That is NOT what Tony said. He stated there is no COMMERCIAL partnership agreement. They can be partners in progressing the technology and not have a commercial agreement.
Howdy All,
So I was just having bit of a poke around to see if I could find out a bit more about the Klepsydra and Frontgrade Gaisler collaboration as per the above post and I stumbled on a Klepsydra Linkedin post from a couple of months ago which mentioned the "REBECCA Project" (see below).
I did a Google search and found the website for the REBECCA Project, which sure enough mentions neuromorphic computing.
As you can see from the screen shots from the website, the REBECCA project is co-funded by the European Union. The aim of the project is to democratize the development of edge AI systems including a hardware and software stack centred around a RISC-V CPU.
As described on the website, it will develop a novel chip that will include a neuromorphic AI accelerator, which you would think would be very likely to be AKIDA, since Frontgrade Gaisler has taken a commercial license for the Akida neural processor IP.
I also looked for further information on the Grant agreement ID: 101097224 and have posted a screen shot of that as well. Total cost for the project is €8 498 328,59 (with EU contribution comprising €2 744 319,72)!!!! The end date is set at 31 July 2026.
Clearly this is a very big deal because it says on the Cordis summary that the "project will contribute to realising business and societal opportunities by validating and demonstrating its approach on real-world use cases and benchmarks based on real-world applications from the smart appliances, energy generation, infrastructure inspection, avionics, automotive and health domains".
View attachment 76117
View attachment 76110
View attachment 76119
View attachment 76115
View attachment 76116
About Rebecca | Rebecca
www.rebecca-chip.eu
View attachment 76120
About Rebecca | Rebecca
Reconfigurable Heterogeneous Highly Parallel Processing Platform for safe and secure AI | REBECCA Project | Fact Sheet | HORIZON | CORDIS | European Commission
REBECCA, a heavily SME-driven project, will democratize the development of novel edge AI systems. Towards this aim, REBECCA will develop a purely European complete Hardware(HW) and Software(SW) stack around a RISC-V CPU, which will provide significantly higher levels of a)...cordis.europa.eu
Howdy All,
So I was just having bit of a poke around to see if I could find out a bit more about the Klepsydra and Frontgrade Gaisler collaboration as per the above post and I stumbled on a Klepsydra Linkedin post from a couple of months ago which mentioned the "REBECCA Project" (see below).
I did a Google search and found the website for the REBECCA Project, which sure enough mentions neuromorphic computing.
As you can see from the screen shots from the website, the REBECCA project is co-funded by the European Union. The aim of the project is to democratize the development of edge AI systems including a hardware and software stack centred around a RISC-V CPU.
As described on the website, it will develop a novel chip that will include a neuromorphic AI accelerator, which you would think would be very likely to be AKIDA, since Frontgrade Gaisler has taken a commercial license for the Akida neural processor IP.
I also looked for further information on the Grant agreement ID: 101097224 and have posted a screen shot of that as well. Total cost for the project is €8 498 328,59 (with EU contribution comprising €2 744 319,72)!!!! The end date is set at 31 July 2026.
Clearly this is a very big deal because it says on the Cordis summary that the "project will contribute to realising business and societal opportunities by validating and demonstrating its approach on real-world use cases and benchmarks based on real-world applications from the smart appliances, energy generation, infrastructure inspection, avionics, automotive and health domains".
View attachment 76117
View attachment 76110
View attachment 76119
View attachment 76115
View attachment 76116
About Rebecca | Rebecca
View attachment 76120
About Rebecca | Rebecca
Reconfigurable Heterogeneous Highly Parallel Processing Platform for safe and secure AI | REBECCA Project | Fact Sheet | HORIZON | CORDIS | European Commission
REBECCA, a heavily SME-driven project, will democratize the development of novel edge AI systems. Towards this aim, REBECCA will develop a purely European complete Hardware(HW) and Software(SW) stack around a RISC-V CPU, which will provide significantly higher levels of a)...
I spotted almost a year ago:
Reading this reminds me when I'm on the rowing machine -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
Yeah, he basically said what the Doc said, using as little words as possible, maybe he had a long day..
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 ...
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’s
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
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)
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.
...
