BRN Discussion Ongoing

[thelittleshort]

Sean Hehir announcing Information Systems Labs joining the BrainChip Early Access Program in January 2022

“ISL has decided to use Akida and Edge-based learning as a tool to incorporate into their portfolio of research engineering and engineering solutions in large part due to our innovative capabilities and production-ready status that provides go-to-market advantages,” said Sean Hehir, BrainChip CEO.

“We are pleased to be included as the AI- and Edge-based learning component of ISL’s research sponsored by AFRL. We feel that the combination of technologies will help expedite its deployment into the field.”

Cloud-based analytics. “The ubiquitous availability of proliferated sensor data opens up boundless new opportunities for artificial intelligence and machine learning applications, across commercial, government, and military uses. The new paradigm of cloud computing allows raw data to be processed into actionable intelligence anywhere there is available compute capacity, from large server farms to orbiting (or lunar) edge compute hardware, to distributed processing across a network of small devices.”

Into the 'outernet': Secure 'internet in space' key to future Space Force hybrid architecture - Breaking Defense

Four Pentagon offices are working together on an ambitious hybrid architecture that spans orbits as well as classification levels, officials told Breaking Defense.

breakingdefense.com

 

[Chimi]

Can we please renove lzzzzzy or whatever.
You are annoying

 

[equanimous]

https://onlinelibrary.wiley.com/doi/10.1002/adma.202204949?af=R

Hi @Diogenese

Have you come across this before. Unfortunately need to pay to get full access.


Research Article

A MoS2 Hafnium Oxide Based Ferroelectric Encoder for Temporal-Efficient Spiking Neural Network​

Yu-Chieh Chien, Heng Xiang, Yufei Shi, Ngoc Thanh Duong, Sifan Li, Kah-Wee Ang
First published: 11 November 2022

https://doi.org/10.1002/adma.202204949
Read the full text

PDF
TOOLS

SHARE

Abstract​

Spiking neural network (SNN), where the information is evaluated recurrently through spikes, has manifested significant promises to minimize the energy expenditure in data-intensive machine learning and artificial intelligence. Among these applications, the artificial neural encoders are essential to convert the external stimuli to a spiking format that can be subsequently fed to the neural network. Here, a molybdenum disulfide (MoS2) hafnium oxide-based ferroelectric encoder is demonstrated for temporal-efficient information processing in SNN. The fast domain switching attribute associated with the polycrystalline nature of hafnium oxide-based ferroelectric material is exploited for spike encoding, rendering it suitable for realizing biomimetic encoders. Accordingly, a high-performance ferroelectric encoder is achieved, featuring a superior switching efficiency, negligible charge trapping effect, and robust ferroelectric response, which successfully enable a broad dynamic range. Furthermore, an SNN is simulated to verify the precision of the encoded information, in which an average inference accuracy of 95.14% can be achieved, using the Modified National Insitute of Standards and Technology (MNIST) dataset for digit classification. Moreover, this ferroelectric encoder manifests prominent resilience against noise injection with an overall prediction accuracy of 94.73% under various Gaussian noise levels, showing practical promises to reduce the computational load for the neural network.

 

[VictorG]

Below is list of neuromorphic technologies for reference purposes.
It's not an exhaustive list but has the main players.

Caleb Naugle on LinkedIn: #newtechnology #data #artificialintelligence #machinelearning…

⁉ If Neuromorphic Computing could be so revolutionary, why isn't everyone working on it? Well it turns out everyone is. Below is a non-exhaustive list of…

www.linkedin.com

 

[FJ-215]

I believe that Tech is referring to the latest incarnation of AKIDA not the Renesas development.

I believe you are right.......

 

[Sam]

Ok

Just watching a movie called Her… a movie about AI in the future. Could be where we are heading in the not to distant future I guess. And yes I’m thinking about Akida

 

[Sam]

Ok

Sorry if this has come through again but didn’t seem to post so I’ll post again…

So about half way through and the main protagonist is making love with the AI assistant getting a little weird guys

 

[mrgds]

Google has been life changing. The best company in massive innovation (google maps, android, youtube) where everything is free to the user.

Big data has its place for sure. I own google stock from years back, but my new money is going to Brainchip.

Edge IoT via SNN is Brainchip's to grab the spotlight over time. Lots of AI/ML companies are going to win.

View attachment 27128

Where are your thoughts on Google now that CHATGPT 3.5 has surfaced? Soon to be CHATGPT 4 ?

 

[equanimous]

Introducing the Dendrify framework for incorporating dendrites to spiking neural networks - Nature Communications

Biologically inspired spiking neural networks are highly promising, but remain simplified omitting relevant biological details. The authors introduce here theoretical and numerical frameworks for incorporating dendritic features in spiking neural networks to improve their flexibility and...

www.nature.com

Introducing the Dendrify framework for incorporating dendrites to spiking neural networks​

 

[Fullmoonfever]

Hi Fmf,

Intel of course have their own NNs, and I think it's too early to have Akida in the Intel Horse Creek mix.

Xilinx Spartan is a COTS FPGA.

https://www.xilinx.com/products/silicon-devices/fpga/spartan-6.html

FPGA are Xilinx's bread and butter, so it would be drawing a long bow to link BrainChip to Intel via Xilinx.

Fair call.

I was thinking more about where they mention commercial Risc-V cores on the same line which SiFive fall into as well, who Intel are also working with and we get opp maybe down track to include our IP via that process.

Oh well.

 

[Diogenese]

https://onlinelibrary.wiley.com/doi/10.1002/adma.202204949?af=R

Hi @Diogenese

Have you come across this before. Unfortunately need to pay to get full access.


Research Article

A MoS2 Hafnium Oxide Based Ferroelectric Encoder for Temporal-Efficient Spiking Neural Network​

Yu-Chieh Chien, Heng Xiang, Yufei Shi, Ngoc Thanh Duong, Sifan Li, Kah-Wee Ang
First published: 11 November 2022

https://doi.org/10.1002/adma.202204949
Read the full text

PDF
TOOLS

SHARE

Abstract​

Spiking neural network (SNN), where the information is evaluated recurrently through spikes, has manifested significant promises to minimize the energy expenditure in data-intensive machine learning and artificial intelligence. Among these applications, the artificial neural encoders are essential to convert the external stimuli to a spiking format that can be subsequently fed to the neural network. Here, a molybdenum disulfide (MoS2) hafnium oxide-based ferroelectric encoder is demonstrated for temporal-efficient information processing in SNN. The fast domain switching attribute associated with the polycrystalline nature of hafnium oxide-based ferroelectric material is exploited for spike encoding, rendering it suitable for realizing biomimetic encoders. Accordingly, a high-performance ferroelectric encoder is achieved, featuring a superior switching efficiency, negligible charge trapping effect, and robust ferroelectric response, which successfully enable a broad dynamic range. Furthermore, an SNN is simulated to verify the precision of the encoded information, in which an average inference accuracy of 95.14% can be achieved, using the Modified National Insitute of Standards and Technology (MNIST) dataset for digit classification. Moreover, this ferroelectric encoder manifests prominent resilience against noise injection with an overall prediction accuracy of 94.73% under various Gaussian noise levels, showing practical promises to reduce the computational load for the neural network.

Analog MemRistor

 

[FlipDollar]

Nor can I. But again anyone thinking someone on this forum can manipulate the SP need to maybe rethink investing. If anyone was to sell their shares because of a post here then it would need to be hard evidence that the IP was fraudulent. That means they would be closer to the tech than Arm, Sifive, Edge Impluse, Nviso, Mercedes, Megachips, Socionext, Prophesee, VVDN etc etc etc.....

Their knowledge would be greater than the minds of the best software developers at the above companies plus so many more. So again the thought that someone comes here without any real evidence (facts) and people believe that it will destroy or kill the forum or the SP, well to me it would only show the weakness in the ability of the investor.

View attachment 27112

Full disclosure - the only time I sold BRN was when during the 2022 run up to 2.34 when Dolci said something along the lines of our SP and $3b MC was unrealistic for a company with no revenue…

Along with saving me from losing a lot of profit in those 4 days, she opened a new door for me and now I pay a lot more attention and invest a lot more time into knowing my portfolio.

Managed to buy back in, and buy a lot more, since.

 

[Izzzzzzzzzzy]

Full disclosure - the only time I sold BRN was when during the 2022 run up to 2.34 when Dolci said something along the lines of our SP and $3b MC was unrealistic for a company with no revenue…

Along with saving me from losing a lot of profit in those 4 days, she opened a new door for me and now I pay a lot more attention and invest a lot more time into knowing my portfolio.

Managed to buy back in, and buy a lot more, since.

You must be a shorter back to hc for you

 

[mrgds]

what is wrong with that comment? Tell me, if you knew that this sp action would occur, would you have not sold at $2.30 and bought back in at these levels. Let’s see the response. I believe 99.9 % of the people in the forum would have happily taken this opportunity. You are seriously just projecting your insecurities at this point of time. It’s not cool and there is no need for it at all.

lzzzzzzzzzzzy:
you have been "vulgar, cras, and quite a pig at times.
i do think you are on many peoples ignore list.
pls dont hold a personal grudge by not "capitalizing on the MB ann 12mths ago" ............... from what i have read, many are in the same boat.
Myself ........ i sold 600k shares @ $1.58, ............ almost a $1mil sell.
Could i have done better ? ................. "ABSOFUCKINGLUTLY" .............. plenty still around at $2.20
If you would like to read my previous few posts, ive now re-purchased those 600k (+) at more than 50% discount.
Its a game that we all play, .............. and to be quite honest, MB announced BRN chip in a "concept car" ............ years til commercilisation.
I must say i did the same at $1.05 last year.
Things with regard to BRN have changed considerably in the last 12mths, as im sure your well aware.
Its still a long road, maybe 12-24mths, but , like many i believe in the team, the tech and at these prices a definite hold for me.

DYOR ....................... AKIDA BALLISTA

 

[wilzy123]

what is wrong with that comment? Tell me, if you knew that this sp action would occur, would you have not sold at $2.30 and bought back in at these levels. Let’s see the response. I believe 99.9 % of the people in the forum would have happily taken this opportunity. You are seriously just projecting your insecurities at this point of time. It’s not cool and there is no need for it at all.

 

[Sam]

lzzzzzzzzzzzy:
you have been "vulgar, cras, and quite a pig at times.
i do think you are on many peoples ignore list.
pls dont hold a personal grudge by not "capitalizing on the MB ann 12mths ago" ............... from what i have read, many are in the same boat.
Myself ........ i sold 600k shares @ $1.58, ............ almost a $1mil sell.
Could i have done better ? ................. "ABSOFUCKINGLUTLY" .............. plenty still around at $2.20
If you would like to read my previous few posts, ive now re-purchased those 600k (+) at more than 50% discount.
Its a game that we all play, .............. and to be quite honest, MB announced BRN chip in a "concept car" ............ years til commercilisation.
I must say i did the same at $1.05 last year.
Things with regard to BRN have changed considerably in the last 12mths, as im sure your well aware.
Its still a long road, maybe 12-24mths, but , like many i believe in the team, the tech and at these prices a definite hold for me.

DYOR ....................... AKIDA BALLISTA

Yep, either that or you just hold until you see your goaltoo much stress for mine, in and out of the market…. I just wait. each to their own, so no offence.

 

[Getupthere]

what is wrong with that comment? Tell me, if you knew that this sp action would occur, would you have not sold at $2.30 and bought back in at these levels. Let’s see the response. I believe 99.9 % of the people in the forum would have happily taken this opportunity. You are seriously just projecting your insecurities at this point of time. It’s not cool and there is no need for it at all.

Just sell and move on
You are a boat anchor my friend.

This is a research site for all BRN holders.

Back to HC you go.

 

[wilzy123]

Flog

We are all better off for your contributions and different opinions here. Thank you.

 

[FlipDollar]

You must be a shorter back to hc for you

Here we go