Jacob Kiraz
Regular
Very good post
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Interesting to see that Kevin reposted the SpaceX post.
Do you think there will come a point where companies will boast that Akida's inside?
www.linkedin.com
Do you think there will come a point where companies will boast that Akida's inside?
Sign Up | LinkedIn
500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.
Last edited:
smoothsailing18
Regular
% they have and it's all fantastic on the low low.
Mt09
Regular
Sign Up | LinkedIn
500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.
Attachments
Okeydokey01
Regular
Thank you SS and MT. Hopefully the low key response from the company acccount rather than individual employees is a sign of things to come. Perhaps given its IBM and what’s potentially at stake a directive to all staff for radio silence? Fingers crossed hey, god knows we need something to stick.
Fullmoonfever
Top 20
smoothsailing18
Regular
I hear you, Hanging there butter cup we'll get there, deep breaths.
Last edited:
From the recent Steve Brightfield interview. His predictions:
"But do your question. I think we're trying to ride the neuromorphic computing and brain chip in particular is trying to ride the coattails of the overall market moving to the edge. And when we look at market research reports from companies, they're saying about 10% of these edge products embedded devices are running some AI software on them. But within the next four years, four to five years, 30 to 35% of those products will have AI on. And I think if we look out, the next five years, 90% of them will have it all embedded in it. And there will be a neuromorphic computing in probably half of those devices. "
My bold above.
"But do your question. I think we're trying to ride the neuromorphic computing and brain chip in particular is trying to ride the coattails of the overall market moving to the edge. And when we look at market research reports from companies, they're saying about 10% of these edge products embedded devices are running some AI software on them. But within the next four years, four to five years, 30 to 35% of those products will have AI on. And I think if we look out, the next five years, 90% of them will have it all embedded in it. And there will be a neuromorphic computing in probably half of those devices. "
My bold above.
Steve Brightfield provided an insight in what Brainchip is doing with Ear Buds/Hearing Aids.
" We're using neuromorphics for the input signaling because of the advantages of this far state, but when we get to some of the large language models, we don't use the neuromorphic algorithms, we use the state space models. And we're looking at combining those two into a single, you know, platform so that you get the enhancement of the signal going into the speech recognition, the speech recognition with the LM can predict what next word is being said and improve the accuracy of the recognition. And then you can have a local, large language model in your earpiece that could have maybe a very limited set of information in it, but it's what you need, right? One of the interesting use cases is a memory LLM for an old person. And you know, it would say, "Oh, your granddaughter's name is Shelley and she's four years old." And so that when you can, if you don't forget this stuff, boom, you have it, right? And you just need to some cues some time to get your memory back. And this is one of those interesting things that we're like the Nationalist to Health says, "This could be really good because that helps solve a lot of these issues with, if you can't hear well, you start having dementia and you start having, you know, problems, cognition problems, right? It's very important to have, you know, hearing insight to keep yourself, your brain healthy because your brain, that's what it's doing. It's constantly processing those signals. "
" We're using neuromorphics for the input signaling because of the advantages of this far state, but when we get to some of the large language models, we don't use the neuromorphic algorithms, we use the state space models. And we're looking at combining those two into a single, you know, platform so that you get the enhancement of the signal going into the speech recognition, the speech recognition with the LM can predict what next word is being said and improve the accuracy of the recognition. And then you can have a local, large language model in your earpiece that could have maybe a very limited set of information in it, but it's what you need, right? One of the interesting use cases is a memory LLM for an old person. And you know, it would say, "Oh, your granddaughter's name is Shelley and she's four years old." And so that when you can, if you don't forget this stuff, boom, you have it, right? And you just need to some cues some time to get your memory back. And this is one of those interesting things that we're like the Nationalist to Health says, "This could be really good because that helps solve a lot of these issues with, if you can't hear well, you start having dementia and you start having, you know, problems, cognition problems, right? It's very important to have, you know, hearing insight to keep yourself, your brain healthy because your brain, that's what it's doing. It's constantly processing those signals. "
A little bit more from Steve Brightfield.
Radar new capabilities in recognising objects (not possible with traditional radar) and how this is transferable to robotics and that Brainchip is in discussions with robotics companies.
He introduces the concept of braintags - we have all heard of airtags - i did not include the detail of that in the quote below as it was starting to get to long. Basically the BrainTag is an AirTag with a tiny AI brain inside. It can listen, recognise sounds, and understand events using an ultra‑low‑power neuromorphic chip, all without sending audio to the cloud.
" What's around the corner or over the horizon? One of the things that was interesting is we got a contract with Air Force research libraries to work on radar using these algorithms, right? And the results actually surprised us and they surprised the contracting agency and now we're expanding that. And we think that we can, you know, add capabilities to radar that weren't there before. Like, for example, radar can detect things, right? But it can't tell you what it is. Well, we can classify objects now with radar in addition to detecting them. We can improve the tracking and the latency of these radars. But we can also make them a lot smaller, right? So it's that size weight and power. Can I put a radar in a robot? So when it's hand has got a radar signal in it and it can basically navigate, you can paint the scene without a camera. You can use it like a camera to paint the scene and recognize and grasp things that a drone. You can fly it inside tunnels or buildings indoors. You can map out where you're going. We see this shrinking of the conventional radar technologies to really go into anything moving because it's all whether it works in the dark. And if it can replicate some of the things in vision, then, you know, you don't have to worry about rain and fog and all the issues that visual, you know, control of robots. Yeah. And are you working with robotic companies or is this still in the research room? It's still in the research. We're working with companies that are creating components or solutions that go to the robotics companies. We are in active conversations with robotic companies today. And they're in evaluation of this, right? But what we decided was to create reference platforms that demonstrate these more holy rather than having a, you know, here's the algorithm go figured out. We'll build a little prototype. So we're doing reference designs and radar. We're also going to do this in these wearables. And this is a quite interesting approach. You know, the air tag, right? Yep. What about having a brain tag? It's a smart air tag, right? It's got inferencing on it."
Radar new capabilities in recognising objects (not possible with traditional radar) and how this is transferable to robotics and that Brainchip is in discussions with robotics companies.
He introduces the concept of braintags - we have all heard of airtags - i did not include the detail of that in the quote below as it was starting to get to long. Basically the BrainTag is an AirTag with a tiny AI brain inside. It can listen, recognise sounds, and understand events using an ultra‑low‑power neuromorphic chip, all without sending audio to the cloud.
" What's around the corner or over the horizon? One of the things that was interesting is we got a contract with Air Force research libraries to work on radar using these algorithms, right? And the results actually surprised us and they surprised the contracting agency and now we're expanding that. And we think that we can, you know, add capabilities to radar that weren't there before. Like, for example, radar can detect things, right? But it can't tell you what it is. Well, we can classify objects now with radar in addition to detecting them. We can improve the tracking and the latency of these radars. But we can also make them a lot smaller, right? So it's that size weight and power. Can I put a radar in a robot? So when it's hand has got a radar signal in it and it can basically navigate, you can paint the scene without a camera. You can use it like a camera to paint the scene and recognize and grasp things that a drone. You can fly it inside tunnels or buildings indoors. You can map out where you're going. We see this shrinking of the conventional radar technologies to really go into anything moving because it's all whether it works in the dark. And if it can replicate some of the things in vision, then, you know, you don't have to worry about rain and fog and all the issues that visual, you know, control of robots. Yeah. And are you working with robotic companies or is this still in the research room? It's still in the research. We're working with companies that are creating components or solutions that go to the robotics companies. We are in active conversations with robotic companies today. And they're in evaluation of this, right? But what we decided was to create reference platforms that demonstrate these more holy rather than having a, you know, here's the algorithm go figured out. We'll build a little prototype. So we're doing reference designs and radar. We're also going to do this in these wearables. And this is a quite interesting approach. You know, the air tag, right? Yep. What about having a brain tag? It's a smart air tag, right? It's got inferencing on it."
Last edited:
Hi Manny,
Some months ago Tony Lewis made an offhand remark which indicated that TENNs state space model was different from Akida NN, and here is a clearer statement from Steve:
"We're using neuromorphics for the input signaling because of the advantages of this far state, but when we get to some of the large language models, we don't use the neuromorphic algorithms, we use the state space models. And we're looking at combining those two into a single, you know, platform so that you get the enhancement of the signal going into the speech recognition, the speech recognition with the LM can predict what next word is being said and improve the accuracy of the recognition."
To me, this clarifies that we have 2 different types of AI processors, and this is reflected in our projected product range. Akida 1, 1599, 2 are the original SNN architecture, while Akida 2 and GenAI implement TENNs. SSM. According to Steve, BRN are developing a hybrid SSN/SSM device which takes advantage of the capabilities of both the SNN for speech recognition and the SSM for speech processing.
No doubt there is a patent application in the offing.
White Horse
Regular
You and quite a few others just don't get it.
Sean does not decide policy, he just implements what the board dictates.
Now Antonio, that's another question.
AusEire
Founding Member.
Is this a threat?
BrainChip Announces Immediate Availability of Akida™ Pico for Remote Evaluation via FPGA Cloud | Markus May
☝ BrainChip Announces Immediate Availability of Akida™ Pico for Remote Evaluation via FPGA Cloud. #pico #futureofcomputing #akida #edge #neuromorphic #milliwatt https://lnkd.in/eVB-5xcS
?
www.linkedin.com
#3nmchip #semiconductor #tsmc #japan | Ashirvadh A Nair
TSMC to Make Advanced Chips at Japan Plant Taiwan Semiconductor Manufacturing Company (TSMC), the world’s largest contract semiconductor manufacturer, has revealed plans to begin the production of advanced three-nanometre (3nm) chips in Japan a landmark step that would bring one of the most...
#fpga #cloud #ai #semiip #ipcores #semiconductor #embedded | Semi IP Hub
BrainChip Announces Immediate Availability of Akida™ Pico for Remote Evaluation via #FPGA #Cloud https://lnkd.in/dA3Ztmr6 “By providing remote access to our Akida IP via FPGAs, we are removing the traditional hardware barriers for engineers,” said Sean Hehir, CEO at BrainChip. “Whether they are...
The Pope
Regular
Unsure if this TRIM capital report from Sept 25 has been posted on TSE but a interesting read from their point of view
The Pope
Regular
Interesting what Rudy has been doing 1 year at Nvidia and Steven Thorne made comment
www.linkedin.com
#nvidia #dynamo #nvidia | Rudy Pei | 11 comments
One year at #NVIDIA 🎉 (NVIDIAsary?) A lot has happened in the past year, and it’s hard to condense it into a single LinkedIn post. I went from a complete noob in basic async programming to architecting core distributed systems in #Dynamo that are now used by many teams. None of this would have...
I am on LinkedIn. I can confirm that Pia has not liked the postings. Matter of fact she has not liked anything that came from the company or linked to the company. Ever.
I think her role in the company specifically says don't like anything and get paid.
Brilliant. Well done.
Similar threads
