BRN Discussion Ongoing

[Diogenese]

Wait a minute @Dio. ...any ARM CPU ... architecture. Am I supposed to take ARM's statement seriously and it doesn't depend on the 22nm (GF) or any nm at all and that's just the qualification process?

IFS

Hi cosors,

Akida is process-agnostic as well as processor-agnostic.

It can be built in 60 nm or 7 nm or any size between.

It can work with ARM, Intel, Nvidia.

It can work with (almost) any processor because, with Akida 1000, the processor is only required for configuring the NN (layers, NPEs per layer, weights, ...). In Akida 1000, the processor plays no part in the classification function, which makes Akida very fast.

Akida 2 TeNNs does have some minor processor involvement.

 

[Bravo]

UMC will also be at Intel’s IFS Direct Connect Feb 22 where the wondrous and soon to be ubiquitous Akida will be presented to all and sundry.

In January Intel and UMC announced a deal whereby UMC would provide IFS with new capabilities such as RF system solutions and WiFi production technologies.

This would be a fantastic fit for us IMO!!! Remember Intellisense chose us to integrate with their RF system solutions. Here’s an excerpt from the IntelliIsense/ Brachip announcement.

Intellisense’s intelligent radio frequency (RF) system solutions enable wireless devices and platforms to sense and learn the characteristics of the communications environment in real time, providing enhanced communication quality, reliability and security. By integrating BrainChip’s Akida™ neuromorphic processor, Intellisense can deliver even more advanced, yet energy efficient, cognitive capabilities to its RF system.

Oh, yes and here’s the other thing!!! UMC recently spent a huge amount of money building a new fab. Take a look at what it says in this article from Feb 2022.

UMC To Invest $5Bn To Build New 22-nm Chip Fab In Singapore

The new facility would be built next to UMC’s other Singapore 12-inch fab, Fab12i

www.electronicsb2b.com

EXTRACT ONLY

The new fab is backed by clients who have signed multiyear supply agreements to secure capacity from 2024, which points to a robust demand outlook for UMC’s 22-nanometer and 28-nanometer technologies for years to come,” the statement said.

UMC, whose clients include Samsung, MediaTek and Qualcomm, said that the clients are to pay a deposit to secure capacity, a new model implemented last year to cope with supply constraints amid the supply crisis.

Specialty technologies to be manufactured in the new facility — such as embedded high-voltage technology, embedded non-volatile memory, radio frequency silicon-on-insulator technology and mixed signal CMOS — are critical for a broad range of applications, including smartphones, smart home devices and electric vehicle applications, UMC said.

 

[Diogenese]

Obviously I'm not Diogenese ..

But my recollection, is that Peter said AKIDA could go down to 7nm process node.

But I'm guessing that's because, that was the smallest viable process node, at that time?

I'm also guessing, that the "neuron fabric" whatever that actually is, would be the limiting factor..

But since it's a "digital" design, there should be no limits? ...

The new smaller process nodes, are completely different "processes" too..

Yes. Akida can go to 7 nm and probably smaller.

The neuron fabric is the interconnected nodes (4 NPEs per node) and the "switchable" communication network which connects them. The network can be configured to arrange the required number of nodes in each layer. This is all "built" in standard CMOS, so it can be implemented in whatever size CMOS can accommodate without a major redesign of the tape-out. There is nothing stopping it being implemented in FINFET (edge-wise transistors), other than a complete new start-from-scratch tape-out.

 

[McHale]

Another issue with the phalanx is the heat it generates in use; 4500 rounds a minute. Once you’ve used it you have to cool it down which doesn’t bode well with multiple targets inbound.

And also the obvious issue of carrying enough onboard and loading the rounds quick enough during conflict situations.

I thought someone was using camera such as prophesee’s with Akida doing the TOF algorithms plotting trajectories and using a laser to bring down drones. Maybe when I read it it was still a research project but whoever can create it will make a motza; and even better save lives.

If the US doesn't yet have that capability, they will have it soon, they are all out working on laser weapons and sophiticated guidance systems to deploy the lasers.

 

[buena suerte :-)]

Can someone please advise me when the next financial is due by is it this week ?.

This was the release date last year...So by next Thursday I'm thinking!

 

[Esq.111]

Morning McHale ,

Only one week ago or so I read a article on America having successfully shot down a drone with a high energy weapon at over one kilometre away.

The age of laser beams is certainly upon us.

Regards,
Esq.

 

[Xray1]

This was the release date last year...So by next Thursday I'm thinking!

View attachment 57365

I note that Sean H will do his Investor Presentation next Tuesday 27/2/24 .... so I wonder when the Annual Report and 4E will be released on the ASX.... Will it be before or after his Presentation .......... Personally, I think that if the Annual Report contains some positive indicators, then it will most likely be released a few days before his presentation, so as to give him some positive investor sentiment beforehand.

 

[Getupthere]

EdgeCortix flagship SAKURA-I Chip showcased for Edge AI applications — Geeky Gadgets

At the prestigious Singapore Airshow 2024, EdgeCortix, a leading Japanese semiconductor company, is set to unveil a new chip that is expected to transform the way artificial intelligence (AI) is processed in the defense and aerospace sectors. The SAKURA-I chip, a specialized co-processor, is...

apple.news

EdgeCortix flagship SAKURA-I Chip showcased for Edge AI applications​

1:45 pm February 19, 2024 By Julian Horsey

​

At the prestigious Singapore Airshow 2024, EdgeCortix, a leading Japanese semiconductor company, is set to unveil a new chip that is expected to transform the way artificial intelligence (AI) is processed in the defense and aerospace sectors. The SAKURA-I chip, a specialized co-processor, is designed to handle AI tasks right at the edge of the network, where data is generated and collected. This innovation is particularly important for applications that require immediate decision-making, such as those found in aviation and military operations.
The airshow, scheduled for February 20-25, will serve as the platform for EdgeCortix to introduce this new technology to the world. Visitors to the event will be able to see the SAKURA-I chip in action at the booth of the Acquisitions, Technology and Logistics Agency (ATLA), which represents Japan’s commitment to advancing its air and defense technologies.

EdgeCortix SAKURA-I​

The SAKURA-I chip stands out for its ability to process complex AI tasks with high efficiency and low latency. This is crucial in environments where quick responses are essential and power resources are often limited. The chip’s debut is timely, as there is a growing need for technologies that can operate effectively under these constraints.
“EdgeCortix’s SAKURA-I chip, with its small form factor and high efficiency, is proving a crucial tool in edge computing in defense and aerospace sectors, which EdgeCortix predicts will increasingly rely on software-driven hardware solutions to achieve their tasks going forward,” says Sakyasingha Dasgupta, CEO and Founder of EdgeCortix. “We are honored to be featured in ATLA’s booth representing Japanese innovation at the Singapore Airshow and are proud to stand shoulder-to-shoulder with such elite companies at the show.”
AI is becoming increasingly important in enhancing safety and efficiency across various industries, including transportation and defense. The SAKURA-I chip is designed to meet the demanding needs of these sectors, providing performance improvements that can help prevent accidents, optimize logistics, and ensure secure operations in sensitive areas.
Edge computing, which involves processing data close to where it is generated, is changing the landscape of defense and aerospace. Innovations like the SAKURA-I chip are at the forefront of this shift, enabling faster and more reliable decision-making in situations where time is of the essence.
The Singapore Airshow 2024 is more than just an exhibition; it is a demonstration of Japan’s technological advancements in defense equipment and technology. The partnership between ATLA and EdgeCortix highlights the role of collaboration between the public and private sectors in achieving technological breakthroughs. The SAKURA-I chip exemplifies such progress and is expected to establish new standards in the industry.
EdgeCortix’s participation in the Singapore Airshow 2024 emphasizes the company’s position as a leader in semiconductor technology and its significant contributions to the evolution of AI processing. The SAKURA-I chip marks a step towards more energy-efficient, software-driven hardware solutions in the fields of defense and aerospace. Attendees are encouraged to witness this state-of-the-art technology at the ATLA booth, where Japan’s expertise in air and defense technology will be on full display.

 

[Falling Knife]

I note that Sean H will do his Investor Presentation next Tuesday 27/2/24 .... so I wonder when the Annual Report and 4E will be released on the ASX.... Will it be before or after his Presentation .......... Personally, I think that if the Annual Report contains some positive indicators, then it will most likely be released a few days before his presentation, so as to give him some positive investor sentiment beforehand.

They do have an extra day to deliver it this year

 

[IloveLamp]

Morning McHale ,

Only one week ago or so I read a article on America having successfully shot down a drone with a high energy weapon at over one kilometre away.

The age of laser beams is certainly upon us.

Regards,
Esq.

That was u.k defense i believe esky

 

[buena suerte :-)]

I note that Sean H will do his Investor Presentation next Tuesday 27/2/24 .... so I wonder when the Annual Report and 4E will be released on the ASX.... Will it be before or after his Presentation .......... Personally, I think that if the Annual Report contains some positive indicators, then it will most likely be released a few days before his presentation, so as to give him some positive investor sentiment beforehand.

Yep..If anything in the report is 'price sensitive' (The report itself will be PS but any additional info!) I would imagine he would want to let the market know prior so he can openly answer questions! re new partners/deals/financials etc etc) in the presentation.

Good luck
(Buena suerte)

 

[Esq.111]

Afternoon ILoveLamp ,

Maybe......Reasonably certain it was USA.

Regards,
Esq.

 

[buena suerte :-)]

Also look under the coffee table ..... I often find a little cash there.


View attachment 57357


Esq.

I'll have a look in the pool

 

[Esq.111]

Waiting.....waiting.... . .

 

[buena suerte :-)]

Waiting.....waiting.... . . View attachment 57369

 

[Space Cadet]

Morning McHale ,

Only one week ago or so I read a article on America having successfully shot down a drone with a high energy weapon at over one kilometre away.

The age of laser beams is certainly upon us.

Regards,
Esq.

Check out oz company EOS. Very good at this shit.

SC

 

[IloveLamp]

Afternoon ILoveLamp ,

Maybe......Reasonably certain it was USA.

Regards,
Esq.

This is what i was thinking of

Discover thousands of collaborative articles on 2500+ skills

Discover 100 collaborative articles on domains such as Marketing, Public Administration, and Healthcare. Our expertly curated collection combines AI-generated content with insights and advice from industry experts, providing you with unique perspectives and up-to-date information on many skills...

www.linkedin.com

 

[Esq.111]

This is what i was thinking of

Discover thousands of collaborative articles on 2500+ skills

Discover 100 collaborative articles on domains such as Marketing, Public Administration, and Healthcare. Our expertly curated collection combines AI-generated content with insights and advice from industry experts, providing you with unique perspectives and up-to-date information on many skills...

www.linkedin.com

Just had a look for my article on high energy .... could not locate.

Would appear any military with a billion or so in R&D are having a dabble in this field.

Regards,
Esq.

 

[HopalongPetrovski]

Just whilst we are waiting to be BRN millionaires again thought this snippet from ABC radios "the Science Show" was interesting about AI and consciousness.

Is artificial intelligence conscious? - ABC listen

Experts put AI to the test.

www.abc.net.au

 

[DingoBorat]

Hi alby,

There isn't much technical detail available other than Wiki's discussion on Tsetlin machines.

https://en.wikipedia.org/wiki/Tsetlin_machine

View attachment 57363

A Tsetlin machine is a form of learning automaton collective for learning patterns using propositional logic. Ole-Christoffer Granmo created[1] and gave the method its name after Michael Lvovitch Tsetlin, who invented the Tsetlin automaton[2] and worked on Tsetlin automata collectives and games.[3] Collectives of Tsetlin automata were originally constructed, implemented, and studied theoretically by Vadim Stefanuk in 1962.

The Tsetlin machine uses computationally simpler and more efficient primitives compared to more ordinary artificial neural networks.[4]

As of April 2018 it has shown promising results on a number of test sets.[5][6]
...
The Tsetlin automaton is the fundamental learning unit of the Tsetlin machine. It tackles the multi-armed bandit problem, learning the optimal action in an environment from penalties and rewards. Computationally, it can be seen as a finite-state machine (FSM) that changes its states based on the inputs. The FSM will generate its outputs based on the current states.

... which is above my pay grade.


There are no published patents for Literal Lbs.

The LL people did publish a paper in Norway in 2022. The abstract is public:

Resultat #2068852 - A Convolutional Tsetlin Machine-based Field Programmable Gate Array Accelerator for Image Classification - Cristin

Resultat #2068852 - A Convolutional Tsetlin Machine-based Field Programmable Gate Array Accelerator for Image Classification - Cristin

app.cristin.no

Vitenskapelig Kapittel/Artikkel/Konferanseartikkel

2022

A Convolutional Tsetlin Machine-based Field Programmable Gate Array Accelerator for Image Classification​

• Svein Anders Tunheim
• Jiao Lei
• Rishad Ahmed Shafik
• Alexandre Yakovlev og
• Ole-Christoffer Granmo

TITTEL

A Convolutional Tsetlin Machine-based Field Programmable Gate Array Accelerator for Image Classification

SAMMENDRAG

This paper presents a Field Programmable Gate Array (FPGA) implementation of an image classification accelerator based on the Convolutional Tsetlin Machine (CTM). The work is a concept design, and the solution demonstrates recognition of two classes in 4 × 4 images with a 2 × 2 convolution window. More specifically, there are two sub-Tsetlin Machines (TMs), one per class. A single sub-TM employs 40 clauses, each controlled by 20 Tsetlin Automata. The accelerator features random patch selection, in parallel for all clauses, based on reservoir sampling. The design is implemented in a Xilinx Zync XC7Z020 FPGA. With an operating clock speed of 30 MHz, the accelerator is capable of inferring at the rate of 3.3 million images per second with an additional power consumption of 20 mW from idle mode. The average test accuracy is 96.7% when trained on data with 10% noise. A training session with 100 epochs and 8192 examples takes 1.5 seconds. Due to the limited hardware resources required, the CTM accelerator represents a promising concept for online learning in energy-frugal systems. The solution can be scaled to multi-class systems and larger images.




From their website:


Literal Labs - Cambridge Future Tech (camfuturetech.com)

Literal Labs | Cambridge Future Tech | DeepTech Venture Builder

A new world of AI-enabled devices that are 10,000 times more energy efficient.

camfuturetech.com

Artifical Intelligence Redefined

Similar to NNs in that customers train a dataset, Literal Labs trains Tsetlin machine models specific to customer datasets. This approach results in an optimised machine model that is then deployed onto the target hardware.

The Tsetlin machine model can be deployed as software only or can be accelerated using Literal Labs accelerators. Literal Labs benchmarking shows it can achieve 250X faster inferencing than XG Boost using software only, and up to 1,000X faster and up to 10,000X less energy consumption when using hardware acceleration.

Value Proposition

One of the major challenges with traditional neural network-based models is their resource-intensive nature. As models become more complex, so too does the resource requirement. Literal Labs’ architecture, based on propositional logic, requires significantly fewer resources to solve AI problems, meaning that Literal Labs can deliver intelligent compute on devices with minimal energy usage and with little or no internet coverage.

The company was spun out of Newcastle University by world leaders in Tsetlin machine Dr. Alex Yakelov and Dr. Rishad Shafik, and led by former Arm CPU division VP and semiconductor startup founder Noel Hurley.

There is a video which shows that the processor is involved in the calculations:



View attachment 57364


This would add to latency, so it is probably slower than Akida.

No wonder Jem was a bit cryptic on the podcast - buyer's remorse. I think he's Tsetlin for second best.

It sounded like it did have good potential, until you mentioned that the processor involved, would put the hand brake on..

Would it be possible to combine the Tsetlin and AKIDA technologies, getting AKIDA to do the "Heavy Lifting" as you say?..

Or is that a mismatch of technologies, trying to accomplish a similar task?..