Fullmoonfever
Top 20
Congrats and happy birthday to him....shouldn't that be him blowing out candles thoughMy son's name is Paul and it's his birthday today
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Xhosa12345
Regular
Feb 25.... fml
Fullmoonfever
Top 20
The slide says edge space and I don't think True North plays in that space.
Loihi is a research chip according to most notes on it.
Jetson or Orin...maybe.
I suspect Innatera, maybe Greenwaves would be a couple....Rain possibly if we have specs and a few others as probables like Qualcomm even in the edge space.
I know a made a bit fun at it yesterday but...
Still, it is asking a bit of blind faith when we can't as investors actually compare our own research on the competitors we are competing with.
I'm curious who they are and if those competitors are already selling product and if so, why, if we stack up better as per the slide.
RobjHunt
Regular
Yeah, but there’s a reason why CEO’s tap dance
rgupta
Regular
For anyone who thinks brainchip can do wonders think these facts
1. Brainchip is too small in size and they will always need big players on their side to climb on ladder of success.
2. No company in this world can survive without their ecosystem partners. You can take example of apple, nvidia, Microsoft etc.
3. Brainchip cannot talk big until they are start getting into customers' products.
4. Even with the best product we cannot be a success unless we are friendly with big players.
5. Unlike other start ups brainchip have no God father and they have to make their own way at their own. It is a difficult work in modern time but brainchip is fighting it out which means there is something in technology.
6. Out of my experience I had not seen a single corporate boss as nice and visionary as PVDM. Show me a company with more than 60% shares to retail investors ( non institutional and promoters) To me he is like you and me otherwise he could had sit with any big player and could have been a billionaire right now.
7. Looking at all those scenarios company is starting on a mid way which is mix yourself with existing technology and find some friends and ecosystem partners. Once we get through some distance, we will start getting some recognition, then we can start penetrating and then we can start commanding.
I believe in technology and invested as per my capacity to bear losses. It is definitely more difficult to fly opposite to wind. Brainchip is trying to fight our cause with limited resources. End of the day it is patience and persistence effort which can take us to the next level.
If someone wants to make millions from brainchip then try to sacrifice a little.
If you are a believer then look through the smoke mirrors and take risk. If you want to negotiate the market then it is high risk investment.
1. Brainchip is too small in size and they will always need big players on their side to climb on ladder of success.
2. No company in this world can survive without their ecosystem partners. You can take example of apple, nvidia, Microsoft etc.
3. Brainchip cannot talk big until they are start getting into customers' products.
4. Even with the best product we cannot be a success unless we are friendly with big players.
5. Unlike other start ups brainchip have no God father and they have to make their own way at their own. It is a difficult work in modern time but brainchip is fighting it out which means there is something in technology.
6. Out of my experience I had not seen a single corporate boss as nice and visionary as PVDM. Show me a company with more than 60% shares to retail investors ( non institutional and promoters) To me he is like you and me otherwise he could had sit with any big player and could have been a billionaire right now.
7. Looking at all those scenarios company is starting on a mid way which is mix yourself with existing technology and find some friends and ecosystem partners. Once we get through some distance, we will start getting some recognition, then we can start penetrating and then we can start commanding.
I believe in technology and invested as per my capacity to bear losses. It is definitely more difficult to fly opposite to wind. Brainchip is trying to fight our cause with limited resources. End of the day it is patience and persistence effort which can take us to the next level.
If someone wants to make millions from brainchip then try to sacrifice a little.
If you are a believer then look through the smoke mirrors and take risk. If you want to negotiate the market then it is high risk investment.
Sirod69
bavarian girl ;-)
At #MWC24, Intel announced new platforms, solutions and services spanning network and edge AI, Intel Core Ultra processors and the AI PC, and more. #IAmIntel
NEWS HIGHLIGHTS
www.intel.com
NEWS HIGHLIGHTS
- Intel announced its future Intel® Xeon® processor with built-in AI acceleration, code-named Granite Rapids-D, and highlighted first-call validation with key partners.
- Intel, in collaboration with 5G core software suppliers, previewed its next-gen Intel Xeon processor for 5G core, code-named Sierra Forest, demonstrating a 2.7x performance per rack improvement1.
- Intel announced Intel’s Edge Platform, a modular and open software platform that enables enterprises to build, deploy, run, manage and scale edge and AI solutions on standard hardware with cloud-like simplicity.
- Intel will announce extended benefits of the AI PC to commercial designs with the new Intel vPro® platform, on day two of MWC 2024.
Intel Brings AI Everywhere Across Network, Edge, Enterprise
At MWC 2024, more than 65 of Intel’s leading customers and partners showcase systems and solutions across new hardware, software and services for modernizing and monetizing future infrastructure.
www.intel.com
Boab
I wish I could paint like Vincent
Not sure if I'm still barking up the wrong tree FMF but there may be some more relevant info on Page(s) 8-11??
Regards
https://brainchip.com/wp-content/uploads/2023/01/BrainChip_Benchmarking-Edge-AI-Inference-1.pdf
Hi FK,
I wish that were true, but the available evidence does not support your conclusion.
The X320 is a mini version of the Prophesee Gen 4 DVS, having about a tenth the number of pixels.
Qualcomm has their own Hexagon NPU in Snapdragon 8.2.
Snapdragon 8 Gen 2 deep dive: Everything you need to know (androidauthority.com)
Snapdragon 8 Gen 2 deep dive: Everything you need to know
All you'll ever need to know about Qualcomm's latest Snapdragon 8 Gen 2 mobile platform for next-gen phones can be found here.
www.androidauthority.com
To boost performance, the Tensor accelerator inside the DSP has doubled in size for twice the performance and has new optimizations specifically for language processing. Qualcomm is also debuting what it calls micro tile inference support, essentially chopping up imaging and other problems into smaller tiles to save on memory at the expense of some result accuracy. Along those lines, the addition of INT4 also means that developers can now implement machine learning problems requiring high bandwidth at the expense of some accuracy if compressing a larger model. Qualcomm is providing tools to partners to help support INT4, so it will require a retooling of existing applications to work.
...
Qualcomm doubled the physical link between the image signal processor (ISP), Hexagon DSP, and Adreno GPU, driving higher bandwidth and lowering latency. This allows the Snapdragon 8 Gen 2 to run much more powerful machine-learning tasks on imaging data right off the camera sensor. RAW data, for instance, can be passed directly to the DSP/AI Engine for imaging workloads, or Qualcomm can use the link to upscale low-res gaming scenarios to assist with GPU load balancing.
So it is possible that Prophesee dumbed-down its DVS so it would work with Snapdragon 8.2.
Getupthere
Regular
It could well be that the competition may well be our partners or future customers however if you are presenting information for new investors then it’s not a good look saying that your technology is better then competitors when you won’t even name the competition.
Better not have the comparision in the first place.
cassip
Regular
Yesterday I read about "catastropic forgetting" of neural networks. Does anybody know if/how Akida deals with this?
see, for example, here:
"Hebbain Learning based orthogonal projection for continual learning of spiking neural networks" (19.2.24)
https://arxiv.org/abs/2402.11984
and:
"Overcoming catastrophic forgetting in neural networks" (2016)
arxiv.org
"A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost" (2023)
see, for example, here:
"Hebbain Learning based orthogonal projection for continual learning of spiking neural networks" (19.2.24)
https://arxiv.org/abs/2402.11984
and:
"Overcoming catastrophic forgetting in neural networks" (2016)
Overcoming catastrophic forgetting in neural networks
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is...
"A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost" (2023)
Perhaps
Regular
Wow, "smart" and "AI" has triggered me. Must be Akida inside, right?Published Feb 26, 2024
Apple Reportedly Exploring Smart Glasses, Adding AI to AirPods
Some Apple employees also want the tech giant to develop a fitness ring, but that's not currently in active development, Bloomberg reports.au.pcmag.com
EXTRACT
View attachment 57974
Bravo
If ARM was an arm, BRN would be its biceps💪!
What’s your problem dude?
Terroni2105
Founding Member
Hi Fmf , do you have the link for todays preso? I watched it live and haven’t been able to find the link since to watch it again.Was finally watching the presso and my word....if you listen to it backwards it reveals the NDA partners
thanks.
Off the top of my head, I think that amnesia only occurs with back propagation ML, which Akida does not do. Akida adjusts the last layer only during ML.Yesterday I read about "catastropic forgetting" of neural networks. Does anybody know if/how Akida deals with this?
see, for example, here:
"Hebbain Learning based orthogonal projection for continual learning of spiking neural networks" (19.2.24)
https://arxiv.org/abs/2402.11984
and:
"Overcoming catastrophic forgetting in neural networks" (2016)
Overcoming catastrophic forgetting in neural networks
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is...
"A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost" (2023)
Food4 thought
Regular
Germany is down 24 % at present
Back to where we were a month ago.
Time to buy more shares again.
Back to where we were a month ago.
Time to buy more shares again.
Perhaps
Regular
Just think about it, some others maybe too:
ASX speeding tickets triple on social media-driven speculation
The number of price queries issued by the market operator has jumped due to market volatility.
Fullmoonfever
Top 20
I see where you're coming from but those are from MCU performances in key areas against Akida ie keyword spotting.
The MCUs used are publicly available results as noted in the presso and are for tiny/ml.
If it was that they considered the Jetson nano a competitor in the other table then why not list it as they have listed it in the tiny/ml comparisons that we would essentially be competing against.
I'd love to but but......
Fullmoonfever
Top 20
Sorry T but no.
I was having some fun for those of us old enough to remember vinyl and the conspiracy theories way back about playing them backwards for hidden or sublimal messages.
Similar threads
