf

What’s New: Intel today announced that its lead products on Intel 18A, Panther Lake (AI PC client processor) and Clearwater Forest (server processor), are out of the fab and have powered-on and booted operating systems. These milestones were achieved less than two quarters after tape-out, with both products on track to start production in 2025. The company also announced that the first external customer is expected to tape out on Intel 18A in the first half of next year.
...
More on Intel 18A: In July, Intel released the 18A Process Design Kit (PDK) 1.0, design tools that enable foundry customers to harness the capabilities of RibbonFET gate-all-around transistor architecture and PowerVia backside power delivery in their designs on Intel 18A. Electronic design automation (EDA) and intellectual property (IP) partners are updating their offerings to enable customers to begin their final production designs.
...
How Customers are Involved: In gaining access to the Intel 18A PDK 1.0 last month, the company’s EDA and IP partners are updating their tools and design flows to enable external foundry customers to begin their Intel 18A chip designs. This is a critical enabling milestone for Intel’s foundry business.

The "A" in 18A is Angstrom, a measurement unit = 0.1 nm, so 18A = 1.8 nm. At these distances you're starting to get close to where parasitic quantum effects can influence the operation of the transistors, and the impedance of the connecting "wires" becomes a significant source of power loss. I would think that this will need a whole new design system. Intel are using gate-all-around transistors which are very different from our planar CMOS technology - no wonder Anil is retiring!

Akida's SNN sparsity would help overcome the connector wire impedance loss by sending electrical impulses less frequently than MACs.

Innovation seems to be a key theme Dio.

Efficiency and power handling is what we do well.
 
  • Like
Reactions: 5 users

TECH

Regular
Researchers at UC Irvine’s Cognitive Anteater Robotics Laboratory (CARL), led by Jeffrey Krichmar, have been experimenting with AKD1000:








View attachment 67694


View attachment 67690


View attachment 67691

View attachment 67692


View attachment 67693



View attachment 67695




Nice Post.....AKD 1000 "yet again" doing us all proud !

Without Peters initial brilliance in creating SNAP 64 none of this would have ever been possible.

AKD 1000 "too narrow" I say yes, if you are referring to making our technology offering to a wider customer base, in an attempt to
potentially capture a larger market share at the edge, BUT AKD 1000 was company defining when in it's first wafer run turned out to
be more successful than both Peter and Anil had hoped for.....

LETS NOT FORGET THAT FACT.......God Bless our Founders 💘 Tech (Perth)
 
  • Like
  • Fire
  • Love
Reactions: 22 users

1723074758537.png
 
  • Like
  • Fire
  • Love
Reactions: 9 users

Frangipani

Regular
The two of them co-authored three papers in recent years, including one in 2022 with another UC Irvine professor and member of the CARL team, Nikil Dutt (https://ics.uci.edu/~dutt/) as well as Anup Das from Drexel University, whose endorsement of Akida is quoted on the BrainChip website:

F59D0CEB-A967-430B-B4BA-C5C50BD6DCFF.jpeg


Speaking of Anup Das (and also of Eric Gallo at Accenture Labs):


717964F6-148A-4D04-ADAF-2E8BFEB131A6.jpeg





408B747F-9714-4BE7-B108-AF04509AF466.jpeg
 
  • Like
  • Love
  • Fire
Reactions: 15 users

7für7

Regular
I thought it’s maybe important so I decided to post this to be shore everyone will read this…I hope other will follow my example and do the same

 
  • Like
  • Sad
Reactions: 6 users
Good morning fellow chippers!
What a great news to wake up to.
New CMO. Looks like big changes are being made! Great move Sean and co!
OMG how exciting! This will surely work for us👍

Can't help to think that if I recall correctly, our previous CMO Nandan had a lot of experience. He was Ex-ARM and came from Amazon. He was touted as the one we need to drive our product marketing globally through his connections. This was 2 years ago and got a lot of share holders excited. Then he left quietly.

I'd give this new guy 2-3 years top.

GLTAH
Not advice
1723077261678.gif
 
  • Like
  • Haha
Reactions: 5 users
  • Haha
Reactions: 1 users
Top Bottom