BRN Discussion Ongoing

stuart888

Regular
Simon Thorpe!

I cannot understand how this video has only 4K viewers? I have watched it at least 3 times, N-of-M and all the spiky goodness.

The Mobile World Congress was all Edge AI Inference, no Cloud! AI Edge with Privacy, no cloud.



1712014409975.png
 
  • Like
  • Fire
  • Love
Reactions: 32 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Last edited:
  • Like
  • Fire
  • Love
Reactions: 68 users

Diogenese

Top 20
Simon Thorpe!

I cannot understand how this video has only 4K viewers? I have watched it at least 3 times, N-of-M and all the spiky goodness.

The Mobile World Congress was all Edge AI Inference, no Cloud! AI Edge with Privacy, no cloud.



View attachment 60131

Hi Stuart,

This is a superb discussion of N/M coding. while ST's group managed to produce a software simulation, PvdM's inspiration was to realize that it could be implemented in silicon.

It's amazing to think that the basic research which led to N/M was done in the 1920s. I guess the only detector sensitive and responsive enough for those measurements would have been the cathode ray tube. (Prof Google tells me that the cathode ray tube was invented by Karl Ferdinand Braun in 1897.)

The video is from 2021.

Do you have a direct link?
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 18 users

Diogenese

Top 20
  • Haha
Reactions: 2 users

Esq.111

Fascinatingly Intuitive.
Afternoon Chippers ,

Just stumbled across this company , they are to be listed shortly apparently.

Started by boffins at Princeton University,



Henk-Jan Boele
CEO



BlinkLab Limited (ASX:BB1)​


Follow
Share Price
-
Market Cap
-
Status
Upcoming

News
About
Price Chart
Reports
Dividends

Latest News​


��
TitleTypeDate
There is no news available for BlinkLab Limited.

News Notifications
Follow BlinkLab Limited (ASX:BB1) for email alerts and the latest news in your newsfeed
Follow

About​

BlinkLab Limited (ASX:BB1) stands poised to change the landscape of diagnosing and treating neurodevelopmental conditions like ASD and ADHD in children.
BlinkLab's innovative approach leverages the power of smartphones, AI and Machine Learning to deliver screening tests specifically designed for children as young as 18 months old. This marks a significant advancement, considering traditional diagnoses typically occur around five years of age, often missing the crucial early window for effective intervention.
BlinkLab, a company started by neuroscientists at Princeton University, over the past several years have fully developed a smartphone based diagnostic platform and is seeking to finalise an FDA Class II medical device registration study in partnership with leading US university hospitals. This approval will pave the way for broad use of the Company's technology in diagnosing and treating conditions like ASD and ADHD.
Why invest in BlinkLab?
Early Detection:
The Company's technology detects potential neurological conditions in children as young as 18 months, significantly earlier than traditional methods (around five years old). This critical window allows for timely intervention, maximising treatment effectiveness and improving long-term outcomes.
Proven Technology: Extensive multi-national clinical trials have already validated the apps efficacy and safety.
Addressing a Critical Need: ASD and ADHD diagnosis and treatment represent a significant cost burden on healthcare systems globally. Early detection through BlinkLab has the potential to improve efficiency, reduce costs, and ultimately benefit countless families.
Strong Partnerships: Future and ongoing research collaborations with prestigious university hospitals underscores the scientific merit and clinical potential of our technology.

BlinkLab is led by an experienced management team and directors with a proven track record in building companies and vast knowledge in digital healthcare, computer vision, AI and Machine Learning. The Company's Scientific Advisory board consists of leading experts in the field of ASD and Brain Development allowing it to bridge most advanced technological innovations with groundbreaking scientific research.
Together, this powerful combination of leadership and scientific expertise enables BlinkLab to:
  • develop clinically relevant solutions based on real-world needs;
  • navigate the regulatory landscape efficiently and effectively; and
  • deliver meaningful results for children, families, and the healthcare system
Share

Share Price Chart​

6 Months


There is no price information available for BlinkLab Limited.

Share Price History​

Select a Date:




��
DateOpenLastChangeChange %HighLowVolume
There is no price history available for BlinkLab Limited.

Annual Reports​

��
NameDate
There are no annual reports available for BlinkLab Limited.

Upcoming Dividend Dates​

��
TypeEx-Dividend DatePayment DateDividendFranking
There are no upcoming dividend dates for BlinkLab Limited.

Dividend History​

��
TypeEx-Dividend DatePayment DateDividendFrankingDRP
There is no dividend history for BlinkLab Limited.

Company Resources​



BlinkLab is a world-first, AI-driven digital healthcare venture, that uses a smartphone and facial recognition to detect autism and ADHD.

It’s listing on the ASX next Thursday (April 4) under the code BB1.

BlinkLab’s development is being led by chair Brian Leedman – a founder of ResApp Health – the cough analysis app sold to Pfizer two years ago in a $179 million deal.

Now Brian’s confident that BlinkLab – first developed at Princeton University – could mirror that success, while also fast-tracking detection of Autism and ADHD and improving patient outcomes.

“We’re the only company in the world using computer vision and machine learning to assess brain responses to audio and visual stimulation – delivered via a smartphone – to detect autism and ADHD,” Mr Leedman said.

https://media.hotcrapper.com.au/embed/bf9cq6gmz6pxicr9z22nff7yug/1/large
“It’s easy for a doctor or specialist to use as a diagnostic tool. We can diagnose children from 18 months old, which is years younger than through traditional methods that typically result in children being diagnosed from the age of five,” he said.

“By the time a child reaches five years old, neuronal development in the brain has significantly advanced as have the behavioural patterns that led to the concerns of the parents. If the child is autistic, then they were autistic from birth.

“As in all medicines, the earlier you can diagnose anyone with anything, the better the outcomes for the patient.”

There are lengthy diagnosis delays both here in Australia and abroad, so the demand for such a tool is extensive.

The global Autism Spectrum Disorder market is expected to reach $700 billion by 2028​

BlinkLab uses AI and machine learning algorithms to predict autism and ADHD and recent clinical trials demonstrated sensitivity of 85% and specificity of 84%, suggesting much higher accuracy comparing to existing FDA approved products.

“Based on clinical trial results to date, we have a very accurate test for autism and we now have to replicate that in a US FDA (Food and Drug Administration) medical device registration study,” Brian Leedman said.

“The NDIS in Australia has come under scrutiny for the tremendous cost to the Australian taxpayer over the fact that ASD (Autism Spectrum Disorder) diagnosis and treatment in children is the single largest expenditure – so the timing for this technology development and ASX listing is spot on.”

Industry data suggests more than a third of those claiming through NDIS report the primary condition of autism. The NDIS paid out $6.73 billion dollars in payments to support those Australians last year alone. What’s also concerning is that the figure was 28 per cent higher than for the previous year, 2022. Autism rates in Australia are among the highest in the world and effect 1 in 25 children.

https://media.hotcrapper.com.au/embed/bdbzigqmjhnxgb4keo0av9657a/1/largeBlinkLab uses AI and machine learning algorithms to predict autism and ADHD and in recent clinical trials demonstrated sensitivity of 85%
BlinkLab’s FDA trial will recruit up to 500 people, and to fund it, BB1 is raising $7 million through the IPO process with 20 cent shares. It plans to complete the study by mid-next year with the aim of gaining FDA approval by 2026. The neurometric testing technology is also being developed and studied for its efficacy in screening for schizophrenia and forms of dementia.

Backed by Princeton University

BlinkLab has an exclusive global commercial licence agreement with Princeton University, where Founders Dr Henk-Jan Boele, Peter Boele and Bas Koekkoek first created early iterations of the idea. It’s come a long way since then with $4.4 million spent on the Software as a Medical Device development. There’ve been 6000 individual diagnostic tests already carried out throughout the world, including eight studies as far afield as Morocco and Ecuador.

The company has forged numerous partnerships with credible institutions including Princeton University, Penn Medicine, Erasmus MC, Baylor College of Medicine, and many others.

No safety risk, BlinkLab just has to prove efficacy

Mr Leedman said another advantage in developing medtech such as BlinkLab was that there could be no safety risks or delays.

“The worst that can happen is the phone is dropped on your foot – literally,” he said.

“That means we don’t face the long and slow process of testing for safety, we just have to prove efficacy.”

Aside from his success with ResApp Health, it’s worth mentioning that Mr Leedman has also chaired Neurotech International (ASX:NTI) which is developing the use of very low THC oral cannabis drug candidate NTI164 for children with autism. During his tenure, the share price had risen over 1,000%.

“This is a natural progression for me,” Brian Leedman said.

“Everything I’ve done is highly relevant to getting BlinkLab to this point and strengthens my belief that we have something truly special here.”


Regards ,
Esq.
 
  • Like
  • Fire
  • Wow
Reactions: 22 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
  • Haha
  • Like
  • Wow
Reactions: 14 users

Damo4

Regular
  • Like
  • Fire
Reactions: 14 users
View attachment 60135




View attachment 60134


Now that it is written here in black and white for all to clearly see Sony is looking at developing SNN offering positions to build Neuromorphic products. This tells me they have been involved for a good long period of time to evaluate this technology prior to the companys conclusion SNN is of value to them in the market
Brainchip as far as we all know is the only company whom offer a complete SNN series of products for testing and integration to potential customers. This tells me that they may very well have been one of the company whom most likely are still under NDA with BRN.
Go brainchip
 
  • Like
  • Fire
  • Love
Reactions: 27 users

stuart888

Regular
MedLM. Kind of figured google would win in other industries.

They make my life a lot better and with no cost. I am a big fan.

 
  • Fire
  • Like
Reactions: 4 users

Diogenese

Top 20
Now that it is written here in black and white for all to clearly see Sony is looking at developing SNN offering positions to build Neuromorphic products. This tells me they have been involved for a good long period of time to evaluate this technology prior to the companys conclusion SNN is of value to them in the market
Brainchip as far as we all know is the only company whom offer a complete SNN series of products for testing and integration to potential customers. This tells me that they may very well have been one of the company whom most likely are still under NDA with BRN.
Go brainchip
Synsense has both analog and digital SNNs and they have used their analog Dynap (Speck) SNN with Prophesee for vision:

US2023385617A1 SIGNAL PROCESSING METHOD FOR NEURON IN SPIKING NEURAL NETWORK AND METHOD FOR TRAINING SAID NETWORK 20210716

1712022249154.png





SynSense | Neuromorphic Developers Partner to Integrate Sensor, Processor – EETimes | SynSense



SALLY WARD-FOXTON

And remind me, this is mixed-signal or digital?

DYLAN MUIR

This is fully digital. It’s an asynchronous digital architecture. I mean the pixel itself obviously has got some analog components for the photo detector and so on. But the processing side is fully digital.

SALLY WARD-FOXTON

Seems like you have two families of chip. The one that’s in this Speck module. And then there’s another family, which is newer, or older?

DYLAN MUIR

Xylo – it’s a little bit newer. So that’s we’re targeting that for natural signal processing, meaning audio, biosignals, vibration, IMU/accelerometers, things like this. We’ve had a few tapeouts already for the Xylo, we have a dev kit available with an audio version, so that includes a little digital processor core plus a very efficient audio front end. We have a recent publication, some presentations from the end of last year where we’re demonstrating ultra-low power audio processing applications on that chip at a few hundred microwatts. So the idea then of course is also smart low power edge sensory processing. The family will have a common processor architecture plus a number of very efficient sensory interfaces. So we have audio out already, we have an IMU sensory interface which we’re bringing up and testing actually at the moment. We plan to have samples available at the end of this year, beginning of next year, and then there will be other sensory interfaces for other classes of application as well. Yeah, we’ll take these in turn for the use cases that that look like the most commercially accessible.

It’s a different architecture, so Speck is really tailored for vision processing applications and it does very efficient convolutional neural network inference. Xylo is a more general-purpose architecture for mostly non convolutional network architectures. It also has a more advanced neuron model. So it’s still spiking neurons of course, the spiking neurons on Speck are very simple. They’re essentially just a digital counter with no temporal dynamics, whereas the neurons on Xylo are a simulation of a a leaky integrate and fire spiking neuron, a very standard neuron model, including these temporal dynamics, which are very configurable on the chip, so that that’s really suited for temporal signal processing. So when we do things like keyword spotting for example, for audio processing, the standard neural network approach is to buffer 100 milliseconds or 50 milliseconds of audio, produce a spectrogram for that 100 milliseconds, and then treat that as an image.

We don’t do that. We really operate in a continuous streaming mode, where we process the audio as it comes into the device meaning we can have potentially lower latency. We don’t need to do buffering, we don’t need… We can get away with smaller resources for the temporal signal processing, because we’ve got this temporal integration of information in the neurons themselves. and so this lets us operate at lower power.

The Xylo chip is synchronous digital. The reason for the difference is the DVS sensor is fundamentally asynchronous itself, and if you’ve got a static camera application, then there can be basically nothing changing, nothing going on in the visual scene, and then you get basically no input and you don’t need to do anything. Whereas for audio processing, you’ve always got ambient sound coming in and so you essentially need to be processing continuously and then the synchronous digital design is a simpler design
.

So essentially we have a digital clocked simulation of the leaky integrate and fire dynamics on Xylo. And so your input clock frequency might be for example 5 megahertz, but then the network dynamics can be slower than this. You can choose to integrate over several seconds and then the simulation of each individual neuron is computed inside Xylo, but you can choose a long time scale to continuously integrate information inside the neuron, if you if you so desire. It’s essentially a little a little synchronous ASIC core for inference in spiking neurons, including these temporal dynamics. So we’re just running a little digital simulation of the of the spiking neuron dynamics
.

SALLY WARD-FOXTON

Last time we spoke, which admittedly was a while ago, you had partnered with Prophesee, also. How is that collaboration going?

DYLAN MUIR

That’s going very well. We’ve fabricated a device with Prophesee, and this is… we’re testing this, examining this at the moment, in conjunction with them.

SALLY WARD-FOXTON

OK, to be clear, it uses a different processor that you’ve made compared to the Speck module – or the same?

DYLAN MUIR

The processor IP is basically the same, same design, that’s our processor design for Speck. These little DYNAP-CNN cores and that’s what we apply for CNN processing. So we’ve also looked at, for example, an RGB standard CMOS camera interface which we could then also process using the same spiking CNN architecture
.
 
  • Like
  • Fire
  • Love
Reactions: 15 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
I wonder what Prophesee is working on with our 2nd gen AKIDA along with all the bells, whistles, vision transformers and TENNs?

Remember this quote from Lucca Verre?


Screenshot 2024-04-02 at 1.47.02 pm.png



BTW, I'm going to assume these smart glasses which Zinn Labs and Prophesee are working on, would be vastly improved with the aid of the AKIDA gen 2.

Event Based Eye Tracking - Zinn Labs | Prophesee

YouTube·PROPHESEE Metavision Technologies·29 Feb 2024



PS: If I hear "let me look that up for you" one more time, I'm going to go cray-cray!
 
Last edited:
  • Like
  • Love
  • Wow
Reactions: 11 users

Diogenese

Top 20
I wonder what Prophesee is working on with our 2nd gen AKIDA along with all the bells, whistles, vision transformers and TENNs?

Remember this quote from Lucca Verre?


View attachment 60142


BTW, I'm going to assume these smart glasses which Zinn Labs and Prophesee are working on, would be vastly improved with the aid of the AKIDA gen 2.

Event Based Eye Tracking - Zinn Labs | Prophesee

YouTube·PROPHESEE Metavision Technologies·29 Feb 2024



PS: If I hear "let me look that up for you" one more time, I'm going to go cray-cray!

"Just a sec"?
 
  • Haha
  • Like
Reactions: 9 users

davidfitz

Regular
  • Like
  • Fire
  • Love
Reactions: 21 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
In other news, I'm not really surprised the share price went up a bit today because I've had to shovel some mulch. I have noticed that the SP has a tendency to increase a fair bit more if I go for a run around the block as opposed to doing shovelling work, but I'll take whatever I can get.

If you are a chartist and you think you might be interested in this phenomenon and how it all works, you can PM me and I'll tell you all about it.

This is not financial advice.
 
  • Haha
  • Like
  • Thinking
Reactions: 37 users

Shadow59

Regular
In other news, I'm not really surprised the share price went up a bit today because I've had to shovel some mulch. I have noticed that the SP has a tendency to increase a fair bit more if I go for a run around the block as opposed to doing shovelling work, but I'll take whatever I can get.

If you are a chartist and you think you might be interested in this phenomenon and how it all works, you can PM me and I'll tell you all about it.

This is not financial advice.
Thanks for your tireless and unselfish good work Bravo
 
  • Like
  • Haha
  • Love
Reactions: 12 users

HopalongPetrovski

I'm Spartacus!
In other news, I'm not really surprised the share price went up a bit today because I've had to shovel some mulch. I have noticed that the SP has a tendency to increase a fair bit more if I go for a run around the block as opposed to doing shovelling work, but I'll take whatever I can get.

If you are a chartist and you think you might be interested in this phenomenon and how it all works, you can PM me and I'll tell you all about it.

This is not financial advice.
I wonder what would happen if you tried shovelling shit??? 🤣🤣🤣

 
  • Haha
  • Like
Reactions: 11 users

Esq.111

Fascinatingly Intuitive.
Afternoon Chippers ,

How's this screen shot for how corrupt the market is....

People want to buy at $0.34 with sellers at $0.34 ......... and nothing moving.



Regards,
Esq
 

Attachments

  • 20240402_144940.jpg
    20240402_144940.jpg
    4 MB · Views: 156
  • Like
  • Haha
  • Fire
Reactions: 18 users

HopalongPetrovski

I'm Spartacus!
Afternoon Chippers ,

How's this screen shot for how corrupt the market is....

People want to buy at $0.34 with sellers at $0.34 ......... and nothing moving.



Regards,
Esq
Occasionally we get a peek behind the wizard's curtains. 🤣
Gotta give em time to get the ducks in a row Esq.
On this occasion the "preferred buyer's" were still on the heli-deck finishing their cigars. 🤣


giphy.gif
 
  • Haha
  • Fire
Reactions: 8 users

HopalongPetrovski

I'm Spartacus!
Well, the share price seems to react extremely positively the worse the activity is, so I'm not at all opposed to this idea!

I suspect the biggest challenge will be getting my hands on a truckload of 💩 and after that we can investigate what it does to our share portfolios. 🚀🚀🚀
I think T&J over on the crapper can help you with that.
Somewhat it's stock in trade.
Whilst it has been fairly quiet today I think it's back on the clock. 🤣
 
  • Haha
  • Like
Reactions: 7 users

Rskiff

Regular
Well, the share price seems to react extremely positively the worse the activity is, so I'm not at all opposed to this idea!

I suspect the biggest challenge will be getting my hands on a truckload of 💩 and after that we can investigate what it does to our share portfolios. 🚀🚀🚀
Just go to HCrapper, there was so much over there.
 
  • Haha
Reactions: 6 users
Top Bottom