BRN Discussion Ongoing

[BaconLover]

A few months back when they had validated the chips and were taking orders, I filled out the USB stick "notify when available" page, but never got confirmation of my inquiry nor ever heard back and the USB stick is no longer listed in BRN Products list.
Running out of stock and or not producing an awaited development product doesn't make best use of excited time and effort spreading the word AKIDA.
To maximize uptake they need to put potential development tools in the hands of as many customers as practical. IMO

I don't think they give importance to the USB stick sale.

IP is where $$$ is at. I am personally happy they're not wasting time making USB sticks. Bring on the big business. We can concentrate on USB and B2C model down the track.

 

[Diogenese]

My little cat nose detects strong Akida VOC compounds. Smells very noice!

What are NASA's Technology Educational Satellites? - NASA

NASA’s TechEdSat series of technology demonstrations aims to bring small payloads back to Earth or to the surface of Mars – while pushing the state of the art

www.nasa.gov

In the past, NASA has expressed a fondness for MemRistor/ReRAM analog NNs because of their inherent radhardness, so the use of the word "analog" circuits is not encouraging.

 

[Potato]

Yeah, but she also gave him a hard time!

At his age, having a hard time isn't such a bad thing

 

[Slade]

A few months back when they had validated the chips and were taking orders, I filled out the USB stick "notify when available" page, but never got confirmation of my inquiry nor ever heard back and the USB stick is no longer listed in BRN Products list.
Running out of stock and or not producing an awaited development product doesn't make best use of excited time and effort spreading the word AKIDA.
To maximize uptake they need to put potential development tools in the hands of as many customers as practical. IMO

The company should have notified you. I believe the USB stick was part of the original plan to flood the market with Akida. Intel have an AI USB and you are right, it puts the tech in the hands of potential clients. As the World is now turning to edge AI, I believe the USB sticks would be very popular. I don’t have a problem with BrainChip changing their strategy but I think they should have notified the market. A simple, we have delayed the production of USB sticks would have sufficed.

 

[Bravo]

Hoots Mon!
Well, we are just going to have to behave better, when we all become Brainchip Billionaires!
I'm giving it ten more years!
And then, if'n my net worth is not o'ertoppin $999,999,999....
I'll be writing a stern letter to our Mr Heheheir...
I'll definitely be needing a young wife by then to prepare my coco at night.

View attachment 3468

Well, if your chompers are anything like his, you're going to need all the help you can get! May be best not to convert your $999999999 into US currency because that means you'll only be worth a measly $751,429,999.25 dollars.

 

[Fact Finder]

In the past, NASA has expressed a fondness for MemRistor/ReRAM analog NNs because of their inherent radhardness, so the use of the word "analog" circuits is not encouraging.

View attachment 3473

Yes I saw that then I thought I would look up the definition of “graphic processor unit” and they are but one part of a GPU which I am sure you know. I then read a Q&A where someone asked if you could run one without a GPU and the answer was that you could for limited purposes run them directly on the CPU.

Then this totally techno unco thought to himself NASA does not mention either a GPU or a CPU being involved but does mention neuromorphic computing and adding much more thinking.

Then I went to the statement in the last couple of months from Brainchip that someone was benchmarking AKIDA against a GPU and it was coming back favourable to AKIDA.

So then I without any engineering qualifications or idea leapt to the following:

1. A graphic processor needs some compute to maximise its potential as a sensor;

2. AKIDA out performs a GPU and is SWaP and COTS ready and is being investigated at Ames. Ames is where this was all developed;

3. Why could AKIDA technology not be providing the extra processing power to maximise the analogue graphic processing unit???

“graphic processor units that use electric analog circuits to mimic the human nervous system, known as or neuromorphic processors, adds much more "thinking" capability in these small boxes”

Wild and meaningless speculation DYOR
FF

AKIDA BALLISTA

 

[Fullmoonfever]

Geez...even made it to Russian IT site on the availability of the board haha.

English version:

Sales of processors that mimic the work of the human brain began. Smart cities and cars need them

BrainChip Akida (neuromorphic processor)

tadviser.com

Translated by

BrainChip Akida (neuromorphic processor)​

Product

Developers:	BrainChip
Date of the premiere of the system:	January 2022
Branches:	Electrical and microelectronics
Technology:	Processors

2022: Start Selling Processor​

On January 18, 2022, BrainChip announced the launch of sales of its Akida neural network processor. According to the developers, this product is the first commercial among neuromorphic AI chips that can provide the benefits of ultra-low power consumption and performance over traditional approaches.
As AI has continued to grow over the past few years, artificial intelligence in peripheral computing is expected to occupy most of the market. This is known as artificial intelligence of things. Peripheral computing also results in less delay than sending information to the cloud.

Sales of Akida processors that mimic the work of the human brain began
BrainChip takes a different approach with its first AKD1000 neuromorphic processor. Neuromorphic calculations differ from classical AI approaches, which are based on convolutional neural networks (CNNs), in that they much more accurately mimic the brain using impulse neural networks (SNNs). Although neuromorphic chips are usually still digital, they, in most cases, work on the basis of asynchronous circuits, which means that there is no global synchronization. Depending on the particular application, neuromorphic calculations can be several orders of magnitude faster and require less energy.
The Akida configuration from BrainChip has an event-oriented architecture. It can support built-in learning and deduction, as well as support various touch inputs, such as applications for vision, sound, sense of smell, and intelligent sensor applications.
The AKD1000-based board can be connected to an existing developer system to open up opportunities for a wide range of AI peripheral applications, including Smart City, Smart Health, Smart Home, and Smart Transport. BrainChip will also offer system integrators and developers complete layout files and material specification (BOM) so that they can create their own personal cards and implement AKD1000 chips in large volumes as an independent integrated accelerator or coprocessor.
Starting January 18, BrainChip begins to accept orders for its first commercially available mini PCIe card with the Akida AKD1000 chip at a price of $500. It can be used as an integrated accelerator or coprocessor. BrainChip notes that this completes the AKD1000 product family after the development kits that were introduced in October 2021 for x86 and Arm-based systems.[1]

Notes​

1. ↑ BrainChip launches neuromorphic process for AI at the edge

 

[Shadow59]

View attachment 3465
Imagine Akida toilet bowl can monitor our health oneday

I'm not sure I would like the fully immersive experience

 

[BigDonger101]

I'm not sure if this has any relevance, just came across this project.

Technology and hardware for neuromorphic computing | TEMPO Project | Fact Sheet | H2020 | CORDIS | European Commission

Massive adoption of computing in all aspects of human activity has led to unprecedented growth in the amount of data generated. Machine learning has been employed to classify and infer patterns from this abundance of raw data, at various levels of abstraction. Among the...

cordis.europa.eu

Title: New ways to integrate emerging memories to enable neuromorphic computing systems

Info: ''Artificial intelligence (AI) and machine learning are used today for computing all kinds of data, making predictions and solving problems. These are processes based increasingly on deep neuronal network (DNN) models. As the volume of produced data slow down machines and consume greater amounts of energy, there is a new generation of neural units. The spiking neural networks (SNNs) incorporate biologically-feasible spiking neurons with their temporal dynamics. The EU-funded TEMPO project will leverage emerging memory technology to design new innovative technological solutions that make data integration simpler and easier via new neuronal DNN and SNN computing engines. Reduced core computational operational systems’ neuromorphic algorithms will serve as demonstrators.''

Objective: ''Massive adoption of computing in all aspects of human activity has led to unprecedented growth in the amount of data generated. Machine learning has been employed to classify and infer patterns from this abundance of raw data, at various levels of abstraction. Among the algorithms used, brain-inspired, or “neuromorphic”, computation provides a wide range of classification and/or prediction tools. Additionally, certain implementations come about with a significant promise of energy efficiency: highly optimized Deep Neural Network (DNN) engines, ranging up to the efficiency promise of exploratory Spiking Neural Networks (SNN). Given the slowdown of silicon-only scaling, it is important to extend the roadmap of neuromorphic implementations by leveraging fitting technology innovations. Along these lines, the current project aims to sweep technology options, covering emerging memories and 3D integration, and attempt to pair them with contemporary (DNN) and exploratory (SNN) neuromorphic computing paradigms. The process- and design-compatibility of each technology option will be assessed with respect to established integration practices. Core computational kernels of such DNN/SNN algorithms (e.g. dot-product/integrate-and-fire engines) will be reduced to practice in representative demonstrators.''

Project Start: 1 May 2019

Project end: 31 Oct 2022

Total Cost: € 34 527 459,75

Coordinated by: INTERUNIVERSITAIR MICRO-ELECTRONICA CENTRUM, Belgium.

 

[Slade]

I'm not sure if this has any relevance, just came across this project.

Technology and hardware for neuromorphic computing | TEMPO Project | Fact Sheet | H2020 | CORDIS | European Commission

Massive adoption of computing in all aspects of human activity has led to unprecedented growth in the amount of data generated. Machine learning has been employed to classify and infer patterns from this abundance of raw data, at various levels of abstraction. Among the...

cordis.europa.eu

Title: New ways to integrate emerging memories to enable neuromorphic computing systems

Info: ''Artificial intelligence (AI) and machine learning are used today for computing all kinds of data, making predictions and solving problems. These are processes based increasingly on deep neuronal network (DNN) models. As the volume of produced data slow down machines and consume greater amounts of energy, there is a new generation of neural units. The spiking neural networks (SNNs) incorporate biologically-feasible spiking neurons with their temporal dynamics. The EU-funded TEMPO project will leverage emerging memory technology to design new innovative technological solutions that make data integration simpler and easier via new neuronal DNN and SNN computing engines. Reduced core computational operational systems’ neuromorphic algorithms will serve as demonstrators.''

Objective: ''Massive adoption of computing in all aspects of human activity has led to unprecedented growth in the amount of data generated. Machine learning has been employed to classify and infer patterns from this abundance of raw data, at various levels of abstraction. Among the algorithms used, brain-inspired, or “neuromorphic”, computation provides a wide range of classification and/or prediction tools. Additionally, certain implementations come about with a significant promise of energy efficiency: highly optimized Deep Neural Network (DNN) engines, ranging up to the efficiency promise of exploratory Spiking Neural Networks (SNN). Given the slowdown of silicon-only scaling, it is important to extend the roadmap of neuromorphic implementations by leveraging fitting technology innovations. Along these lines, the current project aims to sweep technology options, covering emerging memories and 3D integration, and attempt to pair them with contemporary (DNN) and exploratory (SNN) neuromorphic computing paradigms. The process- and design-compatibility of each technology option will be assessed with respect to established integration practices. Core computational kernels of such DNN/SNN algorithms (e.g. dot-product/integrate-and-fire engines) will be reduced to practice in representative demonstrators.''

Project Start: 1 May 2019

Project end: 31 Oct 2022

Total Cost: € 34 527 459,75

Coordinated by: INTERUNIVERSITAIR MICRO-ELECTRONICA CENTRUM, Belgium.

Thanks for posting. I would say it could be very relevant. From the link it looks like Valeo are one of the participants and we know where they get their SNN technology.

 

[Diogenese]

Geez...even made it to Russian IT site on the availability of the board haha.

English version:

Sales of processors that mimic the work of the human brain began. Smart cities and cars need them

BrainChip Akida (neuromorphic processor)

tadviser.com

View attachment 3474


Translated by

BrainChip Akida (neuromorphic processor)​

Product

Developers:	BrainChip
Date of the premiere of the system:	January 2022
Branches:	Electrical and microelectronics
Technology:	Processors

2022: Start Selling Processor​

On January 18, 2022, BrainChip announced the launch of sales of its Akida neural network processor. According to the developers, this product is the first commercial among neuromorphic AI chips that can provide the benefits of ultra-low power consumption and performance over traditional approaches.
As AI has continued to grow over the past few years, artificial intelligence in peripheral computing is expected to occupy most of the market. This is known as artificial intelligence of things. Peripheral computing also results in less delay than sending information to the cloud.

Sales of Akida processors that mimic the work of the human brain began
BrainChip takes a different approach with its first AKD1000 neuromorphic processor. Neuromorphic calculations differ from classical AI approaches, which are based on convolutional neural networks (CNNs), in that they much more accurately mimic the brain using impulse neural networks (SNNs). Although neuromorphic chips are usually still digital, they, in most cases, work on the basis of asynchronous circuits, which means that there is no global synchronization. Depending on the particular application, neuromorphic calculations can be several orders of magnitude faster and require less energy.
The Akida configuration from BrainChip has an event-oriented architecture. It can support built-in learning and deduction, as well as support various touch inputs, such as applications for vision, sound, sense of smell, and intelligent sensor applications.
The AKD1000-based board can be connected to an existing developer system to open up opportunities for a wide range of AI peripheral applications, including Smart City, Smart Health, Smart Home, and Smart Transport. BrainChip will also offer system integrators and developers complete layout files and material specification (BOM) so that they can create their own personal cards and implement AKD1000 chips in large volumes as an independent integrated accelerator or coprocessor.
Starting January 18, BrainChip begins to accept orders for its first commercially available mini PCIe card with the Akida AKD1000 chip at a price of $500. It can be used as an integrated accelerator or coprocessor. BrainChip notes that this completes the AKD1000 product family after the development kits that were introduced in October 2021 for x86 and Arm-based systems.[1]

Notes​

1. ↑ BrainChip launches neuromorphic process for AI at the edge

Hi FMF,

not sure visiting Russian sites is a good idea at the best of times.

In the early days of PCs, I advised a friend to get some security software. He googled the product and, being, shall we say, cost-conscious, he looked for the cheapest offer rather than the home page of the software provider. Also being fairly new to computers, he either did not see the ".ru" or did not understand what it meant.

Needless to say, his computer caught a nasty rash which required a visit to the computer clinic ...

... and he had the temerity to blame me for his troubles.

 

[Bravo]

@HopalongPetrovski

I'm sorry Hoppy, I'm sure you have lovely fangs. Fangstatic even!

 

[HopalongPetrovski]

Well, if your chompers are anything like his, you're going to need all the help you can get! May be best not to convert your $999999999 into US currency because that means you'll only be worth a measly $751,429,999.25 dollars.

Poor Billionaires get a bad rap, probably safer and more politically correct these days to just stay a boring old multi millionaire.

 

[Dang Son]

I don't think they give importance to the USB stick sale.

IP is where $$$ is at. I am personally happy they're not wasting time making USB sticks. Bring on the big business. We can concentrate on USB and B2C model down the track.

Agreed BL,
IP is where $$$ is at, but who's to say big IP $$$ use cases wouldn't come from supplying developer tools to that end of the market like tinkering nerds , design engineers and tech colleges.

 

[TheFunkMachine]

Here's another joke I just thought of:

Question: What do you get if you cross BrainChip with a jalapeno?
Answer: A BrainChipotle

I though the answer would be “an un-irond table cloth”

 

[Fullmoonfever]

Hi FMF,

not sure visiting Russian sites is a good idea at the best of times.

In the early days of PCs, I advised a friend to get some security software. He googled the product and, being, shall we say, cost-conscious, he looked for the cheapest offer rather than the home page of the software provider. Also being fairly new to computers, he either did not see the ".ru" or did not understand what it meant.

Needless to say, his computer caught a nasty rash which required a visit to the computer hospital ...

... and he had the temerity to blame me for his troubles.

Hey D

Good advice and good point for others.

Not running the .ru domain though there is a Russian version if want to visit that one kidding.

I wouldn't visit .ru as you say and also run various requisite software protection, vpn on laptop and mobile plus run restore points and cloud upload regularly as further backup and regular full system / file scans.

Though these days...can only add so many layers of protection as the buggers just find new ways around.

 

[Diogenese]

Hi FMF,

not sure visiting Russian sites is a good idea at the best of times.

In the early days of PCs, I advised a friend to get some security software. He googled the product and, being, shall we say, cost-conscious, he looked for the cheapest offer rather than the home page of the software provider. Also being fairly new to computers, he either did not see the ".ru" or did not understand what it meant.

Needless to say, his computer caught a nasty rash which required a visit to the computer hospital ...

... and he had the temerity to blame me for his troubles.

When I say "cost-conscious", I believe his hip pocket was sewn up.

 

[Fact Finder]

And here is another industry that does not exist yet for AKIDA technology to dominate:

Realistic Retinas Make Better Bionic Eyes

Following nature’s example more closely could lead to better visual sensors

spectrum.ieee.org

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Yak52]

Pump & Dump as usual for BRN.

93c start with Top of $1.05 and low now at 95c.


My bet is another 2.5 mil Shorts were taken out at 98c and have been sold off into the Market to drop the SP from there (98c) @ 2.20pm down to here near the close@ 95c.
Find out maybe tomorrow or Friday if this is the case.
about 4 Mil was traded after 2.20pm and there seems to be a big buying expedition at 95.5c mark which could mean they have bought back Shorts at 95.5c.
Guess work but seems possible.
Overall Short Positions outstanding have dropped significantly.
Tuesdays NEW Shorts were ONLY ...........152,000 . THIS IS THE SMALLEST AMOUNT FOR MONTHS! Normally min 550,000+

Yak52

 

[Bravo]

Sorry if posted previously, this is Renesas's Automotive Strategy dated 3 March 2022. I was trying to find out a bit more about their product development timelines and stumbled on this by accident.

https://www.renesas.com/sg/en/document/ppt/automotive-strategy-2?r=1320481