BRN Discussion Ongoing

[Rach2512]

Sorry if already posted, I like the fact that bimetricupdate have 3,000,000 readers each year.

BrainChip showcases AI-enabled human behavioral analysis with Akida neuromorphic computing | Biometric Update

BrainChip, a company known for its neuromorphic computing, has joined forces with NVISO Group Ltd., experts in AI software for analyzing human behavior.

www.biometricupdate.com

Date 26.2.2024

BrainChip, a company known for its neuromorphic computing, has joined forces with NVISO Group Ltd., experts in AI software for analyzing human behavior. They demonstrated an AI-powered system capable of real-time human behavioral analysis at the CES 2024. This partnership combines the strengths of both companies to offer a solution with potential applications across consumer electronics, surveillance, and automotive industries

About Us | Biometric Update

BiometricUpdate.com is the leading news property that publishes shareable breaking news, analysis, and research about the global biometrics market.

www.biometricupdate.com

Our global audience of 3,000,000 readers each year includes governments, law enforcement agencies, financial institutions and many other other vertical industries along with OEMs, service providers, system integrators, enterprise and industry professionals. Read our media kit for more audience details.

Happy Friday everyone

 

[Rach2512]

Top 5 biometric recognition methods to reimage digital banking systems in 2023 | Biometric Update

Biometric technology is transforming traditional banking methods with more advanced user authentication tactics such as voice, facial, and other analyses.

www.biometricupdate.com

No mention of Brainchip, but many areas which would benefit from Akida. Is it possible that BrainChip is being used in any of the mentioned identification processes, I would not be at all surprised if it is.

 

[Fullmoonfever]

@Diogenese

Huh???

Way above my pay grade....is it within yours?

Abhishek Anand​

Carnegie Mellon University Carnegie Mellon University​

Abhishek Anand - Carnegie Mellon University | LinkedIn

Experience: Carnegie Mellon University · Education: Carnegie Mellon University · Location: Pittsburgh · 72 connections on LinkedIn. View Abhishek Anand’s profile on LinkedIn, a professional community of 1 billion members.

www.linkedin.com

Projects​

• C3S Microarchitecture Enhancement​

  Feb 2023​

  Relax strictly synchronous clocking to asynchronous gamma clocking
  Implement spike encoder block akin to Akida sensory encoder hub
  Optimizing FF TNN for MNIST using sparse convolution??
  
  End Date: May 2023

 

[Fullmoonfever]

@Diogenese

Huh???

Way above my pay grade....is it within yours?

Abhishek Anand​

Carnegie Mellon University Carnegie Mellon University​

Abhishek Anand - Carnegie Mellon University | LinkedIn

Experience: Carnegie Mellon University · Education: Carnegie Mellon University · Location: Pittsburgh · 72 connections on LinkedIn. View Abhishek Anand’s profile on LinkedIn, a professional community of 1 billion members.

www.linkedin.com

Projects​

• C3S Microarchitecture Enhancement​

  Feb 2023​

  Relax strictly synchronous clocking to asynchronous gamma clocking
  Implement spike encoder block akin to Akida sensory encoder hub
  Optimizing FF TNN for MNIST using sparse convolution??
  
  End Date: May 2023

Just found it's to do with cortical columns by the looks.

Think this has been covered already

 

[FJ-215]

@Diogenese

Huh???

Way above my pay grade....is it within yours?

Abhishek Anand​

Carnegie Mellon University Carnegie Mellon University​

Abhishek Anand - Carnegie Mellon University | LinkedIn

Experience: Carnegie Mellon University · Education: Carnegie Mellon University · Location: Pittsburgh · 72 connections on LinkedIn. View Abhishek Anand’s profile on LinkedIn, a professional community of 1 billion members.

www.linkedin.com

Projects​

• C3S Microarchitecture Enhancement​

  Feb 2023​

  Relax strictly synchronous clocking to asynchronous gamma clocking
  Implement spike encoder block akin to Akida sensory encoder hub
  Optimizing FF TNN for MNIST using sparse convolution??
  
  End Date: May 2023

Ok.... C3S in google

Cortical Columns Computing

An example.........

Cortical Columns Computing Systems:

 

[FJ-215]

Just found it's to do with cortical columns by the looks.

Think this has been covered already

Too quick

 

[Frank Zappa]

View attachment 58275

Do you know where we currently are in the standings, Frank?

Definitely out of favour. I think the ASX will look very carefully at us before they will admit us again .

 

[HopalongPetrovski]

Definitely out of favour. I think the ASX will look very carefully at us before they will admit us again .

Fine. From what I have seen pre revenue companies with some surrounding hype seem to get eaten alive.
Going into the 300 puts a short target on our back which is then executed upon entry into the 200.
It is a road we will have to travel eventually as our success mounts but I hope for a more gradual and sustained climb this time around supported by new licences and an ongoing revenue stream to help pay our way, rather than further dilution through the LDA arrangement.

 

[zeeb0t]

Wow great stuff!
Is 11800 unique IP addresses or could non-members be counted as duplicates per session?

Cheers for that Zeebot

So 11800/30 is 393.33
(393 people and a shorter, on average per day, across all company forums).

Can you tell if page views are unique?
Or if I come back to this page several times, to view new posts, I'm assuming that's counted as a view?

I think it's pretty obvious, that while we are probably the most informed BRN holders, outside of the Company itself, we are indeed a select group.

Which says 2 things.

1) We are very fortunate to have an almost "exclusive" access, to the information on this forum.

But more importantly.

2) We are "still" on the ground floor, in regards to our investment, in this Company and the Lion's share of new investor interest has occurred from outside share forums.
(seeing as ours is informationally the best).

Users are counted by Google who do a pretty good job of tracking and figuring out who is a new user and who is a return user. The number of users is new users during the period.

The page views are then impressions of pages viewed by that number of users.

 

[Diogenese]

@Diogenese

Huh???

Way above my pay grade....is it within yours?

Abhishek Anand​

Carnegie Mellon University Carnegie Mellon University​

Abhishek Anand - Carnegie Mellon University | LinkedIn

Experience: Carnegie Mellon University · Education: Carnegie Mellon University · Location: Pittsburgh · 72 connections on LinkedIn. View Abhishek Anand’s profile on LinkedIn, a professional community of 1 billion members.

www.linkedin.com

Projects​

• C3S Microarchitecture Enhancement​

  Feb 2023​

  Relax strictly synchronous clocking to asynchronous gamma clocking
  Implement spike encoder block akin to Akida sensory encoder hub
  Optimizing FF TNN for MNIST using sparse convolution??
  
  End Date: May 2023

I'm guessing Fast Fourier Temporal NN.

Fourier transform breaks a signal down to individual signwave components - fundamental frequency and decreasing harmonics.

Fast Fourier is a digital mathematical shortcut. Very common in signal analysis.

Could be used, eg, in analysing different vibration patterns, spectrum analysis ...

Funnily, Gamma cycles are the decaying oscillations from nerve stimulation which Thorpe, in developing N-of-M coding, showed to be redundant, the leading spike carrying the useful data and the oscillations being unreliable above 10Hz.

Looks like Carnegie has been playing with Akida 2 TeNNs.

https://www.researchgate.net/public...r_Block_and_Relaxing_Gamma_Clock_Asynchronous

The Temporal Neural Network(TNN) style of architecture is a good basis for approximating biological neurons due to its use of timed pulses to encode data and a voltage-threshold-like system. Using the Temporal Neural Network cortical column C3S architecture design as a basis, this project seeks to augment the network's design. This project takes note of two ideas and presents their designs with the goal of improving existing cortical column architecture. One need in this field is for an encoder that could convert between common digital formats and timed neuronal spikes, as biologically accurate networks are temporal in nature. To this end, this project presents an encoder to translate between binary encoded values and timed spikes to be processed by the neural network. Another need is for the reduction of wasted processing time to idleness, caused by lengthy Gamma cycle processing bursts. To this end, this project presents a relaxation of Gamma cycles to allow for them to end arbitrarily early once the network has determined an output response. With the goal of contributing to the betterment of the field of neuromorphic computer architecture, designs for both a binary-to-spike encoder, as well as a Gamma cycle controller, are presented and evaluated for optimal design parameters, with overall system gain and performance.

CONCLUSIONS
Both the encoder and Gamma cycle control system have the potential to be useful additions to the C3S code base [1]. Encoding from binary to spike times is an essential means for communication and data transmission between the two worlds of existing media formats and the evolving TNN infrastructure. This value has been recognized by groups such as BrainChip through their inclusion of such encoders on their novel Akida processor [8]. A binary-to-spike encoder should be added to any upcoming neuromorphic system, for the world we live in is rife with data formats that do not fit well into a TNN style of data processing. The control and potential shortening of Gamma cycles possess the potential to take networks made with C3S columns and layers and improve the speed at which they perform their learning objectives. The potential for reducing the duration of Gamma cycles (and thus increase performance by) by upwards of 68% percent, is significant. Additionally, the inclusion of such a control architecture may bring neuromorphic systems one step closer to the simulation of actual animal brains, which themselves do not always work on consistent frequencies. The benefits of our work are products as modules that add to furthering of neuromorphic architectural research and should be integrated where possible to augment existing TNN neuromorphic systems

FN: Thorpe says that Gammas faster than 0.1 s have been shown to be unreliable. Akida is clocked at 300 MHz, so that's 30 million times faster. Working with Gammas will slow a NN to a snail's pace.

 

[DingoBorat]

I'm guessing Fast Fourier Temporal NN.

Fourier transform breaks a signal down to individual signwave components - fundamental frequency and decreasing harmonics.

Fast Fourier is a digital mathematical shortcut. Very common in signal analysis.

Could be used, eg, in analysing different vibration patterns, spectrum analysis ...

Funnily, Gamma cycles are the decaying oscillations from nerve stimulation which Thorpe, in developing N-of-M coding, showed to be redundant, the leading spike carrying the useful data and the oscillations being unreliable above 10Hz.

Looks like Carnegie has been playing with Akida 2 TeNNs.

https://www.researchgate.net/public...r_Block_and_Relaxing_Gamma_Clock_Asynchronous

The Temporal Neural Network(TNN) style of architecture is a good basis for approximating biological neurons due to its use of timed pulses to encode data and a voltage-threshold-like system. Using the Temporal Neural Network cortical column C3S architecture design as a basis, this project seeks to augment the network's design. This project takes note of two ideas and presents their designs with the goal of improving existing cortical column architecture. One need in this field is for an encoder that could convert between common digital formats and timed neuronal spikes, as biologically accurate networks are temporal in nature. To this end, this project presents an encoder to translate between binary encoded values and timed spikes to be processed by the neural network. Another need is for the reduction of wasted processing time to idleness, caused by lengthy Gamma cycle processing bursts. To this end, this project presents a relaxation of Gamma cycles to allow for them to end arbitrarily early once the network has determined an output response. With the goal of contributing to the betterment of the field of neuromorphic computer architecture, designs for both a binary-to-spike encoder, as well as a Gamma cycle controller, are presented and evaluated for optimal design parameters, with overall system gain and performance.

CONCLUSIONS
Both the encoder and Gamma cycle control system have the potential to be useful additions to the C3S code base [1]. Encoding from binary to spike times is an essential means for communication and data transmission between the two worlds of existing media formats and the evolving TNN infrastructure. This value has been recognized by groups such as BrainChip through their inclusion of such encoders on their novel Akida processor [8]. A binary-to-spike encoder should be added to any upcoming neuromorphic system, for the world we live in is rife with data formats that do not fit well into a TNN style of data processing. The control and potential shortening of Gamma cycles possess the potential to take networks made with C3S columns and layers and improve the speed at which they perform their learning objectives. The potential for reducing the duration of Gamma cycles (and thus increase performance by) by upwards of 68% percent, is significant. Additionally, the inclusion of such a control architecture may bring neuromorphic systems one step closer to the simulation of actual animal brains, which themselves do not always work on consistent frequencies. The benefits of our work are products as modules that add to furthering of neuromorphic architectural research and should be integrated where possible to augment existing TNN neuromorphic systems

FN: Thorpe says that Gammas faster than 0.1 s have been shown to be unreliable. Akida is clocked at 300 MHz, so that's 30 million times faster. Working with Gammas will slow a NN to a snail's pace.

 

[Boab]

I'm guessing Fast Fourier Temporal NN.

Fourier transform breaks a signal down to individual signwave components - fundamental frequency and decreasing harmonics.

Fast Fourier is a digital mathematical shortcut. Very common in signal analysis.

Could be used, eg, in analysing different vibration patterns, spectrum analysis ...

Funnily, Gamma cycles are the decaying oscillations from nerve stimulation which Thorpe, in developing N-of-M coding, showed to be redundant, the leading spike carrying the useful data and the oscillations being unreliable above 10Hz.

Looks like Carnegie has been playing with Akida 2 TeNNs.

https://www.researchgate.net/public...r_Block_and_Relaxing_Gamma_Clock_Asynchronous

The Temporal Neural Network(TNN) style of architecture is a good basis for approximating biological neurons due to its use of timed pulses to encode data and a voltage-threshold-like system. Using the Temporal Neural Network cortical column C3S architecture design as a basis, this project seeks to augment the network's design. This project takes note of two ideas and presents their designs with the goal of improving existing cortical column architecture. One need in this field is for an encoder that could convert between common digital formats and timed neuronal spikes, as biologically accurate networks are temporal in nature. To this end, this project presents an encoder to translate between binary encoded values and timed spikes to be processed by the neural network. Another need is for the reduction of wasted processing time to idleness, caused by lengthy Gamma cycle processing bursts. To this end, this project presents a relaxation of Gamma cycles to allow for them to end arbitrarily early once the network has determined an output response. With the goal of contributing to the betterment of the field of neuromorphic computer architecture, designs for both a binary-to-spike encoder, as well as a Gamma cycle controller, are presented and evaluated for optimal design parameters, with overall system gain and performance.

CONCLUSIONS
Both the encoder and Gamma cycle control system have the potential to be useful additions to the C3S code base [1]. Encoding from binary to spike times is an essential means for communication and data transmission between the two worlds of existing media formats and the evolving TNN infrastructure. This value has been recognized by groups such as BrainChip through their inclusion of such encoders on their novel Akida processor [8]. A binary-to-spike encoder should be added to any upcoming neuromorphic system, for the world we live in is rife with data formats that do not fit well into a TNN style of data processing. The control and potential shortening of Gamma cycles possess the potential to take networks made with C3S columns and layers and improve the speed at which they perform their learning objectives. The potential for reducing the duration of Gamma cycles (and thus increase performance by) by upwards of 68% percent, is significant. Additionally, the inclusion of such a control architecture may bring neuromorphic systems one step closer to the simulation of actual animal brains, which themselves do not always work on consistent frequencies. The benefits of our work are products as modules that add to furthering of neuromorphic architectural research and should be integrated where possible to augment existing TNN neuromorphic systems

FN: Thorpe says that Gammas faster than 0.1 s have been shown to be unreliable. Akida is clocked at 300 MHz, so that's 30 million times faster. Working with Gammas will slow a NN to a snail's pace.

So grateful that you walk among us Dodgy Knees. Good health to you Sir. Thank you very much.

 

[Fullmoonfever]

I'm guessing Fast Fourier Temporal NN.

Fourier transform breaks a signal down to individual signwave components - fundamental frequency and decreasing harmonics.

Fast Fourier is a digital mathematical shortcut. Very common in signal analysis.

Could be used, eg, in analysing different vibration patterns, spectrum analysis ...

Funnily, Gamma cycles are the decaying oscillations from nerve stimulation which Thorpe, in developing N-of-M coding, showed to be redundant, the leading spike carrying the useful data and the oscillations being unreliable above 10Hz.

Looks like Carnegie has been playing with Akida 2 TeNNs.

https://www.researchgate.net/public...r_Block_and_Relaxing_Gamma_Clock_Asynchronous

The Temporal Neural Network(TNN) style of architecture is a good basis for approximating biological neurons due to its use of timed pulses to encode data and a voltage-threshold-like system. Using the Temporal Neural Network cortical column C3S architecture design as a basis, this project seeks to augment the network's design. This project takes note of two ideas and presents their designs with the goal of improving existing cortical column architecture. One need in this field is for an encoder that could convert between common digital formats and timed neuronal spikes, as biologically accurate networks are temporal in nature. To this end, this project presents an encoder to translate between binary encoded values and timed spikes to be processed by the neural network. Another need is for the reduction of wasted processing time to idleness, caused by lengthy Gamma cycle processing bursts. To this end, this project presents a relaxation of Gamma cycles to allow for them to end arbitrarily early once the network has determined an output response. With the goal of contributing to the betterment of the field of neuromorphic computer architecture, designs for both a binary-to-spike encoder, as well as a Gamma cycle controller, are presented and evaluated for optimal design parameters, with overall system gain and performance.

CONCLUSIONS
Both the encoder and Gamma cycle control system have the potential to be useful additions to the C3S code base [1]. Encoding from binary to spike times is an essential means for communication and data transmission between the two worlds of existing media formats and the evolving TNN infrastructure. This value has been recognized by groups such as BrainChip through their inclusion of such encoders on their novel Akida processor [8]. A binary-to-spike encoder should be added to any upcoming neuromorphic system, for the world we live in is rife with data formats that do not fit well into a TNN style of data processing. The control and potential shortening of Gamma cycles possess the potential to take networks made with C3S columns and layers and improve the speed at which they perform their learning objectives. The potential for reducing the duration of Gamma cycles (and thus increase performance by) by upwards of 68% percent, is significant. Additionally, the inclusion of such a control architecture may bring neuromorphic systems one step closer to the simulation of actual animal brains, which themselves do not always work on consistent frequencies. The benefits of our work are products as modules that add to furthering of neuromorphic architectural research and should be integrated where possible to augment existing TNN neuromorphic systems

FN: Thorpe says that Gammas faster than 0.1 s have been shown to be unreliable. Akida is clocked at 300 MHz, so that's 30 million times faster. Working with Gammas will slow a NN to a snail's pace.

Thanks for the explanation.

Thought may be something to do with Fourier Transform as I've seen the FFT or FF used before but wasn't sure.

There are some indicators in charting that use the same underlying mathematical modelling that I've seen relating to time series or sequences / cycles.

 

[Jumpchooks]

Cheers for that Zeebot

So 11800/30 is 393.33
(393 people and a shorter, on average per day, across all company forums).

Can you tell if page views are unique?
Or if I come back to this page several times, to view new posts, I'm assuming that's counted as a view?

I think it's pretty obvious, that while we are probably the most informed BRN holders, outside of the Company itself, we are indeed a select group.

Which says 2 things.

1) We are very fortunate to have an almost "exclusive" access, to the information on this forum.

But more importantly.

2) We are "still" on the ground floor, in regards to our investment, in this Company and the Lion's share of new investor interest has occurred from outside share forums.
(seeing as ours is informationally the best).

Over Analysis leads to Paralysis



However, Akida when you needa



can help you at the edge,,, aahhh



Good Luck to All Investa



goodnight sleep well xox

 

[DingoBorat]

I'm just conservative when it comes to the balance sheet. We have good cash reserves now and if you include what is available thru LDA (whenever it comes) we have something like a 2 year runway. Add in a handful or 3 of IP licenses and royalties on top and it will be better again.

We are on our way!!!

Edit...

We will need to lodge an application for new securities with the ASX for the new shares. Same as we did for the previous ones back in December

Was ready to say I was wrong and apologise profusely..

But I checked the announcements for December last year and if you're talking about the quotation of securities on the 4th of December, that was also the date of the Capital Call..

So there!

 

[supersonic001]

#aapl #arm #tsm | Raghavendra Anjanappa | 17 comments

This infographic created breaks down most of the key logic board chip suppliers for #AAPL's new Vision Pro. It's worth noting that the main M2 processor is designed in-house by Apple, based on #ARM's instruction sets, and manufactured by #TSM. The processor is also supported by Apple's new R1...

www.linkedin.com

Not sure if posted already ….

 

[JoMo68]

Well , you would think with the last couple of weeks in tech stocks , Analysts should have given Brainchip a rather substantial probing by now.

Time to load up ,

Wall Street Bull.

Regards,
Esq.

Is that you Dickleboro!?

 

[JoMo68]

Hi @Diogenese,

Are you able to find out more about this recent Apple patent involving a "Customizable Chip for AI applications".

It says here it involves neural networks and approximates the operation of a human brain.



View attachment 58255

A neutral network Interesting…

 

[GazDix]

Why a bull and a bear?

Bulls and Bears are pretty aggressive animals. Bull is frightening if you wear red and bears are like us really but bigger and like lollies.

What would be the Australian version? I vote Kangaroo and Wombat market. Makes much more sense than what the American market prescribes to us (and the rest of the world).

Fundamentals are everything because we have been fed a whole lot of bollocks all of our lives from mainstream media.

Just an example of how I think Akida will think. Apart from the bollock line.

 

[Damo4]