rgupta
Regular
Is it?
Hi manny100,
I presume you meant to say commercial neuromorphic Edge AI solutions rather than commercial Edge AI solutions in general? But even then, your statement is incorrect. SynSense also offers commercial neuromorphic solutions by now, and so does Innatera:
See this article dated February 6, 2024:
“Innatera, a spinout from the University of Delft, has grown to 65 people with recent funding from the European Innovation Council (15.5 million Euro) alongside Matterwave Ventures and MIG Capital. Commercial samples of the T1 and hardware evaluation kits are available now while the T1 will ramp to production quantities in the second half of this year.”
After Mercedes Chief Software Officer Magnus Östberg had posted “Neuromorphic computing? We’ve got that. ” on LinkedIn earlier this year, I noticed Innatera’s CEO Sumeet Kumar commenting on his post, and subsequently two neuromorphic researchers at Mercedes liking Sumeet Kumar’s post, so those in the industry involved in neuromorphic tech are evidently aware of the choices they have besides implementing Akida. Of course all those neuromorphic solutions available differ from each other in various aspects - Innatera’s T1 spiking neural processor, for example, is not digital and does not have on-chip learning:
View attachment 63165
Magnus Östberg on LinkedIn: #neuromorphic #ml #ai #intel #leadincarsoftware | 38 comments
Neuromorphic computing? We’ve got that. 😎 Because it’s still nascent technology, I am frequently asked to describe #neuromorphic computing. It is a paradigm… | 38 comments on LinkedInwww.linkedin.com
View attachment 63163
View attachment 63164
The BrainChip website and LinkedIn profile reflect this development by no longer talking about offering the only commercially available neuromorphic processor, but by using the term ‘first-to-market’ nowadays:
“BrainChip’s first-to-market, digital neuromorphic processor IP, akidaTM, mimics the human brain to analyze only essential sensor inputs at the point of acquisition—processing data with unparalleled performance, precision, and reduced power consumption.”
Whether or not Akida is the overall best neuromorphic solution available is an entirely different matter. But to say it is “an indisputable fact” that BrainChip offers “the only ‘cloudless’ commercial solution ATM” is simply wrong.
I do agree with you, though, regarding what you said about the BRN share price:
Regards
Frangipani
To me this tweet is very informative especially from non technical and technical views.Is it?
Hi manny100,
I presume you meant to say commercial neuromorphic Edge AI solutions rather than commercial Edge AI solutions in general? But even then, your statement is incorrect. SynSense also offers commercial neuromorphic solutions by now, and so does Innatera:
See this article dated February 6, 2024:
“Innatera, a spinout from the University of Delft, has grown to 65 people with recent funding from the European Innovation Council (15.5 million Euro) alongside Matterwave Ventures and MIG Capital. Commercial samples of the T1 and hardware evaluation kits are available now while the T1 will ramp to production quantities in the second half of this year.”
After Mercedes Chief Software Officer Magnus Östberg had posted “Neuromorphic computing? We’ve got that. ” on LinkedIn earlier this year, I noticed Innatera’s CEO Sumeet Kumar commenting on his post, and subsequently two neuromorphic researchers at Mercedes liking Sumeet Kumar’s post, so those in the industry involved in neuromorphic tech are evidently aware of the choices they have besides implementing Akida. Of course all those neuromorphic solutions available differ from each other in various aspects - Innatera’s T1 spiking neural processor, for example, is not digital and does not have on-chip learning:
View attachment 63165
Magnus Östberg on LinkedIn: #neuromorphic #ml #ai #intel #leadincarsoftware | 38 comments
Neuromorphic computing? We’ve got that. 😎 Because it’s still nascent technology, I am frequently asked to describe #neuromorphic computing. It is a paradigm… | 38 comments on LinkedInwww.linkedin.com
View attachment 63163
View attachment 63164
The BrainChip website and LinkedIn profile reflect this development by no longer talking about offering the only commercially available neuromorphic processor, but by using the term ‘first-to-market’ nowadays:
“BrainChip’s first-to-market, digital neuromorphic processor IP, akidaTM, mimics the human brain to analyze only essential sensor inputs at the point of acquisition—processing data with unparalleled performance, precision, and reduced power consumption.”
Whether or not Akida is the overall best neuromorphic solution available is an entirely different matter. But to say it is “an indisputable fact” that BrainChip offers “the only ‘cloudless’ commercial solution ATM” is simply wrong.
I do agree with you, though, regarding what you said about the BRN share price:
Regards
Frangipani
In memory compute is what neurophonic can do but memory is very limited. Which means we need different algorithms as compared to modern day.
So to me just like prophesse had an event based camera but not an event based processor, we have an event based processor but limited memory. Which means product have unlimited capabilities but limited use. So to me it is taking time to develop efficient models for neurophonic and that is where it is taking so much of time. The task is not impossible but definitely very tough.
Dyor