Please remove this before @Bravo sees it!
An AI powerhouse: Snapdragon 8 Gen 2 AI feature deep dive [+video]
A deep dive into the most powerful AI Engine to date inside the Snapdragon 8 Gen 2 mobile platform.www.qualcomm.com
View attachment 31858
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Ken has a very big sock under his bed.
McHale
Regular
As long as it's not an SVB sock I don't care.
Deadpool
hyper-efficient Ai
And I thank you kindly for your appreciation of us mentally challenged.
McHale
Regular
One perspective re the $2.34 blast is that it took place in the latter end of 2021, and early part of 2022. It was definitely still a risk ON environment.I thought of that many times after that hyper pump to $2 .34.
Don't know what price it would go to after ip deals and such but gee we are going to have a nice floor price after that.
Then the forum will be flooded with I woulda coulda shoulda posts.
Not saying that BRN cannot go ballistic on the right types of contracts and good income, but we are in a different type of market right now (risk off), regardless I am amongst those who feel that there might be something good just around the corner of the LDA deal expiry date - late March early April ?? Pre AGM.
I mean with certain banks starting to look vulnerable (because they have over exposed themselves to crypto), Bonds getting tricky, where might you put some of your money ???
Impressive AKIDA 2nd Gen $10 compared to $1000 for GPU.
I guess the question is how big is the potential market using GPU we can capture and what does this market do/ consist of?
Cheers
Agree, people do not appreciate the importance of the LDA deal.
It means we never have the worry about cash burn which is the nightmare of all young up and coming businesses.
Fact Finder
Top 20
And there is that word “Track.”
Throw in the other word “Prediction.”
Plastic bags are ancient history.
My opinion only DYOR
FF
AKIDA BALLISTA
Deadpool
hyper-efficient Ai
Oh, that's gold
It was me who asked that questionView attachment 31857
Such great information shared and found over the last week. But this for me just makes me grin from ear to ear and back around again.
The best wink, wink nudge, nudge say no more I've seen in a very long longtime.
Deadpool
hyper-efficient Ai
Is that a butterflied Portugues chook? I like your research, I like it a lotI'll just leave my latest research here .
Deadpool
hyper-efficient Ai
I believe in the near future SNN is going to be as common as a bustard arse Tesla on the back of a tow truck.Geez...those WANCAs out there need to realise neuromorphic not going away.
Positions opening constantly at unis & research centres....guess there must be something in this SNN caper
View attachment 31838 View attachment 31839 View attachment 31840
HopalongPetrovski
I'm Spartacus!
Geoffrey Carrick
Non-Executive Director
Chair of the Audit & Governance Committee
By the look of that grin, I'm pretty sure Geoffrey keeps it under his bed.
Fact Finder
Top 20
Some will recall an interview conducted with Rob Telson where he was asked about competition from Nvidia being a problem. Rob Telson answered this question by saying words to the effect 'We see Nvidia more as a partner in the future.' Rob Telson said this with a great degree of confidence and perhaps some may have thought it was born out of conceit or hubris when Nvidia has been and still is accorded the title of leader in the Artificial Intelligence space. We all know that in the past when asked about competition Brainchip representatives would talk about the technical advantages of SNN and how there was a Von Neumann bottleneck but on this occasion when confronted with Nvidia Rob Telson just went straight to they will be a partner. While many of us myself included struggle with the science and engineering and thank our lucky stars @Diogenese graces this forum and is prepared to share his engineering knowledge I found the following explanation as to why Nvidia needs SNN very accessible and worth sharing here. The quote is from page 83 of this very long Thesis and you are welcome to read the whole paper. There is no mention of Brainchip and AKIDA that I saw and having read other papers by Gregor Lenz I know him to be a fan of Intel and Loihi though AKIDA 2nd Generation may well change his entire perspective:
:
Neuromorphic algorithms and hardware for event-based processing Gregor Lenz
"On our prototype device, we also made use of the Tensorflow Lite backend, which in turn uses neural network accelerator hardware for efficient inference. The issue is, however, that when we convert events into frame representations, we lose a lot of the advantages of event cameras.
As mentioned in the beginning of this conclusion, the hardware lottery gave us GPUs to work with, but they are designed for a different kind of data. GPUs are a great workhorse when it comes to parallelising compute-intense tasks, but they fail to exploit high sparsity in signals.
That is why sparse computation on GPUs is something that the research community is actively looking into at the moment [286, 287].
NVIDIA announced in 2020 that their latest generation of tensor cores would be able to transform dense matrices into sparse matrices using a transformation called 4:2 sparsity, where the cost of computation is reduced by half. This accelerates inference up to a factor of 2 for a minor hit of accuracy [288], but such a feature requires supplementary hardware to check for zeros in the data.
On neuromorphic hardware, the sparse input directly drives asynchronous transistor switching activity, without the need for additional checks. The difference is essentially the lack of input in comparison to lots of zeros of input in the case of GPUs.
Even though GPUs and TensorFlow Lite are making amends to reduce the need to process unnecessary zeros, neuromorphic computing tackles different application scenarios.
Sparsity in signals from an event-based sensor reaches levels of 99% depending on scene activity and is therefore much higher than what a 4:2 sparsity could achieve to shrink.
In the end neuromorphic computing that can exploit the absence of new input information will have a head start in certain applications for power-critical systems that track spurious events at high speeds.
This is where GPUs that apply sparsity checks to avoid computation in a later step will not be able to compete. "
My opinion only DYOR
FF
AKIDA BALLISTA
:
Neuromorphic algorithms and hardware for event-based processing Gregor Lenz
"On our prototype device, we also made use of the Tensorflow Lite backend, which in turn uses neural network accelerator hardware for efficient inference. The issue is, however, that when we convert events into frame representations, we lose a lot of the advantages of event cameras.
As mentioned in the beginning of this conclusion, the hardware lottery gave us GPUs to work with, but they are designed for a different kind of data. GPUs are a great workhorse when it comes to parallelising compute-intense tasks, but they fail to exploit high sparsity in signals.
That is why sparse computation on GPUs is something that the research community is actively looking into at the moment [286, 287].
NVIDIA announced in 2020 that their latest generation of tensor cores would be able to transform dense matrices into sparse matrices using a transformation called 4:2 sparsity, where the cost of computation is reduced by half. This accelerates inference up to a factor of 2 for a minor hit of accuracy [288], but such a feature requires supplementary hardware to check for zeros in the data.
On neuromorphic hardware, the sparse input directly drives asynchronous transistor switching activity, without the need for additional checks. The difference is essentially the lack of input in comparison to lots of zeros of input in the case of GPUs.
Even though GPUs and TensorFlow Lite are making amends to reduce the need to process unnecessary zeros, neuromorphic computing tackles different application scenarios.
Sparsity in signals from an event-based sensor reaches levels of 99% depending on scene activity and is therefore much higher than what a 4:2 sparsity could achieve to shrink.
In the end neuromorphic computing that can exploit the absence of new input information will have a head start in certain applications for power-critical systems that track spurious events at high speeds.
This is where GPUs that apply sparsity checks to avoid computation in a later step will not be able to compete. "
My opinion only DYOR
FF
AKIDA BALLISTA
Bravo
If ARM was an arm, BRN would be its biceps💪!
View attachment 31864 View attachment 31865
Magnus Östberg on LinkedIn: #ai #mbos #mercedesbenz
How can #AI models be trained better? This question was recently addressed by the AI Delta Learning project — a collaboration between Mercedes-Benz AG and 16…www.linkedin.com
I think it's interesting Magnus Ostberg thanks the "KI Family" and you can see that he thanks Chrisitan Witt (Valeo) whose LinkedIn page shows he is a Team Leader involved in KI Delta Learning ('21-'23). The following post describes what KI Delta Learning is all about and who else is involved in it:
Last edited:
DingoBorat
Slim
I've sent Tony an email, asking if any of our funds are in SVB, as I think it's a worthwhile query.
I will report back here, once he replys.
It's been over 2 hours mind you, doesn't he work on Saturdays
..FrederikSchack
Regular
Doesn't the tiling sound a bit like vision transformers? They also mention it being able to run transformers. They don't mention anything related to temporal?
They gave up their Zeroth SNN long time ago or did they?
The paper does refer to Prophesee.
I wonder what Gregor Lenz would have said if he had access to Akida 1000 with N-of-M coding?
Deadpool
hyper-efficient Ai
I reported zeeb0t post as Upramping, abuse of one's own power.Anytime so much as one report is received, Dreddb0t is now ready to Judge 24/7/365.
Naming and persona competition for a new feature coming soon!
Punish-bot with The Punisher personathestockexchange.com.au
This is the reply.
Unfortunately, your recent report has been rejected: Post in thread 'BRN Discussion Ongoing' - Nice try but obviously Dreddb0t knows zeeb0t has the most power.
Ha Ha. That's why I love this place.
Kachoo
Regular
If posting jobs they still have their money
Similar threads
