Great find. I think we are a long way ahead of them - imec is a research org, the Nimble chip ip providers seem to be FPGA designers, and their industry advisory board include some of our "partners": ESA, prophesee, Edge Impulse, RTX. It's a pitty that we aren't there, but these guys are just a consortium, and for them to make commercially available chips they would have to spin off a company etc etc, I think.I hate to be the bearer of bad tidings but it looks like the REBECCA project will be utilizing IMEC's SENeCA neuromorphic processor.
I discovered this because one of the consortium partners on the REBECCA project is IMEC, which got me thinking.
Then I found this research paper dated 28 March 2024, under the REBECCA project's grant agreement No. 101097224 (see below). As you can see the research paper focusses on the SENeCA architecture and the authors were all employed by IMEC. The paper compares results with SpiNNaker2 and Loihi, but not AKIDA. However, it does state that "our optimizations for event-based neural networks can be potentially generalized to a wide range of event-based neuromorphic processors."
On a positive note, I noticed that the Funding Statement on the research paper also shows NimbleAI (Horizon EU under grant agreement 101070679). And we know that NimbleAI are combining AKIDA 1500 with the Hailo-8 accelerator for inference processing for one of their prototypes, so it may not be out of the question for different prototypes to be explored in the REBECCA project in the same way that NimbleAI has.
Do we know what's happening with SENeCA's SNN processor at the moment? I believe from past discussions IMEC were looking at taping out in Q1 2025, planned to be submitted to the foundry in Jan 2025.
View attachment 76160
View attachment 76163
Optimizing event-based neural networks on digital neuromorphic architecture: a comprehensive design space exploration - PMC
Neuromorphic processors promise low-latency and energy-efficient processing by adopting novel brain-inspired design methodologies. Yet, current neuromorphic solutions still struggle to rival conventional deep learning accelerators' performance and ...pmc.ncbi.nlm.nih.gov
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
DingoBorat
Slim
That was a definite whale chomp, into the 35 cent line. 
Adika
Member
We can pretty safely assume the neuromorphic processor in that paper will turn out to be Intel’s Loihi.
The paper’s first author David Harbour is the son of Steven Harbour (who is also one of the co-authors). Steven Harbour left SwRI (Southwest Research Institute) last year to become Director of AI Hardware Research at Parallax Advanced Research.
In March, while still at SwRI (which has been closely collaborating with Intel on neuromorphic research for years), Steven Harbour posted this…
View attachment 76164
… tagging Mike Davies and two former Intel Labs researchers (Tim Shea and Yulia Sandamirskaya) as well as Gregory Cohen who is doing research on neuromorphic cameras in space at Western Sydney University’s ICNS.
And I also recalled having seen a poster of the above-mentioned paper on the Parallax website (referring to related work, which includes a paper involving Loihi, co-authored by Steven Harbour):
Neuromorphic Computing for Space: Recognized Innovation at DASC 2024
parallaxresearch.org
View attachment 76165
View attachment 76166
And it appears there is no Akida in the REBECCA project either…
Klepsydra and Frontgrade Gaisler are collaborating on the GR765 - which I believe to be the microprocessor our company will also be involved in.
See also Alf Kuchenbuch’sI spotted almost a year ago:
https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-407807
View attachment 76167
However, unlike Klepsydra, Frontgrade is not even a consortium partner in the REBECCA project.
IMEC, however, is.
REBECCA KDT JU on LinkedIn: 1st REBECCA NEWSLETTER
🚀 We are thrilled to present the first Chips Joint Undertaking project REBECCA KDT JU newsletter! 🚀 Together with the incredible efforts of our consortium…www.linkedin.com
View attachment 76168
View attachment 76169
Looks like you were a little slow off the mark in correcting @Bravo about IMEC this time, she beat you to it! Better luck next time!
Frangipani
Regular
Do we really know that?
No, we don’t.
NimbleAI won’t be combining the AKD1500 and the Hailo-8; instead, the two processors will be benchmarked against each other:
NimbleAI.eu on LinkedIn: #neuromorphicai #edgeai #eventbasedvision #tinyml #computervision…
Proud to be featured in the Neuromorphic Computing, Memory and Sensing 2024 report by Yole Group 👉 https://lnkd.in/di5Jvasq 🚩 NimbleAI contributes to…
After all, the prototype is going to have only one PCIe slot to fit either Hailo or Akida.
As of July 2024, NimbleAI’s project coordinator Xabier Iturbe was still hoping for the AKD1500 to become available as a M.2 module, though
(cf his mail reply to @AI_Inquirer here:
https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-446343)
Attachments
Adika
Member
Gees, that didn't take you long!Do we really know that?
No, we don’t.
NimbleAI won’t be combining the AKD1500 and the Hailo-8; instead, the two processors will be benchmarked against each other:
NimbleAI.eu on LinkedIn: #neuromorphicai #edgeai #eventbasedvision #tinyml #computervision…
Proud to be featured in the Neuromorphic Computing, Memory and Sensing 2024 report by Yole Group 👉 https://lnkd.in/di5Jvasq 🚩 NimbleAI contributes to…
View attachment 76172
After all, the prototype is going to have only one PCIe slot to fit either Hailo or Akida.
View attachment 76179
As of July 2024, NimbleAI’s project coordinator Xabier Iturbe was still hoping for the AKD1500 to become available as a M.2 module, though
(cf his mail reply to @AI_Inquirer here:
https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-446343)
Boab
I wish I could paint like Vincent
DingoBorat
Slim
...
Frangipani
Regular
No, she didn’t. She only posted about it earlier, while I was still busy with other things.
It is now January 17, shortly after 0.30 am my time. I took the following screenshot on January 16, at 8:44 am my time. That’s almost 16 hours ago.
So who found out first about IMEC developing the neuromorphic AI accelerator for the REBECCA project?
Thank you @Boab BrainChip and Quantum Ventura have been working together for a long time. Great to see that they have had success in developing a Cyber Security solution.
7für7
Top 20
What? Who said this… what? Where did it go? Where….where is it??? I..I… I can see the 34…
DingoBorat
Slim
Yeah, it was just one and turns out he was only peckish..
Papacass
Regular
This post has attained a very high score on the wuckfit scale.No, she didn’t. She only posted about it earlier, while I was still busy with other things.
It is now January 17, shortly after 0.30 am my time. I took the following screenshot on January 16, at 8:44 am my time. That’s almost 16 hours ago.
So who found out first about IMEC developing the neuromorphic AI accelerator for the REBECCA project?
View attachment 76180
Adika
Member
No, she didn’t. She only posted about it earlier, while I was still busy with other things.
It is now January 17, shortly after 0.30 am my time. I took the following screenshot on January 16, at 8:44 am my time. That’s almost 16 hours ago.
So who found out first about IMEC developing the neuromorphic AI accelerator for the REBECCA project?
View attachment 76180
I believe Bravo said she was putting you on ignore the other day so it’s a bit silly if you expect her to respond to you. I don’t blame her either. You seem desperate to try to find ways to criticise her contributions and you always manage to do it in a condescending way.
If something that another person has posted is inaccurate, why don’t you politely point it out instead of trying to score points for yourself? That’s exactly what you did with Fact Finder and look what happened. He’s no longer here on TSEx which sux. But that’s what usually happens when you relentlessly criticize other people. I’m sure most people who post here don’t expect to be constantly under interrogation or held to the same standards as a professor.
As @7für7 pointed out the other day, most people like Bravo come here to contribute not expecting to get any credit but simply because they enjoy sharing information You on the hand, make it all about yourself and gloat about how you posted every bit of information before anyone else did. It’s pretty immature.
HopalongPetrovski
I'm Spartacus!
You remember when you were 7 don't you.
Smoothsailing
Regular
I would like to ask a question to the Technically smarter folks here on if any of BRN products could be implemented into a mobile phone for cybersecurity purposes and if so how do you see this working and with what partner would have the capability to do so, Quantum Ventura ?.
Any thoughts on this are much appreciated.
Any thoughts on this are much appreciated.
Last edited:
This is a good read:
BrainChip Provides Low-Power Neuromorphic Processing for Quantum Ventura’s Cyberthreat Intelligence Tool
BrainChip Provides Low-Power Neuromorphic Processing for Quantum Ventura’s Cyberthreat Intelligence Tool
www.businesswire.com
That’s an interesting question and I will leave it to the likes of @Diogenese to answer. However, it looks like Quantum Ventura have have been exploring security on mobile phones.
Quantum-X | Diamond-Droid
www.quantumventura.com
News release on Yahoo...did I miss it here??
Was out walking the dogs and came back to this on my Ameritrade (now Schwab) home page.
Word getting around even if not available through the ASX
Was out walking the dogs and came back to this on my Ameritrade (now Schwab) home page.
Word getting around even if not available through the ASX
Last edited:
Similar threads
