BRN Discussion Ongoing

[Tothemoon24]

Nice publicity​

​

​

ByBusinesswire
December 28, 2023
BrainChip Holdings Ltd, the world’s first commercial producer of ultra-low power, fully digital, event-based, neuromorphic AI IP, was issued its latest U.S. patent, further strengthening its IP portfolio related to sustainable and efficient AI technologies.
Patent US 11,853,862, “Method, Digital Electronic Circuit and System for Unsupervised Detection of Repeating Patterns in a Series of Events,” facilitates learning in a digital hardware implementation of a spiking network. A key aspect of this unique approach is its effectiveness in performing accurate unsupervised detection or learning of repeating patterns, even when these patterns are embedded in high levels of noise, while being extremely efficient in reducing computing time, energy consumption and silicon footprint.
BrainChip’s AkidaTM IP and MetaTFTM tools seamlessly transform contemporary neural networks into event-based or spiking networks. This patented technology uniquely synergizes with the converted spiking networks, enabling the streamlined deployment of edge learning algorithms and unlocking use cases that conventional AI tools or solutions cannot attain.
“While we push the bounds with our innovative neuromorphic technology, preserving its integrity is paramount,” said Sean Hehir, CEO of BrainChip. “With 13 patents issued in the U.S. alone, we stand as leaders in developing and implementing next generation AI technologies for intelligent Edge devices and on-chip processing.”
BrainChip’s portfolio now comprises 19 issued patents (13x US, 4x AU, 1x EP, 1x CN). In addition, there are nearly 30 pending patent applications across the US, Europe, Australia, Canada, Japan, Korea, India, Brazil, Russia, Mexico, and Israel.

 

[MDhere]

2 yrs ago weren't Brainchip mentioned with Mercedes

They still are. Go to brainchip investor page on their website. Here in case u can't find it

 

[Pom down under]

2 yrs ago weren't Brainchip mentioned with Mercedes

 

[David holland]

View attachment 52941
View attachment 52942

My point is it won't be long before the cars hit the asphalt, they say 3 yrs ha ha its getting closer

 

[IloveLamp]

#ai #akida | BrainChip

As we forge ahead into 2024, BrainChip is not only continuing to build momentum but celebrating the substantial strides we've made this year. Our commitment to staying focused on our goal to bring #AI Everywhere is evident in the many achievements of the past year. Highlights include the...

www.linkedin.com

 

[IloveLamp]

#ai #akida | BrainChip

As we forge ahead into 2024, BrainChip is not only continuing to build momentum but celebrating the substantial strides we've made this year. Our commitment to staying focused on our goal to bring #AI Everywhere is evident in the many achievements of the past year. Highlights include the...

www.linkedin.com

View attachment 52943

3rd like in last couple of days by this loser

 

[IloveLamp]

Must watch imo.......6min

View attachment 52847

View attachment 52850 View attachment 52851

The future of AI acceleration | Intel Corporation

“All HPC apps are going to need some level of #AI, machine learning, stats analysis, or data analytics.” Learn more about the evolution of AI acceleration from Sandra Rivera —one of TIME’s 100 most influential people in AI. https://intel.ly/3TEstOs

www.linkedin.com

 

[Fact Finder]

3rd like in last couple of days by this loser

View attachment 52944 View attachment 52945

Hi Ilovelamp

It is interesting that he studied at the Moscow State University and that the following paper was published by that same university in 2022 wherein amongst other things it was stated:

“3.8. Akida​

Akida (Vanarse et al., 2019) is the first commercial neuromorphic processor, commercially available since August 2021. It has been developed by Australian BrainChip since 2013. Fifteen companies, including NASA, joined the early access program. In addition to Akida System on Chip (SoC), BrainChip also offers licensing of their technologies, providing chip manufacturers a license to build custom solutions.

The chip is marketed as a power efficient event-based processor for edge computing, not requiring an external CPU. Power consumption for various tasks may range from 100 μW to 300 mW. For example, Akida is capable of processing at 1,000 frames/Watt (compare to TrueNorth with 6,000 frames/Watt). The first generation chip supports operations with convolutional and fully connected networks, with the prospect to add support of LSTM, transformers, capsule networks, recurrent and cortical neural networks. ANN network can be transformed into SNN and executed on the chip.

One Akida chip in a mesh network incorporates 80 Neural Processing Units, which enables modeling 1,200,000 neurons and 10,000,000,000 synapses. The chip is built at TSMC 28 nm. In 2022, BrainChip announced the second generation chip at 16 nm.

Akida's ecosystem provides a free chip emulator, TensorFlow compatible framework MetaTF for the transformation of convolutional and fully connected neural networks into SNN, and a set of pre-trained models. When designing a neural network architecture for execution at Akida, one should take into account a number of additional limitations concerning the layer parameters (e.g., maximum convolution size is 7, while stride 2 is supported for convolution size 3 only) and their sequence.

The major distinctive feature is that incremental, one-shot and continuous learning are supported straight at the chip. At the AI Hardware Summit 2021 BrainChip showed the solution capable of identifying a human in other contexts after having seen him or her only once. Another product by BrainChip is a smart speaker, that on having heard a new voice asks the speaker to identify and after that calls the person by their name. There results are achieved with help of a proprietary local training algorithm on the basis of homeostatic STDP. Only the last fully connected layer supports synaptic plasticity and is involved in learning.

Another instructive case from the AI Hardware Summit 2021 was a classification of fast-moving objects (for example, a race car). Usually, such objects are off the frame center and significantly blurred but they can be detected using an event-based approach.”

Frontiers | Neuromorphic artificial intelligence systems

Modern AI systems, based on von Neumann architecture and classical neural networks, have a number of fundamental limitations in comparison with the brain. Th...

www.frontiersin.org

Probably means nothing but might provide background to his sudden interest.

My opinion only DYOR
Fact Finder

 

[IloveLamp]

Hi Ilovelamp

It is interesting that he studied at the Moscow State University and that the following paper was published by that same university in 2022 wherein amongst other things it was stated:

“3.8. Akida​

Akida (Vanarse et al., 2019) is the first commercial neuromorphic processor, commercially available since August 2021. It has been developed by Australian BrainChip since 2013. Fifteen companies, including NASA, joined the early access program. In addition to Akida System on Chip (SoC), BrainChip also offers licensing of their technologies, providing chip manufacturers a license to build custom solutions.

The chip is marketed as a power efficient event-based processor for edge computing, not requiring an external CPU. Power consumption for various tasks may range from 100 μW to 300 mW. For example, Akida is capable of processing at 1,000 frames/Watt (compare to TrueNorth with 6,000 frames/Watt). The first generation chip supports operations with convolutional and fully connected networks, with the prospect to add support of LSTM, transformers, capsule networks, recurrent and cortical neural networks. ANN network can be transformed into SNN and executed on the chip.

One Akida chip in a mesh network incorporates 80 Neural Processing Units, which enables modeling 1,200,000 neurons and 10,000,000,000 synapses. The chip is built at TSMC 28 nm. In 2022, BrainChip announced the second generation chip at 16 nm.

Akida's ecosystem provides a free chip emulator, TensorFlow compatible framework MetaTF for the transformation of convolutional and fully connected neural networks into SNN, and a set of pre-trained models. When designing a neural network architecture for execution at Akida, one should take into account a number of additional limitations concerning the layer parameters (e.g., maximum convolution size is 7, while stride 2 is supported for convolution size 3 only) and their sequence.

The major distinctive feature is that incremental, one-shot and continuous learning are supported straight at the chip. At the AI Hardware Summit 2021 BrainChip showed the solution capable of identifying a human in other contexts after having seen him or her only once. Another product by BrainChip is a smart speaker, that on having heard a new voice asks the speaker to identify and after that calls the person by their name. There results are achieved with help of a proprietary local training algorithm on the basis of homeostatic STDP. Only the last fully connected layer supports synaptic plasticity and is involved in learning.

Another instructive case from the AI Hardware Summit 2021 was a classification of fast-moving objects (for example, a race car). Usually, such objects are off the frame center and significantly blurred but they can be detected using an event-based approach.”

Frontiers | Neuromorphic artificial intelligence systems

Modern AI systems, based on von Neumann architecture and classical neural networks, have a number of fundamental limitations in comparison with the brain. Th...

www.frontiersin.org

Probably means nothing but might provide background to his sudden interest.

My opinion only DYOR
Fact Finder

You're blowing my mind ff

 

[IloveLamp]

Redirecting

Top emerging 5G and edge computing innovations to watch out for now | Samsung Networks

The convergence of #5G and #edgecomputing is gaining momentum with enhanced speeds and low latency enabling transformative applications in #smartcities, autonomous vehicles, #IndustrialIoT, and #digitaltwins, according to Joe McKendrick via ZDNET. https://lnkd.in/epBBjJmQ

www.linkedin.com

BRN / CARNEGIE

BrainChip Empowers Next Generation of Technology Innovators with Launch of the University AI Accelerator Program

Empower your tech innovation journey with BrainChip's University AI Accelerator Program. Unleash the future here!

brainchip.com

 

[Pom down under]

COYI

 

[Worker122]

#ai #akida | BrainChip

As we forge ahead into 2024, BrainChip is not only continuing to build momentum but celebrating the substantial strides we've made this year. Our commitment to staying focused on our goal to bring #AI Everywhere is evident in the many achievements of the past year. Highlights include the...

www.linkedin.com

View attachment 52943

Great! flags in the right order!

 

[buena suerte :-)]

Hmmmnnnnn ok!

 

[IloveLamp]

Hmmmnnnnn ok!

View attachment 52949
View attachment 52950

 

[Pom down under]

COYI

What’s up @miaeffect lol

 

[HopalongPetrovski]

Tis but a $66,270 scratch!

Now,

 

[buena suerte :-)]

Tis but a $66,270 scratch!

Now,

 

[buena suerte :-)]

COYI

 

[HopalongPetrovski]

Of course, Sean may be doing all this on purpose, cause he's after a spanking!
And frankly, who isn't?

 

[rgupta]

Hmmmnnnnn ok!

View attachment 52949
View attachment 52950

What a mismatch of holders expectations and company management behaviour.
Holders are thinking their's a few hundred thousands can make them millionaires while brainchip directors have no money to pay their tax obligations and selling shares at through away prices is the only way.
It again proves remuneration is very very generous. Even on a year when sp falls more than 70% Sean manages to make 400000 just from stock options. While most of the holders are in red management of brainchip can afford to make too much extra.
Just my own thinking point.