BRN Discussion Ongoing

[Stable Genius]

This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/

 

[Dr E Brown]

This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/

Perhaps because he’s the CEO of Tenstorrent?

 

[MrNick]

This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/

Jim Keller has also been very, publicly, wrong, on quite a few occasions.

 

[Stable Genius]

Perhaps because he’s the CEO of Tenstorrent?

Hi @Dr E Brown and @MrNick I’m not saying he’s right.

I found a lot of his interview quite interesting and enlightening as I’m not in the industry so it’s nice to hear from thought leaders who are.

I’ve put my money where my mouth is and backing Brainchip however I respect others opinions. His disregard of SNN did seem to have more of a software focus so maybe he’s not up to date with Akida in particular; but I’m not knowledgable enough to disagree with him.

As most people in the industry he would have an agenda to push; but overall I enjoyed the interview.



Edit: I also liked how he discussed the fact that the larger companies such as Intel or Nvidia don’t necessarily have entitlement to the next big successful thing and said smaller start-ups can have wins too!

 

[Bravo]

This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/

It seemed like Jim Keller was downplaying SNN's. Comparing neuromorphic computing to just another type of encoding method isn't exactly fair or particularly accurate I'd have thought. I would have liked to have seen him address the known benefits such as real-time on-chip learning and training, reduced latency, improved privacy and security, low power consumption, etc..

And, he came across a little disingenuously IMO when he said "It's not likely that interesting, but maybe.."

Not that interesting? Good luck telling that to our growing list of partners as well as Renesas and MegaChips who are in the process of making this technology widely available.

 

[HopalongPetrovski]

This is worth a listen for those that have time.

Very insightful (sometimes rambling) discussion about the current AI developments with Jim Keller who previously worked with Apple and AMD so I would consider him a thoughtful industry insider. He’s been in the game for 40 years so he know the tech, history and industry quite well!

His opinion is SNN won’t be successful But I’m hoping he is proven wrong there!

https://www.eetimes.com/jim-keller-on-ai-risc-v-tenstorrents-move-to-edge-ip/

Interesting guy with an interesting and insightful take on how our minds work and the recent history of computing technology.
He poo poo's our spiking stuff as mere switches but that may just be bias built from his experience and personal narrative.
But I think he is worth a listen as he tries to distil his 40 years in the business into a prognosis of where we might be heading over the next 5 or so years. And I think he does it in a fairly genuine and honest way.
Thanks for sharing.

 

[Straw]

Interesting guy with an interesting and insightful take on how our minds work and the recent history of computing technology.
He poo poo's our spiking stuff as mere switches but that may just be bias built from his experience and personal narrative.
But I think he is worth a listen as he tries to distil his 40 years in the business into a prognosis of where we might be heading over the next 5 or so years. And I think he does it in a fairly genuine and honest way.
Thanks for sharing.

Aren't neurons essentially switches that have evolved with senses to be useful in the real world?

 

[manny100]

Sean said at the Understanding AI interview after the AGM that Data Centre businesses and AI at the Edge businesses would complement each other (as opposed to compete).
There will be some data suitable for Data Centre's and some for AI at the Edge, eg BRN. Both will co exist side by side.
As AI moves to IOT, Autos, Industrial machinery and Health a lot of the data will be more suitable for the Edge for reasons we all know about, latency, low power use, cost, privacy etc.
The above is what is holding us up........... the delay in demand for items that use the Edge. Its only a matter of time before demand becomes explosive.
The above is the only risk BRN faces IMO and that is the explosion in Edge demand happens well before our First mover advantage is used up.
I figure we have at least 2 years maybe more as the advantage.
As Sean said once business is on board they are on board for generations of products.
He also said in a decade BRN aim to be one of the few leaders in Edge business (or words to that effect).
Anyway the key is understanding is that Data Centers' and At the Edge busineses are not in competition. Even a lot of Analysts do not get that.

 

[HopalongPetrovski]

Sean said at the Understanding AI interview after the AGM that Data Centre businesses and AI at the Edge businesses would complement each other (as opposed to compete).
There will be some data suitable for Data Centre's and some for AI at the Edge, eg BRN. Both will co exist side by side.
As AI moves to IOT, Autos, Industrial machinery and Health a lot of the data will be more suitable for the Edge for reasons we all know about, latency, low power use, cost, privacy etc.
The above is what is holding us up........... the delay in demand for items that use the Edge. Its only a matter of time before demand becomes explosive.
The above is the only risk BRN faces IMO and that is the explosion in Edge demand happens well before our First mover advantage is used up.
I figure we have at least 2 years maybe more as the advantage.
As Sean said once business is on board they are on board for generations of products.
He also said in a decade BRN aim to be one of the few leaders in Edge business (or words to that effect).
Anyway the key is understanding is that Data Centers' and At the Edge busineses are not in competition. Even a lot of Analysts do not get that.

As I understand it we are starting at the edge because we didn't think there was much competition there and so it was seen as the fastest path to revenue. It is also a place to get recognition and establish ourselves, but I think our plan then involves us working backwards from the sensor towards the datacenter, over time, where our energy efficiency alone would make us valuable, let alone what further iterations of our tech may offer, particularly in the field of AI.
Hence our catch cry of ubiquity.
So yeah, for now we are happy to coexist and compliment each other's latent capabilities, but existing CNN tech is reaching its due by date, whereas we are just getting started.

 

[alwaysgreen]

Perhaps because he’s the CEO of Tenstorrent?

Tenstorrent just signed a deal to partner with LG to develop RISC-V ai chips.

Disappointing because I was hoping they were one of our future buyers.

 

[Dr E Brown]

Hi @Dr E Brown and @MrNick I’m not saying he’s right.

I found a lot of his interview quite interesting and enlightening as I’m not in the industry so it’s nice to hear from thought leaders who are.

I’ve put my money where my mouth is and backing Brainchip however I respect others opinions. His disregard of SNN did seem to have more of a software focus so maybe he’s not up to date with Akida in particular; but I’m not knowledgable enough to disagree with him.

As most people in the industry he would have an agenda to push; but overall I enjoyed the interview.



Edit: I also liked how he discussed the fact that the larger companies such as Intel or Nvidia don’t necessarily have entitlement to the next big successful thing and said smaller start-ups can have wins too!

All good mate. I’m just a cynical old bugger

 

[Learning]

Apology if this has been posted.

Since its such a quite night, anyone interested in reading this 100 page paper?

Link to the paper is below.

Radware Bot Manager Captcha

Learning 🏖

 

[Fullmoonfever]

I see our mates at Prophesee presenting shortly at the following symposium.

Having some challenges they say and are discussing a stacked event sensor. We know they work with Sony (one of the Chairs for this session) stacked sensor but also acknowledge the emphasis on connectivity to neuromorphic processor architectures....one would trust Akida is one such processor.

Original paper HERE

2023 Symposium on VLSI Technology and Circuits Advance Program

Circuits Session 22
Advanced Imagers [Suzaku II]
Thursday, June 15, 14:00-15:40

Chairpersons: T. Takahashi, Sony Semiconductor Solutions Corp.
M. Dielacher, Infineon Technologies AG

C22-2 - 14:25
A 320 x 320 1/5" BSI-CMOS Stacked Event Sensor for Low-Power Vision Applications, G. Schon, D. Bourke, P.-A. Doisneau, T. Finateu, A. Gonzalez, N. Hanajima, T. Hitana, L. Janse Van Vuuren, M. Kadry, C. Laurent, F. Le Goff, D. Matolin, A. Mezaour, B. Michel,
T. Naguleswaran, T. Opperman, P. Perrin, E. Reynaud, F. Shahrokhi, H. Tahachouite, C. Tianfan, G. van den Branden, A. Ziram, J.-L. Jaffard and C. Posch, Prophesee, France

Event-based vision is an emerging paradigm of acquisition and processing of visual information. The highly efficient way of acquiring sparse data and the robustness to uncontrolled lighting conditions make event-based vision attractive for applications in industrial, surveillance, IoT, AR/VR, automotive.

However, the unconventional format of the event data, non-constant data rates, non-standard interfaces pose challenges to usage and integration. A 320x320 6.3μm pixel BSI stacked event sensor was designed with the explicit goal to improve integrability and usability in embedded at-the-edge vision systems. Emphasis has been put on event data pre-processing and formatting, data interface compatibility and low-latency
connectivity to various processing platforms including low-power uCs and neuromorphic processor architectures.

Furthermore, the sensor has been optimized for ultra-low power operation, featuring a hierarchy of low-power modes and application-specific modes of operation. On-chip power management and an embedded microcontroller core further improve sensor flexibility and useability at-the-edge.

 

[MDhere]

It seemed like Jim Keller was downplaying SNN's. Comparing neuromorphic computing to just another type of encoding method isn't exactly fair or particularly accurate I'd have thought. I would have liked to have seen him address the known benefits such as real-time on-chip learning and training, reduced latency, improved privacy and security, low power consumption, etc..

And, he came across a little disingenuously IMO when he said "It's not likely that interesting, but maybe.."

Not that interesting? Good luck telling that to our growing list of partners as well as Renesas and MegaChips who are in the process of making this technology widely available.

the words but maybe means he is a swinger on voting bit like me saying its not likely that interesting blue cheese, but maybe


(and that phrase is true i now am a fan of one type of blue cheese but its nane is under an NDA)

 

[Fullmoonfever]

Apology if this has been posted.

Since its such a quite night, anyone interested in reading this 100 page paper?

View attachment 38156

Link to the paper is below.

Radware Bot Manager Captcha

Learning 🏖

Just did a keyword Akida and Brainchip search and didn't pick up a mention of us but the content list looked an interesting read but probs above my brain space

 

[Learning]

Just did a keyword Akida and Brainchip search and didn't pick up a mention of us but the content list looked an interesting read but probs above my brain space

It's above my brain cells also.
It's a an British origin paper i believe and Simon Thorpe is part author to this paper.

Hence, I thought it might be of interest.

Learning 🏖

 

[Sirod69]

Unlock the potential of AI for business transformations and data-driven decisions with our Minsky™ platform.

Know More: https://lnkd.in/g4NjdXK5

 

[thelittleshort]

New Senior Director of Product Management and Customer Success

 

[thelittleshort]

 

[Deleted member 118]

Apology if this has been posted.

Since its such a quite night, anyone interested in reading this 100 page paper?

View attachment 38156

Link to the paper is below.

Radware Bot Manager Captcha

Learning 🏖