BRN Discussion Ongoing

[misslou]

Great post @Esq.111!

Hmmm...All this talk of 4nm chips has got me thinking about Tesla since it has just placed a HUGE order for 4nm chips at TSMC's new US facility in Arizona with volume production expected to begin in 2024. Tesla's Hardware 3 in its electric cars will be replaced by Hardware 4 with the 4nm chips from TSMC. It says in another article that at the moment details are scarce but it's expected that this "new chip" will increase the range capacity as well as triple the power of the current model.

A girl can always dream...

View attachment 25180


View attachment 25181

Tesla chooses TSMC over Samsung, places huge 4nm chip order

One month ago, back in November, news broke that Tesla had placed a huge order for silicon at TSMC, choosing the Taiwanese chip manufacturer over Samsung. The deal is moving forward!

www.phonearena.com

Tesla Teams Up With TSMC to Create Cutting-Edge Autonomous Driving Technology

According to new reports in Taiwanese media, Tesla has become one of TSMC's biggest customers after securing the purchase of large quantities of microchips for its new generation of the FSD system.

www.torquenews.com

Elon was live on twitter a few hours ago answering questions from listeners. People got to switch on their mics and speak to him. I logged on just as he mentioned energy efficiency and battery life. I clicked immediately to ask a question and braced myself, practicing what I was going to say about neuromorphic technology and whether he thought spiking neural networks would improve the performance of Tesla vehicles, but he stopped taking questions before they got to me.
I don’t know if I was devastated or relieved because I just about wet myself with nerves.
Anyway, just wanted to let you know that I could’ve had the answer to your question but instead I have a story about a missed opportunity of a lifetime

 

[alwaysgreen]

Hi Bravo,

I know you are keen on establishing a link to Qualcomm, and I have been a little negative, but of course Qualcomm must be considering Akida.

After all, as you know, they are invested in SiFive ...

https://www.eetimes.com/qualcomm-takes-stake-in-sifive/

Qualcomm Takes Stake in SiFive​

By Nitin Dahad 06.07.2019

Qualcomm Ventures is the newest investor in SiFive, the RISC-V processor IP startup. It’s a clear signal Qualcomm plans to exploit the potential of the RISC-V architecture in wireless and mobile. SiFive announced it raised $65.4 million in funding, with another $11m for its Chinese sister company SaiFan China.

https://www.notebookcheck.net/Qualc...rs-in-SiFive-an-ARM-alternative.423631.0.html
Qualcomm, Samsung and Intel revealed as investors in SiFive, an ARM alternative
Qualcom, Samsung and Intel are all investors in RISC-V fabless US-based chip designing company SiFive. (Source: SiFive)
RISC-V chip designer SiFive it has been revealed to have some pretty interesting investors. A recent filing shows that it has raised US$65.4 million in its latest funding round including a cash injection from Qualcomm that sees it join fellow heavyweights in Samsung and Intel as investors.
Sanjiv Sathiah, Published 06/09/2019


... and BrainChip and SiFive are partners:

https://brainchip.com/brainchip-sifive-partner-deploy-ai-ml-at-edge/

BrainChip and SiFive Partner to Deploy AI/ML Technology at the Edge​

Laguna Hills, Calif. – April 5, 2022 – BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power neuromorphic AI chips and IP, and SiFive, Inc., the founder and leader of RISC-V computing, have combined their respective technologies to offer chip designers optimized AI/ML compute at the edge.

... so it is likely that Qualcomm will see the light soonish if they were to make an objective comparison with their AI acceleration engine in Snapdragon 8.2, particularly as Qualcommm has indicated they will be switching a lot of their production to RISC-V in light of the ARM litigation. .

https://www.theregister.com/2022/11/15/qualcomm_snapdragon_8_gen_2/?td=readmore

Qualcomm pushes latest Arm-powered Snapdragon chip amid bitter license fight

The Snapdragon 8 Gen 2 system-on-chip features eight off-the-shelf cores from Arm, which is locked in a bitter legal fight with Qualcomm over licenses and contracts.
...
This includes an AI acceleration engine that is, we're told, up to 4.35 times faster than the previous generation, and with a potential 60 percent increase in performance-per-watt, depending on how it's used. This unit can be used to speed up machine-learning tasks on the device without any outside help, such as object recognition, and real-time spoken language translation and transcription. The dual-processor engine can handle as low as INT4 precision for AI models that don't need a lot of precision but do need it done fast on battery power, which the 4-bit integer format can afford developers, according to Qualcomm.

Qualcomm is pushing the INT4 capabilities as a precision ideal for modern mobile apps. It said a cross-platform Qualcomm AI Studio is due to be made available in preview form in the first half of next year that will optimize developers' models for this precision as well as other formats. This studio looks like a typical IDE in which programmers can organize their training workflows.

... and there are a couple of other investors in SiFive who can profit from incorporating Akida in their products, one of whom has recently shed the cloak of invisibility.

.

 

[Rise from the ashes]

Intel's Mike D talking to Anastasi about Neuromorphic

Thanks for the video.
Anyone else mocking him whilst viewing the vid?

 

[charles2]

Thanks for the video.
Anyone else mocking him whilst viewing the vid?

Mocking? I'm pleased that he has (seemingly) recognized that Loihi is number 2. Humble pie never is delicious but we have all eaten it.

 

[Rise from the ashes]

Mocking? I'm pleased that he has (seemingly) recognized that Loihi is number 2. Humble pie never is delicious but we have all eaten it.

Well they may have had a premonition that their chip would be second best considering the name of it 'Loihi 2'
Can't wait for loihi 3, 4, 5, 6
Yes a serving of humble pie is good for the soul.

 

[Newk R]

Merry Christmas all chippers. Stay safe over the break and try not to drink too much more than me.
Cheers

 

[Fullmoonfever]

Given we are apparently available within the SynQuacer....I wonder

Original blog appears from mid 21 though refreshed / updated this year?

Socionext Human Detection Works with Nx - Network Optix

Socionext Video Analytics is a real-time low power and high-performance analytics solution that utilizes human detection technology.

www.networkoptix.com

Socionext Human Detection Works with Nx​

NETWORK OPTIX June 13, 2022 11 Min Read

Socionext Human Detection Works with Nx​

Categories: Analytics​

Compatible Nx Version: Nx Witness 4.0, Nx Witness 4.1​

Integrated with Nx: Metadata SDK​

• Product Website

---

About Socionext SNIAI​

SNIAI is a real-time, low-power, and high-performance video analytic solution that integrates with Powered by Nx products. Using a dedicated accelerator, SNIAI can detect humans across 20 cameras in real-time.

Components:

Processor: SynQuacer Socionext SC2A11 96 Boards (24 Cores of ARM Cortex-A53)

AI accelerator: SNI AI accelerator



Integrations

https://nxvms.com/integrations

Supported devices

https://nxvms.com/ipvd

Partners

Nx Tech Partner Listing | Network Optix

Discover Nx Tech Partners for Access Control, Alarm, Analytics, & Cloud Computing, and more. Join the tech partnership with Nx for cutting-edge solutions.

www.networkoptix.com

BrainChip and Socionext Provide a New Low-Power Artificial Intelligence Platform for AI Edge Applications

BrainChip and Socionext Provide a New Low-Power Artificial Intelligence Platform for AI Edge Applications March 23, 2020

brainchip.com

Socionext also offers a high-efficiency, parallel multi-core processor SynQuacerTM SC2A11 as a server solution for various applications.

Socionext’s processor is available now and the two companies expect the Akida SoC engineering samples to be available in the third quarter of 2020.

In addition to integrating BrainChip’s AI technology in an SoC, system developers and OEMs may combine BrainChip’s proprietary Akida device and Socionext’s processor to create high-speed, high-density, low-power systems to perform image and video analysis, recognition and segmentation in surveillance systems, live-streaming and other video applications.

 

[Bravo]

Hi Bravo,

I know you are keen on establishing a link to Qualcomm, and I have been a little negative, but of course Qualcomm must be considering Akida.

After all, as you know, they are invested in SiFive ...

https://www.eetimes.com/qualcomm-takes-stake-in-sifive/

Qualcomm Takes Stake in SiFive​

By Nitin Dahad 06.07.2019

Qualcomm Ventures is the newest investor in SiFive, the RISC-V processor IP startup. It’s a clear signal Qualcomm plans to exploit the potential of the RISC-V architecture in wireless and mobile. SiFive announced it raised $65.4 million in funding, with another $11m for its Chinese sister company SaiFan China.

https://www.notebookcheck.net/Qualc...rs-in-SiFive-an-ARM-alternative.423631.0.html
Qualcomm, Samsung and Intel revealed as investors in SiFive, an ARM alternative
Qualcom, Samsung and Intel are all investors in RISC-V fabless US-based chip designing company SiFive. (Source: SiFive)
RISC-V chip designer SiFive it has been revealed to have some pretty interesting investors. A recent filing shows that it has raised US$65.4 million in its latest funding round including a cash injection from Qualcomm that sees it join fellow heavyweights in Samsung and Intel as investors.
Sanjiv Sathiah, Published 06/09/2019


... and BrainChip and SiFive are partners:

https://brainchip.com/brainchip-sifive-partner-deploy-ai-ml-at-edge/

BrainChip and SiFive Partner to Deploy AI/ML Technology at the Edge​

Laguna Hills, Calif. – April 5, 2022 – BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power neuromorphic AI chips and IP, and SiFive, Inc., the founder and leader of RISC-V computing, have combined their respective technologies to offer chip designers optimized AI/ML compute at the edge.

... so it is likely that Qualcomm will see the light soonish if they were to make an objective comparison with their AI acceleration engine in Snapdragon 8.2, particularly as Qualcommm has indicated they will be switching a lot of their production to RISC-V in light of the ARM litigation. .

https://www.theregister.com/2022/11/15/qualcomm_snapdragon_8_gen_2/?td=readmore

Qualcomm pushes latest Arm-powered Snapdragon chip amid bitter license fight

The Snapdragon 8 Gen 2 system-on-chip features eight off-the-shelf cores from Arm, which is locked in a bitter legal fight with Qualcomm over licenses and contracts.
...
This includes an AI acceleration engine that is, we're told, up to 4.35 times faster than the previous generation, and with a potential 60 percent increase in performance-per-watt, depending on how it's used. This unit can be used to speed up machine-learning tasks on the device without any outside help, such as object recognition, and real-time spoken language translation and transcription. The dual-processor engine can handle as low as INT4 precision for AI models that don't need a lot of precision but do need it done fast on battery power, which the 4-bit integer format can afford developers, according to Qualcomm.

Qualcomm is pushing the INT4 capabilities as a precision ideal for modern mobile apps. It said a cross-platform Qualcomm AI Studio is due to be made available in preview form in the first half of next year that will optimize developers' models for this precision as well as other formats. This studio looks like a typical IDE in which programmers can organize their training workflows.

... and there are a couple of other investors in SiFive who can profit from incorporating Akida in their products, one of whom has recently shed the cloak of invisibility.

.

On the 12th day of Christmas BrainChip sent to me
Twelve unexpected announcements
Eleven Intel Foundry Services partners
Ten Mercedes MBUX's
Nine NVISO SDK's
Eight Valeo Lidars
Seven new Socionext auto applications
Six CES 2023 honourable mentions
Five custom designs with SiFive
Four lines of royalties from Renesas
Three wiz-bang Prophesee event-based camera's
Two NASA orbits and not even one ogre from my dear Dodgy-Knee (s)

 

[Fact Finder]

Surely not? View attachment 25199

AKITA is a Japanese dog breed with the known traits of being loyal and fiercely protective of its family, aggressive to strangers and other dogs BUT very hard to train.

Seems a very funny name to choose if correct. Perhaps it’s just the project name which would make it intriguing???

My opinion only DYOR
FF

AKIDA BALLISTA

 

[pgetties]

I proposed this question on the openai CHATbot.. very interesting to read the response..

“How will Brainchip akida revolutionise the AI sector”

Brainchip Akida is a neuromorphic system-on-chip (SoC) that has been designed to enable artificial intelligence (AI) and machine learning (ML) capabilities in edge devices. The Akida SoC is based on a novel spiking neural network (SNN) architecture that is inspired by the way the brain works. According to Brainchip, the Akida SoC can perform a wide range of AI and ML tasks, including image recognition, object detection, and natural language processing, with high accuracy and low power consumption.

The potential benefits of the Akida SoC for the AI sector are significant. By enabling AI and ML capabilities on edge devices, the Akida SoC could potentially revolutionize the way that AI is deployed and used. For example, the Akida SoC could enable the development of AI-powered devices that can operate independently, without the need for a connection to a central server or cloud computing infrastructure. This could make AI more accessible and widely available, and enable a wide range of new applications and use cases.

It is important to note that the Akida SoC is still a relatively new technology, and it remains to be seen how it will be adopted and used in the AI sector. However, the potential benefits of the Akida SoC are significant, and it is likely that it will play a significant role in the future of AI and ML.

 

[Diogenese]

View attachment 25203


On the 12th day of Christmas BrainChip sent to me
twelve unexpected announcements
eleven Intel Foundry Services partners
ten Mercedes MBUX's
nine NVISO SDK's
eight Valeo Lidars
seven new Socionext auto applications
six CES 2023 honourable mentions
five custom designs with SiFive
four lines of royalties from Renesas
three wiz-bang Prophesee event-based camera's
two NASA orbits and not even one ogre from my dear Dodgy-Knee (s)

Your scansion's a bit dodgy ...

 

[Diogenese]

I proposed this question on the openai CHATbot.. very interesting to read the response..

“How will Brainchip akida revolutionise the AI sector”

Brainchip Akida is a neuromorphic system-on-chip (SoC) that has been designed to enable artificial intelligence (AI) and machine learning (ML) capabilities in edge devices. The Akida SoC is based on a novel spiking neural network (SNN) architecture that is inspired by the way the brain works. According to Brainchip, the Akida SoC can perform a wide range of AI and ML tasks, including image recognition, object detection, and natural language processing, with high accuracy and low power consumption.

The potential benefits of the Akida SoC for the AI sector are significant. By enabling AI and ML capabilities on edge devices, the Akida SoC could potentially revolutionize the way that AI is deployed and used. For example, the Akida SoC could enable the development of AI-powered devices that can operate independently, without the need for a connection to a central server or cloud computing infrastructure. This could make AI more accessible and widely available, and enable a wide range of new applications and use cases.

It is important to note that the Akida SoC is still a relatively new technology, and it remains to be seen how it will be adopted and used in the AI sector. However, the potential benefits of the Akida SoC are significant, and it is likely that it will play a significant role in the future of AI and ML.

Akida could also put openai Chatbot out of a job.

 

[Fact Finder]

Just having a little look around and the orange xxxx’s mark the spot where in the past week and interesting update was made to AKIDA models. @Diogenese can tell us if this amendment has any significance and almost forgot since when has AKD500 been available. Peter van der Made said this might be used in white goods:

Upgrade to akida/cnn2snn 2.2.6 and akida_models 1.1.8​

last week

ktsiknos-brainchip
2.2.6-doc-1
d334eea
Upgrade to akida/cnn2snn 2.2.6 and akida_models 1.1.8
Latest

Update akida and cnn2snn to version 2.2.6​

New features​

• [akida] Upgrade to quantizeml 0.0.13
• [akida] Attention layer
• [akida] Identify AKD500 devices
• [engine] Move mesh scan to host library

API changes​

• [engine] toggle_learn must be called instead of program(p,learn_enabled)
• [engine] set_batch_size allows to preallocate inputs

Bug fixes​

• [engine] Memory can grow indefinitely if queueing is faster than processing

Update akida_models to 1.1.8​

• updated CNN2SNN minimal required version to 2.2.6 and QuantizeML to 0.0.13
• VWW model and training pipeline refactored and aligned with TinyML
• Layer names in almost all models have been updated in preparation for quantization with QuantizeML
• Tabular data models and tools have been removed from the package

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

• Transformers pretrained models updated to 4-bits

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

• Introduced calibration utils in training toolset
• KWS and ImageNet training scripts now offer a "calibrate" CLI action
• ImageNet training script will now automatically restore the best weights after training

Documentation update​

• dropped quantizeml API details for now

Releases · Brainchip-Inc/akida_examples

Brainchip Akida Neuromorphic System-on-Chip examples and documentation. - Brainchip-Inc/akida_examples

github.com

 

[HopalongPetrovski]

Whilst I know we would all love to have a higher share price (just 'coz, right) it occurs to me that given our history (particularly coming up on a certain phenomena that occurred just shy of a year ago) and the buzz that surrounded that event, along with the quiet but undoubtedly noticed strides our Company has made, unfussily cementing it's position within many high ranking eco systems, without all the who/har normally associated with such.......that it's only gonna take a spark (the right spark, mind you) to set all this knowledge fuel ablaze, and when that happens, what will you do?
Run the broad scenarios in your minds over the next few days, taking into consideration the tax implications along with your strategies both short and long term. Last year, when our price went ape shit, I was as frozen as a deer in the headlights and have been metaphorically kicking myself in the arse with hindsight backchat ever since.
Of course, there is no universal right choice and I am not advocating any particular version of buy, sell (sell some) or hold, as that will vary with each individuals/partnerships circumstances, goals and risk/reward tolerance.
Hopefully we all by now have a well developed plan in mind maximising the benefit we will derive from our investment, but if your not quite there yet, then at least spare a few minutes to give this a muse.
Cause it might just explode with this coming CES in a few days time, or it could be that expected announcement out of the blue, which could drop at any time from a myriad of known and unknown sources.
Be ready fellow Chipper's and ........

 

[charmander]

Merry Christmas from a serial lurker, Brainchip Fam.

The time, effort, and passion y'all put into researching and posting about this beautiful little nugget is absolutely incredible and it's truly an honour to be involved (from the quiet backseat) in this community

 

[HopalongPetrovski]

Merry Christmas from a serial lurker, Brainchip Fam.

The time, effort, and passion y'all put into researching and posting about this beautiful little nugget is absolutely incredible and it's truly an honour to be involved (from the quiet backseat) in this community

Don't be afraid to show us a bit of leg from time to time.
It takes all kinds.

 

[Diogenese]

Don't be afraid to show us a bit of leg from time to time.
It takes all kinds.

 

[KKFoo]

Merry Christmas

 

[Diogenese]

Just having a little look around and the orange xxxx’s mark the spot where in the past week and interesting update was made to AKIDA models. @Diogenese can tell us if this amendment has any significance and almost forgot since when has AKD500 been available. Peter van der Made said this might be used in white goods:

Upgrade to akida/cnn2snn 2.2.6 and akida_models 1.1.8​

last week

ktsiknos-brainchip
2.2.6-doc-1
d334eea
Upgrade to akida/cnn2snn 2.2.6 and akida_models 1.1.8
Latest

Update akida and cnn2snn to version 2.2.6​

New features​

• [akida] Upgrade to quantizeml 0.0.13
• [akida] Attention layer
• [akida] Identify AKD500 devices
• [engine] Move mesh scan to host library

API changes​

• [engine] toggle_learn must be called instead of program(p,learn_enabled)
• [engine] set_batch_size allows to preallocate inputs

Bug fixes​

• [engine] Memory can grow indefinitely if queueing is faster than processing

Update akida_models to 1.1.8​

• updated CNN2SNN minimal required version to 2.2.6 and QuantizeML to 0.0.13
• VWW model and training pipeline refactored and aligned with TinyML
• Layer names in almost all models have been updated in preparation for quantization with QuantizeML
• Tabular data models and tools have been removed from the package

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

• Transformers pretrained models updated to 4-bits

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

• Introduced calibration utils in training toolset
• KWS and ImageNet training scripts now offer a "calibrate" CLI action
• ImageNet training script will now automatically restore the best weights after training

Documentation update​

• dropped quantizeml API details for now

Releases · Brainchip-Inc/akida_examples

Brainchip Akida Neuromorphic System-on-Chip examples and documentation. - Brainchip-Inc/akida_examples

github.com

Remember that, like sgt. Schultz, I know nothing about Transformers.

As I understand it:

Update akida_models to 1.1.8​

• Transformers pretrained models updated to 4-bits

means the model libraries (speech was the initial application of Transformers) have been updated.

There are about 44 phonemes in English, but dialect and accent will multiply this.

The updating was to convert the libraries to 4-bit bytes (from ... 8-bits?) so they are compatible with Akida NPUs.

This is only changing some numbers in memory - no silicon was harmed in performing this update.

Remembering that we are selling Akida IP, implementing Transformers in Akida may be as simple as updating the model library and designing the appropriate NPU configuration, the configuration being implemented by the ARM Cortex M MPU as part of the set up procedure.

Now I suppose you do need LSTM for transformers, so this will require some additional memory for previous words/sentences, so there may be some collateral damage to the silicon at this stage.

So I wonder if we have had to go back to the drawingboard after implementing LSTM to update the silicon for Transformers which are a very recent phenomenon for Akida.

 

[equanimous]

I proposed this question on the openai CHATbot.. very interesting to read the response..

“How will Brainchip akida revolutionise the AI sector”

Brainchip Akida is a neuromorphic system-on-chip (SoC) that has been designed to enable artificial intelligence (AI) and machine learning (ML) capabilities in edge devices. The Akida SoC is based on a novel spiking neural network (SNN) architecture that is inspired by the way the brain works. According to Brainchip, the Akida SoC can perform a wide range of AI and ML tasks, including image recognition, object detection, and natural language processing, with high accuracy and low power consumption.

The potential benefits of the Akida SoC for the AI sector are significant. By enabling AI and ML capabilities on edge devices, the Akida SoC could potentially revolutionize the way that AI is deployed and used. For example, the Akida SoC could enable the development of AI-powered devices that can operate independently, without the need for a connection to a central server or cloud computing infrastructure. This could make AI more accessible and widely available, and enable a wide range of new applications and use cases.

It is important to note that the Akida SoC is still a relatively new technology, and it remains to be seen how it will be adopted and used in the AI sector. However, the potential benefits of the Akida SoC are significant, and it is likely that it will play a significant role in the future of AI and ML.

AI Backing AI. Classic