BRN Discussion Ongoing

[jtardif999]

I particularly like this claim (I like all the claims), this claim says this patent is Akida2

“[0081] The sound prediction learning rule minimizes or at least reduces the error between a prediction of the upcoming speech sounds generated by the acoustic model 124 (or a prediction of future feature coefficients that will be received by the acoustic model 124 ) and the actual observed speech sounds (or the actual feature coefficients). This can be important as it allows the speech processing engine 120 to operate in a fully self-supervised manner in which only the future speech of the user is needed to adjust the parameters of the acoustic model 124 . In addition, partial predictions can also be used to improve efficiency. For example, predicting the speech sounds of parts of speech while other parts are indecipherable due to background noise or an end of speech event is not detected reduces the latency in providing a response to the user. The sound prediction learning rule can be processed continuously by the neuromorphic processor 123 allowing for real-time and continuous self-learning of the acoustic model 124 . In this example, the acoustic model 124 is configured to output the predicted speech sounds and/or predicted feature coefficients for future utterances that the acoustic model 124 predicts the user to make. The acoustic model 124 can predict future utterances based on the predicted speech sounds. For example, the acoustic model 124 can predict the future utterances based on a probability of the future utterances following the predicted speech sounds output by the acoustic model 124 .”

The acoustic model being mentioned can be in the cloud or on the actual device.

This patent is a significant development in the company’s fortunes imo. Thank you @TECH for the find

 

[Wags]

Nice early find Tech. They haven't published the drawings yet.

Dio, I can see the drawings, ttl 7. Not that they mean anything to me, but I can see them. cheers

 

[Diogenese]

Asking the question as I am definitely not an expert and would genuinely like to know.

Are the figures (Fig 1 to7) considered the drawings or is there more to it? Plus,
Would they not publish the patent without making this available?

View attachment 59825

Yes - they are the titles of the drawings in the description. The drawings are in a separate file under a separate tab. It's just an administrative matter - they put the description and abstract first before posting the drawings as they are separate files. I was just remarking on how soon Tech found the abstract, which happened to be before the drawings were posted.

 

[Flenton]

Redirecting

View attachment 59824

I was only thinking today that I wondered what's happened with Dell......

Episode 6: The Outside Looking in - A Conversation with Rob Lincourt, Dell Technologies

In this episode, we continue with our “outside looking in” theme with this insightful conversation with Rob Lincourt

brainchip.com

 

[TopCat]

Intel CEO Gelsinger proposes a fab tour for Elon Musk — could be an attempt to win orders from Tesla, other Musk companies

CHIP Act funding arrives, hastens the need to get IFS customers lined up.

www.tomshardware.com

Musk would surely be an excellent catch for IFS. This superrich entrepreneur has fingers in many tech pies that are highly reliant on processors, lots of state-of-the-art processors. Musk's firms buy AI accelerators from both AMD and Nvidia, for tasks like machine learning, computer vision, self-driving, Grok, and more, but the firm is also developing its own Dojo ASICs (Application-Specific Integrated-Circuits) with new generations in development.

 

[Smoothsailing]

Intel CEO Gelsinger proposes a fab tour for Elon Musk — could be an attempt to win orders from Tesla, other Musk companies

CHIP Act funding arrives, hastens the need to get IFS customers lined up.

www.tomshardware.com

View attachment 59831

Musk would surely be an excellent catch for IFS. This superrich entrepreneur has fingers in many tech pies that are highly reliant on processors, lots of state-of-the-art processors. Musk's firms buy AI accelerators from both AMD and Nvidia, for tasks like machine learning, computer vision, self-driving, Grok, and more, but the firm is also developing its own Dojo ASICs (Application-Specific Integrated-Circuits) with new generations in development.

I was only thinking today that I wondered what's happened with Dell......

Episode 6: The Outside Looking in - A Conversation with Rob Lincourt, Dell Technologies

In this episode, we continue with our “outside looking in” theme with this insightful conversation with Rob Lincourt

brainchip.com

Rob said ….Dell has a plethora of products on the edge that brainchip could be apart of to reduce power.

 

[Bigal7425]

Pretty cool comment from Apple from the interview linked below. Great to hear that mindset.

Senior Vice President Hardware Technologies of Apple Johnny Srouji made the following comment:

"Our aspiration is the product; we want to build the best products on the planet. As ta technology team, which also includes the chips. in this case, we want to build the best technology that would enable that vision. So, if there is a technology that we can buy off the shelf and that delivers to our objective for the product, we'll do it. Because I want to focus the team on what really, really matters on the most differentiating aspects of the chips. So, if there is a chip that we can buy and there is no differentiation in building internally, I would buy so we can focus our efforts on the things that really matter, and we maximise our benefits".

 

[Smoothsailing]

Pretty cool comment from Apple from the interview linked below. Great to hear that mindset.

Senior Vice President Hardware Technologies of Apple Johnny Srouji made the following comment:

"Our aspiration is the product; we want to build the best products on the planet. As ta technology team, which also includes the chips. in this case, we want to build the best technology that would enable that vision. So, if there is a technology that we can buy off the shelf and that delivers to our objective for the product, we'll do it. Because I want to focus the team on what really, really matters on the most differentiating aspects of the chips. So, if there is a chip that we can buy and there is no differentiation in building internally, I would buy so we can focus our efforts on the things that really matter, and we maximise our benefits".

Can someone send old Johnny boy a brainchip linkden invite maybe.
Wow the opportunity

 

[Diogenese]

Dio, I can see the drawings, ttl 7. Not that they mean anything to me, but I can see them. cheers

Thanks Wags,

It was just a matter of time until they posted the drawings file.

 

[Kozikan]

Yes. Let's not forget that, while the world and his wife are familiar with the use of OpenAi's GPT "X", they do not have a clue as to how it works, let alone the underlying technology. However, we are seeing frequent examples of the tech world's increasing awareness.

One field of tech where Akida's potential is as yet untapped is in the implementation of LLMs.

Sensors (microphones, cameras, ...) and keyboards are essential input devices, and the input signals need to be converted to a format which the system can interpret. This requires the system management processor to be able to interpret natural language. Doing that purely in software burns a lot of electricity. Akida 2 introduces long range skip connexions:

https://brainchip.com/akida-generations/

With the added support for short and long-range skip connections, an akidaTM neural processor can now accelerate complex neural networks such as ResNet completely in hardware without model computations on a host CPU.
Skip connections are implemented by storing data from previous layers in the akidaTM mesh or in a scratchpad memory for combination with data in later layers.

Key Benefits:​

• Complex Network Acceleration: Enables complete hardware execution of non feed-forward model architectures such as ResNet and DenseNet.
• Low Latency: Eliminates CPU interaction during network evaluation which minimizes model latency.

By performing these functions in silicon, Akida reduces both power usage and latency compared with earlier LSTM/Attention software implementations.

Akida 2 provides a much more efficient foundation for implementing LLMs and particularly SLMs (Small Language Models adapted for edge applications). However, for the moment, the cloud-based Chat GPT and its LLMs have the advantage of incumbency despite their unsustainable growth in energy consumption. Nvidia's Jensen Huang is rightfully proud of the 2.5 times improvement in power consumption of Blackwell, but that is not sufficient to mitigate the exponential growth in power consumption to contain it within acceptable limits.

Akida offers orders of magnitude greater improvement, particularly with the use of SLMs at the edge. Akida has the potential to be the foundation stone of all things GPT. The development of SLMs is just some of the lead in Akida's saddlebags.

While Edge GPT is the present Holy Grail, there is a myriad of other applications for Akida which can be implemented in the near term.

ADAS - DMS - UI - lidar/..., space, SDR, Edge Box, ...

For startup companies, the rational basis for assessing share price is the market potential of the product.

The problem is that the share price is the plaything of manipulators who take advantage of the fact that many shareholders and potential shareholders do not fully grasp the potential of this revolutionary technology, and the fact that the pre-income phase has been longer than anyone anticipated. One reason for the delay in revenue is that the technology is evolving at an unprecedented rate, LSTM, Attention, 4-bit weights and actuations, Chat GPT, TeNNs, ViT, ... Remember, Akida 2 is just 1 year old.

Added to that is the fact that the company has made a few mis-steps or changed course over the last few years in an attempt to come to grips with an entirely unheralded market. The company was metaphorically feeling its way in the dark and needed to test the waters to see which way the current flows ... and the current has not flowed smoothly.

So there are a lot of factors to be taken into account which no one could have foreseen a few years ago. This has been a learning experience for the shareholders and the company.

Bravo Here Here

 

[DK6161]

Yes. Let's not forget that, while the world and his wife are familiar with the use of OpenAi's GPT "X", they do not have a clue as to how it works, let alone the underlying technology. However, we are seeing frequent examples of the tech world's increasing awareness.

One field of tech where Akida's potential is as yet untapped is in the implementation of LLMs.

Sensors (microphones, cameras, ...) and keyboards are essential input devices, and the input signals need to be converted to a format which the system can interpret. This requires the system management processor to be able to interpret natural language. Doing that purely in software burns a lot of electricity. Akida 2 introduces long range skip connexions:

https://brainchip.com/akida-generations/

With the added support for short and long-range skip connections, an akidaTM neural processor can now accelerate complex neural networks such as ResNet completely in hardware without model computations on a host CPU.
Skip connections are implemented by storing data from previous layers in the akidaTM mesh or in a scratchpad memory for combination with data in later layers.

Key Benefits:​

• Complex Network Acceleration: Enables complete hardware execution of non feed-forward model architectures such as ResNet and DenseNet.
• Low Latency: Eliminates CPU interaction during network evaluation which minimizes model latency.

By performing these functions in silicon, Akida reduces both power usage and latency compared with earlier LSTM/Attention software implementations.

Akida 2 provides a much more efficient foundation for implementing LLMs and particularly SLMs (Small Language Models adapted for edge applications). However, for the moment, the cloud-based Chat GPT and its LLMs have the advantage of incumbency despite their unsustainable growth in energy consumption. Nvidia's Jensen Huang is rightfully proud of the 2.5 times improvement in power consumption of Blackwell, but that is not sufficient to mitigate the exponential growth in power consumption to contain it within acceptable limits.

Akida offers orders of magnitude greater improvement, particularly with the use of SLMs at the edge. Akida has the potential to be the foundation stone of all things GPT. The development of SLMs is just some of the lead in Akida's saddlebags.

While Edge GPT is the present Holy Grail, there is a myriad of other applications for Akida which can be implemented in the near term.

ADAS - DMS - UI - lidar/..., space, SDR, Edge Box, ...

For startup companies, the rational basis for assessing share price is the market potential of the product.

The problem is that the share price is the plaything of manipulators who take advantage of the fact that many shareholders and potential shareholders do not fully grasp the potential of this revolutionary technology, and the fact that the pre-income phase has been longer than anyone anticipated. One reason for the delay in revenue is that the technology is evolving at an unprecedented rate, LSTM, Attention, 4-bit weights and actuations, Chat GPT, TeNNs, ViT, ... Remember, Akida 2 is just 1 year old.

Added to that is the fact that the company has made a few mis-steps or changed course over the last few years in an attempt to come to grips with an entirely unheralded market. The company was metaphorically feeling its way in the dark and needed to test the waters to see which way the current flows ... and the current has not flowed smoothly.

So there are a lot of factors to be taken into account which no one could have foreseen a few years ago. This has been a learning experience for the shareholders and the company.

Great reminder. Thankyou

 

[Bravo]

Bravo Here Here

Yes, I‘m here.

 

[White Horse]

Hi all,
Some here have found evidence of Ukraine studying our Akida chip.
This youtube video shows how inventive they have become because of the war.
I can see several opportunities for the application of our technology.

 

[Fullmoonfever]

Interesting concept by what appears to be a start up out of Istanbul.

Not dug around much as just saw them on a search.

If I read correct, the offering is to use their MindCraft tool (nice spin on the game MineCraft) that can drop their Artificial Brain model onto a host neuromorphic chip......like ours for one.

Didn't realise Orin was neuromorphic though

Artificial Brain | Artificial Brain Platform

Artificial Brain: Technology that makes machines smarter.

www.confederation.ai

 

[TECH]

Good morning all,

The drawings have now been included with the Accenture Global Solutions Patent Application.

Looks extremely promising, doesn't it....the writings on the wall, Peter, Anil, Tony and all our wonderful team/s globally are heading
to the summit, the buying price of our shares is really unbelievable, opportunities like this may never come by in our lifetime again.

Sorry to keep repeating myself, but I truly love what Brainchip represents...AKIDA FOR PRESIDENT Tech.

Espacenet – search results

Espacenet: free access to millions of patent documents. Find out if your invention is unique or if other inventors have filed patent applications that are considered to be prior art.

worldwide.espacenet.com

 

[Tezza]

Good morning all,

The drawings have now been included with the Accenture Global Solutions Patent Application.

Looks extremely promising, doesn't it....the writings on the wall, Peter, Anil, Tony and all our wonderful team/s globally are heading
to the summit, the buying price of our shares is really unbelievable, opportunities like this may never come by in our lifetime again.

Sorry to keep repeating myself, but I truly love what Brainchip represents...AKIDA FOR PRESIDENT Tech.

Espacenet – search results

Espacenet: free access to millions of patent documents. Find out if your invention is unique or if other inventors have filed patent applications that are considered to be prior art.

worldwide.espacenet.com

Very exciting and opportunistic times. The times may get better after next quarterly report. But this maybe it for these prices.
December 1 2024 is my, check the position I hold day.

 

[AARONASX]

Good morning,

worth a watch.

watch from the start but mark note of comments made at the 8:50 mark...and if integratable with Akida, Akida could be huge!

 

[supersonic001]

Sign Up | LinkedIn

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

www.linkedin.com

 

[IloveLamp]

MediaTek Edge AI

Discover how MediaTek is leading the Generative AI revolution with high-performance AI processors and data center-grade modules. Explore our powerful AI technologies for diverse applications in homes, education, businesses, mobile, and vehicles.

bit.ly

 

[IloveLamp]

Innoviz to develop new lidar platform for next-gen BMW automated vehicles

Innoviz is developing an enhanced solution including the InnovizTwo lidar, a new InnovizCore compute box, and AI-powered software solutions including an industry-first MRM system to enable Level 3 automated driving capabilities to a broader range of future vehicles.

insideautonomousvehicles.com

Redirecting

View attachment 41472




‐--------UNRELATED----------

EVgo and General Motors Open 1,000th DC Fast Charging Stall as Part of Metropolitan Charging Collaboration

EVgo Inc. (NASDAQ: EVGO), one of the nation’s largest public fast charging networks for electric vehicles, and General Motors have surpassed 1,000 fast charging stalls as part of their longstanding collaboration to expand fast charging infrastructure. First announced in 2020 and expanded upon in...

news.gm.com

View attachment 41473

VW is ready to bring autonomous driving to large-scale production

VW is now the first vehicle manufacturer to develop a Level 4 autonomous driving (AD) service vehicle for large-scale production.

electrek.co

VW is ready to bring autonomous driving to large-scale production | Innoviz Technologies

Innoviz is thrilled to be the direct #LiDAR supplier for Mobileye in their latest partnership with Volkswagen Group! Mobileye's level 4 autonomous driving system, Chauffeur, which incorporates Innoviz's #LiDAR, will be featured in Volkswagen's #Autonomous model of the ID Buzz electric minibus...

www.linkedin.com