BRN Discussion Ongoing

[Tuliptrader]

Great read from Tata


Boom

Spiking neural networks

www.tcs.com

That is indeed a great read from TCS.

I had a bit of chuckle whilst reading it though. In the middle of the article is this quote.

"AI will probably most likely lead to the end of the world, but in the meantime, there'll be great companies."​

Sam Altman​

Chairman of OpenAI

How's that for some jolly honest fatalism.

Oh well, I suppose, if you can't beat them......

TT

 

[IloveLamp]

Hiya loveLamp, love the possibilities here. When Bosh said they were dumping their Lidar program after 3 or so years. I was “Oh, bum, kinda thought , Bosh generally, were a possible good fit” But i noted that Bosh took up a keen interest in mm wavelength tech. From my uneducated, vague and low researched perspective , it seemed that mm wavelength offered another exciting opportunity to a BrainChip-Bosh link.
Thanks for your research and it’s just another wait and see prospect.
I think back in the day, way back, Bosh was tossed about as a reasonable dot join.
Anyway, if anyone can add some supporting commentary or musings.
That would be welcomed.
Just a few random thoughts that may have reminded others more knowledgeable

Cheers

Agreed @Kozikan A bosch connection is highly probable imo can't wait to see what unfolds over the coming months / years.

As Rene Haas said in the interview i posted this morning, "when it comes to ai, we're 2min into the first qtr of the first game"

 

[charles2]

BRN is not a run-ot-the-mill company with a single product or known product range and established customers. Even the product development roadmap changes with the rapid developments in the market and changing customer requirements.

Akida is in a state of continuous rapid development.

We were (mostly) pleasantly surprised to learn about the capabilities of Akida 2, which had been under development for a considerable time before it was announced. Akida 2 has capabilities which no one outside the company had imagined. TeNNs were not part of any previously disclosed development road map. Anyone with pre-knowledge of TeNNs who bought shares before the release of Akida 2 would have been guilty of insider trading.

We know Akida 3 is in development, but we don't know what surprises it will embody.

The iceberg analogy has been used in relation to BRN because fully two thirds of its potential customer base is under NDA.

Some of BRN's customer engagements are in the form of joint development partnerships, again giving the board and management exclusive confidential knowledge not available to the market about the progress and intended destination of the joint development and associated commercial aspects.

I don't know about the US, but in Australia insider trading is a jailable offence, so I understand the board and management's abstinence from on-market trading.

Well it hardly seems to qualify as an offense risking jail if you buy stock because you like your company's prospects.

To me Australia has orchestrated short sellers that would be first in line for jail if there was even a modicum of market oversight.

 

[HopalongPetrovski]

Well it hardly seems to qualify as an offense risking jail if you buy stock because you like your company's prospects.

To me Australia has orchestrated short sellers that would be first in line for jail if there was even a modicum of market oversight.

Given the cautious approach to the way the BOD share information and the interpretation they have taken in regards ASX announcements I think they have a good excuse for not buying on market.

And given the generous allowances made to each of them and other connected parties as part of the remuneration packages, they don't need to.

But , this second factor is not only applicable to BRN but instead is seemingly propagated by most who reach such exalted positions.

An industry within industries, something akin to the real estate market where those who are in the greatest positions to gain are also coincidently puling the strings of those making the rules resulting in engineered shortages to make sure demand is always exceeding available supply.

Unfortunately corruption is the go to modus operandi in human affairs and proliferates beneath the surface benefiting the few at the expense of the rest.

Maybe when the AI's take over, with an intergenerational plan for our betterment they will institute a fairer environment, over time.
Too honest, too fair, too soon..........too much of a shock to our system.

 

[Crestman]

Just came across this site (apologies if already posted), has some quotes from Rob Telson and Roger Levinson.

https://idstch.com/geopolitics/next...g-from-cloud-to-iot-edge-devices-and-mobiles/

Edit: Apologies, its from 2022, I was searching only for sites updated in the last week, so it must have had some sort of update. Still interesting info though.

 

[Kozikan]

Agreed @Kozikan A bosch connection is highly probable imo can't wait to see what unfolds over the coming months / years.

As Rene Haas said in the interview i posted this morning, "when it comes to ai, we're 2min into the first qtr of the first game"

Too true.

 

[Pom down under]

Agreed @Kozikan A bosch connection is highly probable imo can't wait to see what unfolds over the coming months / years.

 

[TECH]

Good evening,

Many will remember when we (Brainchip) presented alongside Tata Consultancy Services in Vancouver demonstrating Gesture Recognition
in Robotics.

This Tata Patent was published a little over 5 weeks ago, maybe it's already been posted, but never-the-less check it out, we get a little mention
in the artwork, mean something, I think so...we head this space, don't we ?

Espacenet – search results

Espacenet: free access to millions of patent documents. Find out if your invention is unique or if other inventors have filed patent applications that are considered to be prior art.

worldwide.espacenet.com

 

[Pom down under]

What’s happening with Sifive?




Maybe this will answer and are we apart of the shift toward custom RISC-V cores.

RISC-V champ SiFive confirms it's laying off 1 in 5 workers

The purpose is refocusing and 'realigning,' according to chip designer

www.theregister.com

 

[Diogenese]

Good evening,

Many will remember when we (Brainchip) presented alongside Tata Consultancy Services in Vancouver demonstrating Gesture Recognition
in Robotics.

This Tata Patent was published a little over 5 weeks ago, maybe it's already been posted, but never-the-less check it out, we get a little mention
in the artwork, mean something, I think so...we head this space, don't we ?

Espacenet – search results

Espacenet: free access to millions of patent documents. Find out if your invention is unique or if other inventors have filed patent applications that are considered to be prior art.

worldwide.espacenet.com

Hi Tech,

Great find!

One exciting thing is the priority date of 20220429, just 18 months ago, indicating a potential ongoing relationship. After all, who does CNN2SNN better than BRN?

... and a couple of the inventors are familiar faces ...

US2023325001A1 ACOUSTIC SYSTEM AND METHOD BASED GESTURE DETECTION USING SPIKING NEURAL NETWORKS 20220429

Inventors: GIGIE ANDREW [IN]; GEORGE ARUN [IN]; KUMAR ACHANNA ANIL [IN]; DEY SOUNAK [IN]; PAL ARPAN [IN]

Conventional gesture detection approaches demand large memory and computation power to run efficiently, thus limiting their use in power and memory constrained 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) estimated 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 Spiking Neural Network (SNN) via an ANN (Artificial Neural Network)-to-SNN conversion mechanism. The SNN is further configured to detect/classify gestures performed by users.

[0089] The active power consumption of a neuromorphic hardware is mainly contributed by the spiking network's total number of synaptic operations (SOP). Following (7) and the method mentioned in Sorbaro et al. (e.g., refer “Martino Sorbaro, Qian Liu, Massimo Bortone, and Sadique Sheik, “Optimizing the energy consumption of spiking neural networks for neuromorphic applications,” Frontiers in Neuroscience, vol. 14, pp. 662, 2020.”), total number of synaptic operation for the SNN of the system 100 is found to be ˜35M while that for the CNN is ˜95M (considering matrix multiplication only). This converted SNN can be implemented on neuromorphic platforms such as Brainchip Akida (e.g., refer “Brainchip unveils the akidatm development environment,” https://www.brainchipinc.com/news-m...chip-unveils-the-akida-developmentenvironment, 2019″), Intel® Loihi (e.g., refer “Mike Davies. et. al, “Advancing neuromorphic computing with loihi: A survey of results and outlook,” Proceedings of the IEEE, vol. 109, no. 5, pp. 911-934, 2021.”), etc. to achieve further power benefit (˜100×).

 

[David holland]

Good evening,

Many will remember when we (Brainchip) presented alongside Tata Consultancy Services in Vancouver demonstrating Gesture Recognition
in Robotics.

This Tata Patent was published a little over 5 weeks ago, maybe it's already been posted, but never-the-less check it out, we get a little mention
in the artwork, mean something, I think so...we head this space, don't we ?

Espacenet – search results

Espacenet: free access to millions of patent documents. Find out if your invention is unique or if other inventors have filed patent applications that are considered to be prior art.

worldwide.espacenet.com

I don't know do we ? Until the company confirm 1 way or another it's speculation

 

[Fullmoonfever]

Couldn't recall if this one with Todd & Edge Impulse posted on multi object detection.

Apparently put up about 3 days ago.

 

[Humble Genius]

This is great Frangipani! You will notice whilst Zach doesn't specifically mention Brainchip its clear that Arm and Brainchip are shown TOGETHER in the bottom right had side of graph. Not only that both are in a BOXED IN together! View attachment 49901
Then I referred to a Arm tech talk in May 2023 that Nandan and other executives were on and Nadan specifically mentions that Brainchip is able to go into Any cortex system. To further add within the Arm tech talk speech has a slide another slide together with Arms cortex range inc M55 and M85 etc. View attachment 49902 So essentially its way more then an interesting presentation and your a genius to display it. Zach from edge impulse didn't probably need to spell out as it's proof right there boxed IN WITH ARM. Can't get better than that Marcel Marceau you made my Sunday Frangipani ❤ View attachment 49901

"This is great Frangipani! You will notice whilst Zach doesn't specifically mention Brainchip its clear that Arm and Brainchip are shown TOGETHER in the bottom"

To me that symbolises an ARM chip with AKIDA inside.

 

[Esq.111]

Evening TECH & Chippers ,

Good find on the patent front.

Briefly skimmed through ...

Brainchip mentioned under Description @ 0089.

I now have a headache.

Regards,
Esq.

 

[Bravo]

Hi Tech,

Great find!

One exciting thing is the priority date of 20220429, just 18 months ago, indicating a potential ongoing relationship. After all, who does CNN2SNN better than BRN?

... and a couple of the inventors are familiar faces ...

US2023325001A1 ACOUSTIC SYSTEM AND METHOD BASED GESTURE DETECTION USING SPIKING NEURAL NETWORKS 20220429

Inventors: GIGIE ANDREW [IN]; GEORGE ARUN [IN]; KUMAR ACHANNA ANIL [IN]; DEY SOUNAK [IN]; PAL ARPAN [IN]

View attachment 49937

Conventional gesture detection approaches demand large memory and computation power to run efficiently, thus limiting their use in power and memory constrained 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) estimated 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 Spiking Neural Network (SNN) via an ANN (Artificial Neural Network)-to-SNN conversion mechanism. The SNN is further configured to detect/classify gestures performed by users.

[0089] The active power consumption of a neuromorphic hardware is mainly contributed by the spiking network's total number of synaptic operations (SOP). Following (7) and the method mentioned in Sorbaro et al. (e.g., refer “Martino Sorbaro, Qian Liu, Massimo Bortone, and Sadique Sheik, “Optimizing the energy consumption of spiking neural networks for neuromorphic applications,” Frontiers in Neuroscience, vol. 14, pp. 662, 2020.”), total number of synaptic operation for the SNN of the system 100 is found to be ˜35M while that for the CNN is ˜95M (considering matrix multiplication only). This converted SNN can be implemented on neuromorphic platforms such as Brainchip Akida (e.g., refer “Brainchip unveils the akidatm development environment,” https://www.brainchipinc.com/news-m...chip-unveils-the-akida-developmentenvironment, 2019″), Intel® Loihi (e.g., refer “Mike Davies. et. al, “Advancing neuromorphic computing with loihi: A survey of results and outlook,” Proceedings of the IEEE, vol. 109, no. 5, pp. 911-934, 2021.”), etc. to achieve further power benefit (˜100×).

One of the inventors is Sunak Dey
I recall he had some great stuff to say
About how Akida is getting on
Being betterer than NVIDIA Jetson

 

[David holland]

I don't know do we ? Until the company confirm 1 way or another it's speculation

The CEO Has stated our engagement with customers is at a record high, so where got them in our shop ,engagement is there however it's whether they put cash in the till or walk out

 

[Labsy]

My interpretation of this is that all these companies essentially rely on the ARM/BRAINCHIP ip... ubiquitous baby..

 

[Fullmoonfever]

Good to see we'll be at CES.

Appointment only, like quite a few on the Alliance list, though some do have booths.

Presume when our blurb says, live demos with partner platforms, just means we will be there with certain partners booths....be good to check which partners we know have booths and what they showing

Wouldn't it be great to at least get a non sensitive Ann advising the mkt we will be there (or have I missed it)...no diff imo when mining companies advise they'll be attending say Diggers and Dealers

Alliance Members at 2024 CES - Edge AI and Vision Alliance

The Edge AI and Vision Alliance 2024 CES Directory for game-changing computer vision and perceptual AI technologies Many Alliance Member companies will be showing off the latest building-block technologies that enable new capabilities for machines that see! CES is huge so we’ve created a handy...

www.edge-ai-vision.com

News / November 15, 2023

The Edge AI and Vision Alliance 2024 CES Checklist for game-changing computer vision and perceptual AI technologies​

Many Alliance Member companies will be showing off the latest building-block technologies that enable new capabilities for machines that see! CES is huge so we’ve created a handy checklist of these companies and where to find them including how to request suite/demo access.​

Brainchip​

Appointment Only​

Brainchip is hosting a showcase at the Venetian Resort Hotel with live demonstrations of the Akida neuromorphic processor technology in action with partner platforms. Experience ultra-efficient edge AI processing of all sensor modalities—vision, sound, vibration—and explore possibilities for disruptive new solutions. For requests to meet at the Brainchip suite, please contact
sales@brainchip.com.

 

[Learning]

Any advance technical member/ programmer could do a little dig in this. I had a skim through. But haven't found it.

When you put 'Akida' in the Arm Developer. Arm Ethos-U65 NPU Technical Reference Manual come up.

'Arm Ethos is a family of synthesizable neural processor IPs designed by Arm for IoT and edge applications'. So could Arm implement Akida IP in it???

Search – Arm Developer

developer.arm.com

Ethos-U65 NPU| Efficient AI with Double ML Performance

The Arm Ethos-U65 NPU offers low-cost, efficient AI for embedded devices, extending power efficiency to Cortex-A, Cortex-R, and Neoverse systems with twice the ML performance of the Ethos-U55.

www.arm.com

Learning

 

[Tothemoon24]

New GenX320 Sensor Wins CES 2024 Innovation Award

Prophesee has been named a CES® 2024 Innovation Awards Honoree for its GenX320 Event-based Metavision sensor, the industry’s smallest and most power-efficient event-based vision sensor.

www.prophesee.ai