Stable Genius
Regular
And then there’s this image showing both Honda and Daimler at ADAS level III.
But this is my favourite Valeo quote:
Cheers
And then there’s this image showing both Honda and Daimler at ADAS level III.
Well here's a little somethin' that you can't get at home:
WO2021094065A1 METHOD FOR OPERATING A DISTANCE SENSOR OF A VEHICLE IN WHICH A TRANSMISSION SIGNAL IS ADAPTED IN ACCORDANCE WITH HOW AN OBJECT IS CLASSIFIED, COMPUTING DEVICE, AND SENSOR DEVICE
Valeo patent application from November 2019 using a neural network to classify LiDaR signals - how sweet it is.
View attachment 5148
a method for operating a distance sensor (4) of a vehicle (1), in which method a plurality of successive measurement cycles are carried out in an operating mode, wherein, in each measurement cycle, a transmission signal is transmitted, a reception signal (Rx1 to Rx8) is determined on the basis of the transmission signal reflected in a surrounding region (9) of the vehicle (1), the object (8) is classified, and the transmission signal is selected from a plurality of predefined transmission signals in accordance with how the object (8) is classified, wherein the transmission signal is selected in accordance with an assignment rule determined in a learning mode, said assignment rule describing an assignment of the plurality of predefined transmission signals to classes of objects (8), wherein, in each measurement cycle, the object (8) is classified on the basis of the reception signal (Rx1 to Rx8) and the transmission signal is selected in accordance with how the object (8) is classified for subsequent measurement cycles.
[0014] In one embodiment, a method of machine learning is used to determine the assignment rule on the basis of the respective received signals. In particular, so-called deep learning can be used. Provision can also be made for an artificial neural network and/or a generic algorithm to be used in the learning mode. Because the reference measurements for the individual reference objects are carried out with the respective transmission signals, different information is available to the learning algorithm for each individual reference object, as a result of which redundancy can be increased. Furthermore, different object shapes or classes of objects react differently to the different shapes of the transmission signals. This makes it possible to achieve better results in the training because the variance of the transmission signals takes account of the difference in the objects or object classes to be detected. In this way, more significant input data can be supplied to the deep learning algorithm used in practice.
Further and better particulars m'lud:Is not Brainchip their customer???
This is simply wild or poorly informed wishful thinking but adding up these numbers:Just realised I did leave out something which I thought of at point 1. but was in a hurry needing to buy tomatoes for lunch and it slipped my mind.
At point 2. the known unknowns should include the customers of the companies at point 1. above who will buy their products containing AKIDA IP. The prime examples being Valeo, Renesas and MegaChips.
My opinion only DYOR
FF
AKIDA BALLISTA
Further and better particulars m'lud:
DUTH are on my "Partners" list.
Nowhere was it specified that we were talking about "customers", unless you apply the ejusdem generis rule. Birds of a feather ...
This is simply wild or poorly informed wishful thinking but adding up these number:
Point 1: Including Ford and a couple of @uiux and @Rocket577 disclosures around US Miltary applications we have a comfortable 20 disclosed engagements.
Point 2. We have about 10 outstanding EAP’s and proof of concepts plus let’s say a further 10 as a result of Socionext, 10 as a result of RENESAS, 10 as a result of MegaChips 10 as a result of Valeo then well north of 100 NDA’s but say 33 to be conservative giving a total of 76 further customer engagements.
Point 3. Let me be very conservative and say that from all of the names in Rob Telson’s black book and every trade show they have attended they have picked up only 10 additional engagements
WE HAVE A GRAND TOTAL OF 106 CUSTOMER ENGAGEMENTS.
Now a history lesson for newer shareholders. The former CEO Mr. Dinardo in one of his webinars in 2020 went into detail about the advantages of targeting OEM’s (original equipment manufacturers like Valeo) but the one relevant is how it gave Brainchip a large footprint in the market and after they are up to speed they have very little impact on company resources.
Think MegaChips for example. Brainchip have trained their people and now they are doing it all sales, marketing, design, implementation.
So my wild speculation is this we know that the aim is to have around 100 employees by end of 2022.
Is a staff ratio of about one staff member for each customer engagement (106) over kill or is my total clearly an under estimate of the known unknowns and the unknown unknowns when Valeo, Socionext, Renesas & MegaChips will be absolutely low maintenance so the real number on my estimate falls back to 66 when you take their customers out of the picture.
A staff ratio of 1 employee for every .66 customer seems far too high.
If I am correct then my 106 customer engagements is rubbish and the number must be much greater.
My wild speculation etc DYOR
FF
AKIDA BALLISTA
3 billion is a lot of royalties for someone.And then there’s this image showing both Honda and Daimler at ADAS level III.
View attachment 5153
But this is my favourite Valeo quote:
View attachment 5154
Cheers
And keep in mind here we are talking about one customer only.3 billion is a lot of royalties for someone.
My opinion only DYOR
FF
AKIDA BALLISTA
That’s why I was way out on the 4c FF. I was expecting some of them royalties to start trickling in! When they finally do come in these prices will look ridiculously cheap.3 billion is a lot of royalties for someone.
My opinion only DYOR
FF
AKIDA BALLISTA
3 billion is a lot of royalties for someone.
My opinion only DYOR
FF
AKIDA BALLISTA
Afternoon Diogenese,Further and better particulars m'lud:
DUTH are on my "Partners" list.
Nowhere was it specified that we were talking about "customers", unless you apply the ejusdem generis rule. Birds of a feather ...
Afternoon Chippers,Hi All ,
Just phoned Tony Dawe , regarding the top 20 list, left a message on his answering machine.
Shall update when I receive a reply.
Esq.
Afternoon Diogenese,
Afternoon Chippers,
Tony Dawe was kind enough to return my call.
I have been asked not to disclose our conversation.
Needless to say , the top 20 has not changed much.
Tony comes across as a top bloke , willing to engage with those that are civil.
When in doubt , give him a call.
Regards,
Esq.
This bloke reckons "that BrainCHip's Akida chip is a good fit" and he looks like he knows what he's talking about if you ask me.
StereoSpike: Depth Learning with a Spiking Neural Network - 25 Nov 21
View attachment 5160
View attachment 5159
You do know who this bloke is???This bloke reckons "that BrainChip's Akida chip is a good fit" and he looks like he knows what he's talking about if you ask me.
StereoSpike: Depth Learning with a Spiking Neural Network - 25 Nov 21
View attachment 5160
View attachment 5159
He should know Bravo hes MThis bloke reckons "that BrainChip's Akida chip is a good fit" and he looks like he knows what he's talking about if you ask me.
StereoSpike: Depth Learning with a Spiking Neural Network - 25 Nov 21
View attachment 5160
View attachment 5159
You do know who this bloke is???
Mr T in JASTYou do know who this bloke is???
Give me a JYou do know who this bloke is???
Yep - that is pretty much the idiomatic translation.Afternoon Diogenese,
All I could decipher from your last post......
Birds of a feather......
Flock together.
So I assume
Afternoon Chippers,
Tony Dawe was kind enough to return my call.
I have been asked not to disclose our conversation.
Needless to say , the top 20 has not changed much.
Tony comes across as a top bloke , willing to engage with those that are civil.
When in doubt , give him a call.
Regards,
Esq.
You do know who this bloke is???