BRN Discussion Ongoing

M_C

Founding Member
1000006857.png
 
  • Like
  • Fire
  • Wow
Reactions: 17 users

Perhaps

Regular
https://www.linkedin.com/posts/ai-l...2-N6oo?utm_source=share&utm_medium=member_ios

Couple of things I noticed in this post that I thought was interesting:

1. Real time processing
2. Predictive maintenance

They might just be small statements and hashtags, but with a known partnership I think they hold a little weight behind them.

The question to ask is. How are they achieving real time processing and predictive maintenance? Is it cloud based or on device in real time like Akida like to differentiate themself?
The term real time processing is widely used for cloud based systems with lots of computing power behind, so it isn't related to Edge AI directly.

1697626490242.png



1697626610902.png


 
Last edited:
  • Like
Reactions: 9 users

Sam

Nothing changes if nothing changes
  • Like
  • Haha
Reactions: 4 users

M_C

Founding Member
Last edited:
  • Like
  • Fire
  • Love
Reactions: 44 users

Esq.111

Fascinatingly Intuitive.
Good Morning Chippers,

Just perusing the CNBC news site .... apparently CHAT GP3 can now trawl through the latest internet data.

For those who know how to operate such tech this may provide more links to articles / undisclosed partners of 🧠chip ....... though could well help confuse us further .


Regards,
Esq.
 
  • Like
  • Wow
  • Fire
Reactions: 20 users

cosors

👀
Good Morning Chippers,

Just perusing the CNBC news site .... apparently CHAT GP3 can now trawl through the latest internet data.

For those who know how to operate such tech this may provide more links to articles / undisclosed partners of 🧠chip ....... though could well help confuse us further .


Regards,
Esq.
Good night to you Down Under 🛌 from Up Above
🙃😅
 
  • Haha
  • Like
Reactions: 6 users

TECH

Regular
Tata patent / application
Brainchip mention




mand large memory and computation power to run effi- ciently, thus limiting their use in power and memory con- strained edge devices. Present application/disclosure provides a Spiking Neural Network based system which is a robust low power edge compatible ultrasound-based gesture detection system. The system uses a plurality of speakers and microphones that mimics a Multi Input Multi Output (MIMO) setup thus providing requisite diversity to effectively address fading. The system also makes use of distinctive Channel Impulse Response (CIR) estimat- ed by imposing sparsity prior for robust gesture detection. A multi-layer Convolutional Neural Network (CNN) has been trained on these distinctive CIR images and the trained CNN model is converted into an equivalent Spik- ing Neural Network (SNN) via an ANN (Artificial Neural Network)-to-SNN conversion mechanism. The SNN is further configured to detect/classify gestures performed by user(s).
Conventional gesture detection approaches de-
Processed

Thanks for your solid efforts in posting on the forum...I and many other genuine holders do appreciate your time in researching.

As the months tick by product designs must be (could be) in some cases be bordering on closure, hence why my suggestion of checking in on all
patents worldwide every month at the very least will produce dividends, in my view of course.

Tech (y)
 
  • Like
  • Fire
  • Love
Reactions: 23 users

Getupthere

Regular
  • Like
Reactions: 5 users

TheFunkMachine

seeds have the potential to become trees.
In this section, we give a brief summary of state-of-the-art neuromorphic processors. Several research groups from academia and industry have reported very promising implementations of neuromorphic processors. For example, a mixed-signal, multi-core neuroprocessor called dynamic neuromorphic asynchronous processor (DYNAP) was reported which combines the efficiency of analog computational circuits with the robustness of asynchronous digital logic for communications [96] and implemented in 180 nm CMOS process. Thakur et al. introduced an improved version called DYNAP with scalable and learning devices (Dynap-SEL) containing additional features implemented in a 28 nm FDSOI (Fully Depleted Silicon-On-Insulator) process [97]. There are four cores with each containing 16 × 16 analog neurons where each neuron has 64 programmable (4-bit) synapses. There is an additional fifth core containing 1 × 64 analog neurons, 64 × 128 plastic synapses (on-line learning capability), and 64 × 64 programmable synapses.
Two other famous neuroprocessors named ’SpiNNaker’ [26] and ’BrainScaleS’ [23] came out of human brain project (HBP) in Europe [98]. The SpiNNaker, developed by researchers at the University of Manchester, contains more than one million parallel ARM processors which are used to model one billion spiking neurons with biologically-realistic synaptic connections in real time [26]. On the other hand, BrainScaleS is a mixed-signal neuromorphic system at wafer-scale with upwards of 40 million synapses and 180 thousand neurons that has been developed from a research collaboration between the University of Heidelberg and the Technische Universita ̈t Dresden [23].
TrueNorth, a famous neuroprocessor from IBM [24], consists of 4096 neurosynaptic cores with 1 million digital neurons and 256 million synapses tightly interconnected by an event-driven routing infrastructure consuming 65 mW power. They also introduced a novel hybrid asynchronous–synchronous model along with new CAD tools for the design and verification. Another prominent neuroprocessor is Loihi from Intel [27] which contains 128 neuromorphic cores, three ×86 processor cores, and four communication interfaces that extend the mesh in four directions to other chips. Each neuromorphic core has 1024 primitive spiking neural units grouped into sets of neuronal trees. The mesh protocol can support up to 16,384 chips and 4096 on-chip cores using hierarchical addressing. Loihi introduced several novel features, such as hierarchical connectivity, dendritic compartments, synaptic delays, and programmable synaptic learning rules.
A family of dynamically adaptive neural processors have been developed by the TENNLab neuromorphic research group at in University of Tennessee. The first one is called DANNA (dynamic adaptive neural network array) [99] which was initially designed for FPGA and later adapted for 130 nm CMOS ASIC (application specific integrated circuit) implementation. An improved version called DANNA2 was introduced in 2018 with improved network density, achievable clock speeds, and training convergence rate [100]. In parallel, a mixed-signal extension known as memristive dynamic adaptive neural network array (mrDANNA), was later developed that utilized memristor devices in the synapses to improve the efficiency of the neuromorphic system [101] with an online learning methodology called synchronous digital long term plasticity (DLTP). Currently, TENNLAB is working on developing a convergent and flexible architecture as part of a reconfigurable and very efficient neuromorphic system or RAVENS [102].
8

Name Dynap-SEL [97] FPAA [103] BrainScaleS [23] TrueNorth [24] SpiNNaker [26] mrDANNA [101] Loihi [27]
Operation Mixed Analog Digital Digital Digital Mixed Digital
power/energy
260 pJ/spike
< 1μW
10 pJ/transmit
60 mW
100 nJ/neuron + 43 nJ/synapse
22.31 pJ/neuron/spike + 0.48 pJ/synapse/spike 81 pJ/neuron + 120 pJ/synapse
V. ALGORITHM AND ARCHITECTURE
timescale ns ms to s ns
ns
ns
ns to μs ns
on-chip learning STDP
STDP Configurable plasticity none Configurable DLTP Configurable STDP
TABLE II: State-of-the-art Neuromorphic Processors

https://arxiv.org/pdf/2310.09692.pdf

Unfortunately Brainchip not even mention in this Neuromorphic Published paper. Are they living under a rock?

However there are many familiar terms used among these other competitors. I wonder if we have something in our patent protection against these? STDP for instance…
 

Attachments

  • 3B879F36-DBD9-4733-989D-BF5F6B42B782.jpeg
    3B879F36-DBD9-4733-989D-BF5F6B42B782.jpeg
    423.7 KB · Views: 68
  • Like
  • Thinking
  • Fire
Reactions: 14 users

IloveLamp

Top 20
  • Like
  • Fire
  • Love
Reactions: 21 users

Perhaps

Regular
In this section, we give a brief summary of state-of-the-art neuromorphic processors. Several research groups from academia and industry have reported very promising implementations of neuromorphic processors. For example, a mixed-signal, multi-core neuroprocessor called dynamic neuromorphic asynchronous processor (DYNAP) was reported which combines the efficiency of analog computational circuits with the robustness of asynchronous digital logic for communications [96] and implemented in 180 nm CMOS process. Thakur et al. introduced an improved version called DYNAP with scalable and learning devices (Dynap-SEL) containing additional features implemented in a 28 nm FDSOI (Fully Depleted Silicon-On-Insulator) process [97]. There are four cores with each containing 16 × 16 analog neurons where each neuron has 64 programmable (4-bit) synapses. There is an additional fifth core containing 1 × 64 analog neurons, 64 × 128 plastic synapses (on-line learning capability), and 64 × 64 programmable synapses.
Two other famous neuroprocessors named ’SpiNNaker’ [26] and ’BrainScaleS’ [23] came out of human brain project (HBP) in Europe [98]. The SpiNNaker, developed by researchers at the University of Manchester, contains more than one million parallel ARM processors which are used to model one billion spiking neurons with biologically-realistic synaptic connections in real time [26]. On the other hand, BrainScaleS is a mixed-signal neuromorphic system at wafer-scale with upwards of 40 million synapses and 180 thousand neurons that has been developed from a research collaboration between the University of Heidelberg and the Technische Universita ̈t Dresden [23].
TrueNorth, a famous neuroprocessor from IBM [24], consists of 4096 neurosynaptic cores with 1 million digital neurons and 256 million synapses tightly interconnected by an event-driven routing infrastructure consuming 65 mW power. They also introduced a novel hybrid asynchronous–synchronous model along with new CAD tools for the design and verification. Another prominent neuroprocessor is Loihi from Intel [27] which contains 128 neuromorphic cores, three ×86 processor cores, and four communication interfaces that extend the mesh in four directions to other chips. Each neuromorphic core has 1024 primitive spiking neural units grouped into sets of neuronal trees. The mesh protocol can support up to 16,384 chips and 4096 on-chip cores using hierarchical addressing. Loihi introduced several novel features, such as hierarchical connectivity, dendritic compartments, synaptic delays, and programmable synaptic learning rules.
A family of dynamically adaptive neural processors have been developed by the TENNLab neuromorphic research group at in University of Tennessee. The first one is called DANNA (dynamic adaptive neural network array) [99] which was initially designed for FPGA and later adapted for 130 nm CMOS ASIC (application specific integrated circuit) implementation. An improved version called DANNA2 was introduced in 2018 with improved network density, achievable clock speeds, and training convergence rate [100]. In parallel, a mixed-signal extension known as memristive dynamic adaptive neural network array (mrDANNA), was later developed that utilized memristor devices in the synapses to improve the efficiency of the neuromorphic system [101] with an online learning methodology called synchronous digital long term plasticity (DLTP). Currently, TENNLAB is working on developing a convergent and flexible architecture as part of a reconfigurable and very efficient neuromorphic system or RAVENS [102].
8

Name Dynap-SEL [97] FPAA [103] BrainScaleS [23] TrueNorth [24] SpiNNaker [26] mrDANNA [101] Loihi [27]
Operation Mixed Analog Digital Digital Digital Mixed Digital
power/energy
260 pJ/spike
< 1μW
10 pJ/transmit
60 mW
100 nJ/neuron + 43 nJ/synapse
22.31 pJ/neuron/spike + 0.48 pJ/synapse/spike 81 pJ/neuron + 120 pJ/synapse
V. ALGORITHM AND ARCHITECTURE
timescale ns ms to s ns
ns
ns
ns to μs ns
on-chip learning STDP
STDP Configurable plasticity none Configurable DLTP Configurable STDP
TABLE II: State-of-the-art Neuromorphic Processors

https://arxiv.org/pdf/2310.09692.pdf

Unfortunately Brainchip not even mention in this Neuromorphic Published paper. Are they living under a rock?

However there are many familiar terms used among these other competitors. I wonder if we have something in our patent protection against these? STDP for instance…
Typical university research, you can find many like this. At least in Europe it seems they never heard of Brainchip. Not to forget, they don't care about commercial aspects.

When you break this down to real competition in form of neuromorphic processors, only the known names left over:

Intel Loihi (market-ready product planned for 2027/28)
IBM True North (analog failure, no foundry in the world could build these for the mass market, apart from lots of issues like heat-sensitivity)
Dynap SEL (SynSense) less powerful, biggest handicap, changed from Swiss to Chinese owners, headquartered in China now.

There are dozens of neuromorphic projects running at NASA and DARPA. When it comes to neuromorphic processors used in these projects you find only two names, Intel Loihi and Brainchip Akida, with a clear overweight of Akida.

Guess they know what they're doing, should be more real than any university studies.
 
  • Like
  • Fire
  • Love
Reactions: 38 users

Labsy

Regular
How good would a 35mill revenue be...
Please 🙏
When is the next 4c guys? Couple weeks now?
 
  • Like
  • Love
  • Fire
Reactions: 15 users

buena suerte :-)

BOB Bank of Brainchip
How good would a 35mill revenue be...
Please 🙏
When is the next 4c guys? Couple weeks now?
How great would that be Labsy 🙏🙏.....Just 9 trading days to hope for some decent $$$$$$$ in the 4C 🙏🙏

EDIT:.... Of course we won't see anything like that kind of revenue for some time!!!!!!..........But a couple of Million would be a great to help to steady the ship!!! :)
 
Last edited:
  • Like
  • Thinking
Reactions: 11 users

Xray1

Regular
How good would a 35mill revenue be...
Please 🙏
When is the next 4c guys? Couple weeks now?
From the last 4C .... it was stated that:

" Cash inflow from customers in the current quarter of $0.83M was higher than the prior quarter (US$0.04M)."

Accordingly, with the Co's ongoing "Cone of Silence" I am not expecting, nor anticipating any mentionable cash inflow from our only 2 IP customers.

I am also concerned about the sudden departure of Chris Stevens at this point of time in the Co's history ....... I wonder if there was any upper management pressure raised due to the lack of any new Sales / IP Lic's Agt's and potentially in turn thus resulting in rather low substantive ongoing Cash flow issues for the Co as a whole.

IMO,.... "IF".... this upcoming 4C turns out to be another rather low " Lumpy " figuge of say about US $0.04M then I am of the opinion that we are well and truely heading for a "Strike 2" scenario at the next AGM which I would like to think is something that the Founders Peter and Anil including all Directors would want to avoid at all costs for their own reputations as well as that of the Co BRN.
 
  • Like
  • Fire
  • Sad
Reactions: 13 users

Taproot

Regular
 
  • Fire
  • Like
Reactions: 6 users

Evermont

Stealth Mode
There is a good chance BrainChip might feature in a few conversations here.


1697669957630.png


1697669988822.png
 
  • Like
  • Love
  • Fire
Reactions: 34 users
How great would that be Labsy 🙏🙏.....Just 9 trading days to hope for some decent $$$$$$$ in the 4C 🙏🙏
Seriously people dream on this site, slowly slowly the conversations have ceased due to lack of sales of I.P' licences, just a known fact, Until this company release something we'll be continually manipulated
 
  • Like
Reactions: 1 users
How good would a 35mill revenue be...
Please 🙏
When is the next 4c guys? Couple weeks now?
Based on what exactly? Yes it absolutely would be amazing... but really, its just another pipe dream. And nothing we all have dreamed up here has come through so far, as we all watched the financials intently (or we may as well call it stalked the financials intently).

And how do you get 35 million? Genuinely interested btw, not having a stab. And yes I did my own research etc etc.
 
  • Like
  • Haha
  • Wow
Reactions: 12 users
From the last 4C .... it was stated that:

" Cash inflow from customers in the current quarter of $0.83M was higher than the prior quarter (US$0.04M)."

Accordingly, with the Co's ongoing "Cone of Silence" I am not expecting, nor anticipating any mentionable cash inflow from our only 2 IP customers.

I am also concerned about the sudden departure of Chris Stevens at this point of time in the Co's history ....... I wonder if there was any upper management pressure raised due to the lack of any new Sales / IP Lic's Agt's and potentially in turn thus resulting in rather low substantive ongoing Cash flow issues for the Co as a whole.

IMO,.... "IF".... this upcoming 4C turns out to be another rather low " Lumpy " figuge of say about US $0.04M then I am of the opinion that we are well and truely heading for a "Strike 2" scenario at the next AGM which I would like to think is something that the Founders Peter and Anil including all Directors would want to avoid at all costs for their own reputations as well as that of the Co BRN.
1697675195137.gif
 
  • Haha
  • Like
Reactions: 3 users
Top Bottom