BRN Discussion Ongoing

[Fullmoonfever]

Something I personally haven't seen before. It appears to be from a 2022 IEEE conference.

Maybe others are aware of it though?

You might recognise a couple of the authors (but are all from TCS Research India) and a couple of the references used that I pasted below

Is a purchase only one I can find so far, so abstract only, but curious as to whether it has been continued in development.

https://ieeexplore.ieee.org/abstract/document/9937951

EchoWrite-SNN: Acoustic Based Air-Written Shape Recognition Using Spiking Neural Networks​

Publisher: IEEE
Cite This


Arun M George; Andrew Gigie; A Anil Kumar; Sounak Dey; Arpan Pal; K Aditi

Abstract:​

In this paper, we propose EchoWrite-SNN, a robust edge compatible air-writing recognition system (used in applications such as AR/VR, HRI etc.) based on principles of SONAR and neuromorphic computing. The bare finger movements in air are captured by a pair of commonly available speaker-microphone pair. A new tracking algorithm based on windowed difference cross-correlation and ESPRIT is employed which shows better tracking accuracy compared to state-of-the-art methods with a median tracking error of only 3.31mm. To classify these air-written shapes, a 5-layer CNN is trained and then converted to a Spiking Neural Network (SNN) using ANN-to-SNN conversion technique to reap the benefits of low power neuromorphic computing on edge. Experimental results show that the converted SNN achieves 92% accuracy (a mere 3% less than the CNN) while showing 4.4 × reduction in number of operations compared to CNN resulting in further energy benefit when run on actual neuromorphic computation platforms.


Brainchip unveils the akidatm development environment, 2019, [online] Available: https://www.brainchipinc.com/news-media/press-releases/ detail/61/brainchip-unveils-the-akida-development-environment.

S. Dey, A. Mukherjee, G. Bzard and D. McLelland, "Human gesture recognition using spiking input on akida neuromorphic platform", Neural Information Processing Systems (NeurIPS), 2019.

 

[Diogenese]

Something I personally haven't seen before. It appears to be from a 2022 IEEE conference.

Maybe others are aware of it though?

You might recognise a couple of the authors (but are all from TCS Research India) and a couple of the references used that I pasted below

Is a purchase only one I can find so far, so abstract only, but curious as to whether it has been continued in development.

https://ieeexplore.ieee.org/abstract/document/9937951

EchoWrite-SNN: Acoustic Based Air-Written Shape Recognition Using Spiking Neural Networks​

Publisher: IEEE
Cite This


Arun M George; Andrew Gigie; A Anil Kumar; Sounak Dey; Arpan Pal; K Aditi

Abstract:​

In this paper, we propose EchoWrite-SNN, a robust edge compatible air-writing recognition system (used in applications such as AR/VR, HRI etc.) based on principles of SONAR and neuromorphic computing. The bare finger movements in air are captured by a pair of commonly available speaker-microphone pair. A new tracking algorithm based on windowed difference cross-correlation and ESPRIT is employed which shows better tracking accuracy compared to state-of-the-art methods with a median tracking error of only 3.31mm. To classify these air-written shapes, a 5-layer CNN is trained and then converted to a Spiking Neural Network (SNN) using ANN-to-SNN conversion technique to reap the benefits of low power neuromorphic computing on edge. Experimental results show that the converted SNN achieves 92% accuracy (a mere 3% less than the CNN) while showing 4.4 × reduction in number of operations compared to CNN resulting in further energy benefit when run on actual neuromorphic computation platforms.


Brainchip unveils the akidatm development environment, 2019, [online] Available: https://www.brainchipinc.com/news-media/press-releases/ detail/61/brainchip-unveils-the-akida-development-environment.

S. Dey, A. Mukherjee, G. Bzard and D. McLelland, "Human gesture recognition using spiking input on akida neuromorphic platform", Neural Information Processing Systems (NeurIPS), 2019.

Hi FMF,

I have a vague recollection of seeing this (or a similar) acoustic gesture tracking method before, but I can't put my finger on it.

 

[Fullmoonfever]

Hi FMF,

I have a vague recollection of seeing this (or a similar) acoustic gesture tracking method before, but I can't put my finger on it.

Maybe wave your finger in the air and it might come to you

 

[Baneino]

Happy blessed new year. May our course reach 3 digits. Everyone here deserves it.

 

[Fullmoonfever]

Something I personally haven't seen before. It appears to be from a 2022 IEEE conference.

Maybe others are aware of it though?

You might recognise a couple of the authors (but are all from TCS Research India) and a couple of the references used that I pasted below

Is a purchase only one I can find so far, so abstract only, but curious as to whether it has been continued in development.

https://ieeexplore.ieee.org/abstract/document/9937951

EchoWrite-SNN: Acoustic Based Air-Written Shape Recognition Using Spiking Neural Networks​

Publisher: IEEE
Cite This


Arun M George; Andrew Gigie; A Anil Kumar; Sounak Dey; Arpan Pal; K Aditi

Abstract:​

In this paper, we propose EchoWrite-SNN, a robust edge compatible air-writing recognition system (used in applications such as AR/VR, HRI etc.) based on principles of SONAR and neuromorphic computing. The bare finger movements in air are captured by a pair of commonly available speaker-microphone pair. A new tracking algorithm based on windowed difference cross-correlation and ESPRIT is employed which shows better tracking accuracy compared to state-of-the-art methods with a median tracking error of only 3.31mm. To classify these air-written shapes, a 5-layer CNN is trained and then converted to a Spiking Neural Network (SNN) using ANN-to-SNN conversion technique to reap the benefits of low power neuromorphic computing on edge. Experimental results show that the converted SNN achieves 92% accuracy (a mere 3% less than the CNN) while showing 4.4 × reduction in number of operations compared to CNN resulting in further energy benefit when run on actual neuromorphic computation platforms.


Brainchip unveils the akidatm development environment, 2019, [online] Available: https://www.brainchipinc.com/news-media/press-releases/ detail/61/brainchip-unveils-the-akida-development-environment.

S. Dey, A. Mukherjee, G. Bzard and D. McLelland, "Human gesture recognition using spiking input on akida neuromorphic platform", Neural Information Processing Systems (NeurIPS), 2019.

That's the presso fwiw. We get our small mention Pg 5

 

[Dallas]

Jim Fan on LinkedIn: There’re two algorithms that scale indefinitely: learning and search. May…

There’re two algorithms that scale indefinitely: learning and search. May you learn well and find your own green tree in 2025!

www.linkedin.com

 

[Dallas]

A.Lewis ,like this☝

 

[DingoBorat]

Just a quick thought, or two, or..

We know from recent data, that Dave took out another 10 million shorts (borrowed shares).
It's fairly obvious and I think It will be shown, that at least another "additional" 10 million shorts, were taken out and used New Year's eve.

This is circa 20 million new shorts in the system between a price of 35 and 43.5 cents (assuming none of the new ones were covered during that time).

Optimism for BrainChip, is extremely high right now, so Dave would need to take out additional shorts again, in an "effort" to further drop the share price and release trapped shorts, at much lower prices. below 30 cents (again assuming none of those have been covered).

They've up until now, effectively been trying to put out fiery demand, with petrol, with borrowed shares being eagerly snapped up.

Daves not an amateur, even if he looks like a bit of a goose sometimes, but I think he may be over the barrel somewhat at the moment..

Will he get spanked, is the question..

If the whales (or lots of hungry seals) are still around, he's definitely in trouble..

If a big positive announcement drops "shortly" forget it..

Good Luck and Happy New Year to everyone!
(except Dave, he can go and get ____)

 

[BrainShit]

Can anyone access the link.

https://inflation.us/content/brainchip-asx-brn-will-surpass-all-quantum-computing-stocks-combined

This is BS in my opinion. The site and the article.

 

[MDhere]

This 10 sec short video is music to my ears

 

[BrainShit]

This 10 sec short video is music to my ears

If you share a link, everyone could hear it.

 

[MDhere]

If you share a link, everyone could hear it.

added to post, though the highlight in pink that i made was the drawcard for me.

 

[Baisyet]

Is this the first time, we've had external media report on an investor podcast? ...

Morning @DingoBorat I was thinking the same wondering if anything to do with IP agreement recently

 

[Quercuskid]

Hmm Morningstar now gives a valuation of $0.30, they can’t quite make up their mind.

 

[Esq.111]

This 10 sec short video is music to my ears

Good Morning MDhere ,

Thay may have used random footage in the video, or........ thay may not have????

Either way the ear buds showen appear to be APPLE .

AirPods

AirPods deliver an unparalleled wireless headphone experience, from magical setup to high-quality sound. Available with free engraving.

www.apple.com

Regards,
Esq.

 

[TECH]

Good morning All,

My review that I set myself over 2.5 years ago for January 2025 was done yesterday, I feel very satisfied that progress is accelerating, I plan on buying a little more stock and have decided my next review on company overall performance will be 1 July 2026.

I'm quietly confident our share price will be north of the $2 mark, I'm expecting some IP deals between now and then, AKIDA II/TENN's embedded
in product(s), positive news on handheld medical devices, positive news on hearing aids and revenue steadily increasing as traction in the space sector really ramps up, that's what I will personally be evaluating come July 2026, and last but not least, stability within our staff ranks.

CES 2025 maybe a defining moment in time for our company, fingers crossed.

We are 100% backing a future winner...........no regerts (damn tattoo)

P.S. I wouldn't get to hung up on not hearing anything about AKIDA III, our company has enough going on with AKIDA I, AKIDA I.5, AKIDA II
and TENN's....happy to proven wrong, but listening carefully to Sean the other day, he definitely makes the point of implying that all energy
is going into AKIDA II and TENN's....in my opinion of course.

Tech (2025)

 

[Esq.111]

Good Morning Chippers ,

Well appears some Accountants , Lawyers & Solicitors were working over the holiday period.

Congratulations Weebit holders.

Should be a great day.

Regards,
Esq.

 

[Boab]

Good Morning Chippers ,

Well appears some Accountants , Lawyers & Solicitors were working over the holiday period.

Congratulations Webit holders.

Should be a great day.

Regards,
Esq.

This announcement will only enhance the number of eyes looking at all things tech related.
Happy days.

 

[Shadow59]

I

Good Morning Chippers ,

Well appears some Accountants , Lawyers & Solicitors were working over the holiday period.

Congratulations Weebit holders.

Should be a great day.

Regards,
Esq.

Hi Esqi

This announcement is interesting, in that it's considered market sensitive as an asx announcement, but look at the wording....

As part of the engagement, Weebit is required to meet several technical milestones based on an agreed workplan. Weebit will receive manufacturing license fees, non-recurring engineering fees (NRE) and royalties based on production volumes. The economic materiality of this agreement is not known at this time. However, Weebit views this commercial agreement as strategically important given onsemi’s position in the US semiconductor industry, and the commercial validation it provides for Weebit’s ReRAM technology when a company of this stature commits to Weebit’s technology, with the associated investment in preparing its own systems for production. In addition, the royalties are expected to be material over time depending on the number of products that onsemi decides to produce using Weebit’s technology.

No figures are provided on the value of the contract. I see this as a potential way around getting more announcements out for Brainchip.

 

[Bravo]

LG Unveils AI-Powered 2025 LG Gram Laptops at CES - Be Korea-savvy

SEOUL, Jan. 1 (Korea Bizwire) — LG Electronics has introduced its 2025 lineup of LG Gram laptops, featuring advanced artificial …

koreabizwire.com

EXTRACT