BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
toasty
Regular
I've said it before but once more for the dummies.....Peter and Anil would not have spent the time and money on taping it out if they weren't confident it was going to work...................
Papacass
Regular
Hey JK. I’ve been around for about 6 years as well. You may remember when AKD1000 was on tbe bench we all pretty much knew what it was capable of because of the Akida development environment. When it went to silicon it exceeded expectations. I am confident the same will occur with AKD1500. Asking what will happen if it fails to deliver as expected is pointless. We all know the answer to that. I reiterate that the brains trust at BRN know how AKD will perform. They would not have gone to tape out otherwise. Cheers. Onward.
I understand your point. I will look forward to see better and wise views from you. Please don't throw anything like "What if fails".
I just topped up all of my quarterly bonus today because I believe in BRN and the Management.
Well we have to allow for that possibility because, while Anil is the King of CMOS, he would not have the same level of experience with FD-SOI.
That said, I'm confident his experience, dedication, and meticulousness will win through - that and the FD-SOI experts he engages. Engineers understand theoretical limits and safety factors.
The design will have been thoroughly tested by simulation before tape-out commenced.
In the unlikely event that it is not 100%, an autopsy will find the problem and it will work the second time around.
Fullmoonfever
Top 20
To be fair though.
You bench test the shit outta something and show that it works and that in theory moving to a physical implementation should produce the same.
However, couple of known variables in the 1500 that need to be considered.
(We don't fully understand any other potential variable / enhanced capability impacts in the design yet).
So...
22nm not 28nm and FDSOI vs CMOS.
Doesn't mean will be issues at all, just means that it's not proven physically as yet until Fab'd imo.
That should be a milestone Ann imo once confirmed working as designed.
You bench test the shit outta something and show that it works and that in theory moving to a physical implementation should produce the same.
However, couple of known variables in the 1500 that need to be considered.
(We don't fully understand any other potential variable / enhanced capability impacts in the design yet).
So...
22nm not 28nm and FDSOI vs CMOS.
Doesn't mean will be issues at all, just means that it's not proven physically as yet until Fab'd imo.
That should be a milestone Ann imo once confirmed working as designed.
DollazAndSense
Regular
Well this is quite a pointless, rhetorical question as we all know the answer would not be good for any business to have an unsatisfactory product.
I would ask you to look back at Brainchip’s history and ask yourself if you truly think it will be a one off that Peter and Anil created a more than satisfactory product.
"Aliso Viejo, Calif. – 8 November, 2021 – BrainChip Holdings Ltd (ASX: BRN), (OTCQX: BCHPY), a leading provider of ultra-low power, high-performance artificial intelligence technology and the world’s first commercial producer of neuromorphic AI chips, today confirmed that functionality and performance testing of the AKD1000 production chips has been completed, which showed better performance than the original engineering samples.
As part of the continued development of its Akida™ Neuromorphic System-on-Chip (NSoC), BrainChip tested a production version of its AKD1000 chip with several neural network applications, including object classification, keyword spotting and spiking neural networks. The improved performance and lower power consumption results were achieved through a better layout and some minor design changes to the design, which were recognized after previous testing of earlier engineering samples."
Can I ask why after 6 years of belief in Brainchip, you suddenly feel like Akida won't measure up?
BaconLover
Founding Member
I don't think it's his disbelief.
From his question, (as I understand) he was trying to know the process of "what if" such a scenario were to occur.
Slymeat
Move on, nothing to see.
PVD has offered an open invitation, on linked in, to go and let him know what info you want him to share. What a great opportunity.
www.linkedin.com
Peter Van Der Made on LinkedIn: #neuromorphic #neuroscience #cortical #innovation #technology
Hey LinkedIn! If you’re new to following me, I talk about #neuromorphic, #neuroscience, #cortical, #innovation, and #technology. Let me know which topic…
cassip
Regular
"As for the rest of BMW’s new lineup, such as the 7 Series and upcoming 5 Series, there’s going to be an iDrive 8.5 that replaces the current iDrive 8. But don’t fret. The user of interface of iDrive 8.5 is identical to iDrive 9. Why do the flagship models only get iDrive 8.5, while the entry-level X1 and X2 get iDrive 9? It has to do with the basic coding platforms each car uses.
Cars like the BMW 7 Series, 5 Series, and most other BMW models have Linux-based systems, while the new X1, X2, and future MINIs have Android-based systems. So the updated iDrive systems have to be slightly different to work with each system. However, both iDrive 8.5 and iDrive 9 will look identical and have the same user interface. The only differences between the two will be functionality, as iDrive 8.5 will lack some of the features that are available on iDrive 9. For instance, iDrive 9 will get an app store, while iDrive 8.5 won’t.
While BMW is heavily updating its iDrive for this new generation, it’s still going to be mostly touchscreen base. In the case of the X1, it’s entirely touchscreen-based, which is sure to upset some fans (myself included). However, BMW plans on advanced voice recognition bcoming the main form of interaction with iDrive, for better or worse."
BMW iDrive 9 Coming to BMW X1 in Two Months, iDrive 8.5 to others
The BMW X1 will get an all-new iDrive 9, replacing the old iDrive 8, and it will bring with it an all new user interface, new functionality, and even an app store.
Tothemoon24
Top 20
Slymeat
Move on, nothing to see.
WBT's product is simply much more well understood than Brainchip's.
Everyone already knows where RAM and FLASH memory are currently used and what it does. They can easily see that the far superior ReRAM can easily be swapped in its place and hence they can see value in ReRAM and Weebit.
On the other hand, very few truly understand the advantages offered by Akida and struggle to see its value.
Implementations using ReRAM will not suffer a development cycle and subsequent lag in getting to market, unlike products employing Akida which will take years to come to market. I also expect less (even zero) NDAs for Weebit customers. Except those maybe using ReRAM for novel products and with advantage over competitors.
IMHO, and note this is ONLY my opinion even as honest as it can be, I believe time will show that both companies are EXTREMELY undervalued. They both have a lot of room to grow, and grow they both will. They each have HUGE TAMs—large enough to allow many competitors even.
Also IMHO, Weebit's ReRAM doesn't have as wide a moat as Brainchip's Akida. Other ReRAM offerings already exist. Weebit will probably market their offering as a viable alternative to ReRAM from the big players, such as TSMC. But I do believe Weebit have a bit of a moat with their selector, which they are still trying to improve.
And note: Weebit is currently forming some huge partnerships. Players will be knocking down the doors on both companies soon.
And as a final say: many on this forum would already be aware of my efforts to get Weebit and Brainchip into a partnership. If that happens, their growth will feed off, and self-promote, each other.
cosors
👀
WoW, thanks for the tip I really appreciate it! Then maybe I could have saved some stupid questions (e.g. about the selector.)Coby touched on this at the meet and greet. Don't quote me but I think he said that it was a long term goal.
EDIT: How good is Youtube transcript feature! Here are his exact words (complete with um's)
"if you look at further in terms of the AI neuromorphic stuff there's a question that's coming around is there any update on the research that's been undertaken in that space. Um there's ongoing work uh you know talking about short and Midterm I always said that's the longer term that's uh not something that's really anywhere in in the near term so there is work going on with these research institutes there's progress being made um but it's right now we're so swamped with the short term with getting um getting these uh initial Fab agreements customer agreements".
_____
For me I have the perfect candidate for the transscript function. I sometimes find it really hard to understand Indians
MosChip
https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-236654
Last edited:
Tothemoon24
Top 20
Real-time intelligent fusion service, forklift-assist program could enhance warehouse efficiency, safety
Anna Akins February 7, 2023
Real-time intelligent fusion service, forklift-assist program could enhance warehouse efficiency, safety
A photo showing how GTRI's Real-Time Intelligent Fusion Service would appear to a forklift driver. By giving warehouse workers real-time information about everything going on in the warehouse, RIFS could help reduce the risk of accidents and streamline efficiencies. Credit: Stephen Balakirsky, GTRI
Although warehouses are vital to the success of many organizations, they can also be dangerous to workers and inefficient.
The Georgia Tech Research Institute (GTRI) is working to solve this challenge by integrating its Real-time Intelligent Fusion Service (RIFS) into its Forklift Assist System (FAS) for warehouse operations to streamline efficiencies and enhance worker safety. RIFS, which is a part of FAS, was built with the cross-platform game engine Unity and produces spatial information about a room and then displays that information as meshes on a device, such as a desktop computer or tablet. FAS also includes a camera system that has additional forklift assistance features.
This project has been supported by the U.S. Marine Corps and U.S. Navy, and has also been tested at the Marine Corps Logistics Base in Albany, Georgia.
According to recent estimates, the average U.S. warehouse wastes 6.9 weeks a year on unnecessary motion, which costs the industry $4.3 billion, or 265 million hours of labor annually. Additionally, in 2020, the latest year for which statistics are available, there were 5.5 injury and illness cases per 100 full-time workers and 21 fatalities in the warehouse and storage industry.
RIFS would be incorporated into a warehouse's order management system and provide real-time information about everything going on in the warehouse. For example, a forklift operator could display RIFS on their tablet device and it would help them navigate to their pick up and drop off locations while ensuring they steer clear of obstacles.
"The system would know where all the other forklifts and people are in the warehouse and have route planning functionality," said Stephen Balakirsky, a GTRI principal research scientist who is leading the project. "A lot of warehouses have one-way aisles and it can be difficult for humans to determine the most efficient path to take, but RIFS could automatically determine that for you."
RIFS works by creating a grid of a particular environment with individual grid spaces that indicate which areas are traversable or not, explained GTRI Research Scientist Emily Strube, who has expertise with RIFS. The software then utilizes a pathfinding algorithm to determine the effort or "cost" required to move from one grid space to another and maps out the most efficient path possible. People and objects are shown as meshes, or geometric objects, in RIFS.
For example, in a warehouse, the algorithm would determine how much effort is required for a worker to move from their current position to their pick up or drop off point and outlines the most expedient route, Strube said.
She added that the algorithm can be adjusted to accommodate changes in a warehouse's workflow and forklift routes.
FAS' camera system would help forklift drivers move towards a pallet and secure it without damaging the warehouse's infrastructure or other pallets and items. The camera system would also have a backup feature to give drivers additional awareness as they move throughout the space in reverse.
To reduce the risk of forklift loads colliding with the top of doorframes, GTRI is also considering developing and installing sensors near doorways to alert drivers of imminent collisions.
"There are lots of different safety features that could be added to this project," Balakirsky said.
Additionally, GTRI seeks to further utilize RIFS to provide remote inspection and validation of inventory through virtual reality (VR) technology, where the warehouse maps and images would be created by autonomous robots.
RIFS has been incorporated into several other projects, including GTRI's Independent Research and Development (IRAD) of the Year winner for fiscal year 2022, which Strube leads. That project seeks to increase the situational awareness of troops on the ground.
Provided by Georgia Institute of Technology
ga
Anna Akins February 7, 2023
Real-time intelligent fusion service, forklift-assist program could enhance warehouse efficiency, safety
A photo showing how GTRI's Real-Time Intelligent Fusion Service would appear to a forklift driver. By giving warehouse workers real-time information about everything going on in the warehouse, RIFS could help reduce the risk of accidents and streamline efficiencies. Credit: Stephen Balakirsky, GTRI
Although warehouses are vital to the success of many organizations, they can also be dangerous to workers and inefficient.
The Georgia Tech Research Institute (GTRI) is working to solve this challenge by integrating its Real-time Intelligent Fusion Service (RIFS) into its Forklift Assist System (FAS) for warehouse operations to streamline efficiencies and enhance worker safety. RIFS, which is a part of FAS, was built with the cross-platform game engine Unity and produces spatial information about a room and then displays that information as meshes on a device, such as a desktop computer or tablet. FAS also includes a camera system that has additional forklift assistance features.
This project has been supported by the U.S. Marine Corps and U.S. Navy, and has also been tested at the Marine Corps Logistics Base in Albany, Georgia.
According to recent estimates, the average U.S. warehouse wastes 6.9 weeks a year on unnecessary motion, which costs the industry $4.3 billion, or 265 million hours of labor annually. Additionally, in 2020, the latest year for which statistics are available, there were 5.5 injury and illness cases per 100 full-time workers and 21 fatalities in the warehouse and storage industry.
RIFS would be incorporated into a warehouse's order management system and provide real-time information about everything going on in the warehouse. For example, a forklift operator could display RIFS on their tablet device and it would help them navigate to their pick up and drop off locations while ensuring they steer clear of obstacles.
"The system would know where all the other forklifts and people are in the warehouse and have route planning functionality," said Stephen Balakirsky, a GTRI principal research scientist who is leading the project. "A lot of warehouses have one-way aisles and it can be difficult for humans to determine the most efficient path to take, but RIFS could automatically determine that for you."
RIFS works by creating a grid of a particular environment with individual grid spaces that indicate which areas are traversable or not, explained GTRI Research Scientist Emily Strube, who has expertise with RIFS. The software then utilizes a pathfinding algorithm to determine the effort or "cost" required to move from one grid space to another and maps out the most efficient path possible. People and objects are shown as meshes, or geometric objects, in RIFS.
For example, in a warehouse, the algorithm would determine how much effort is required for a worker to move from their current position to their pick up or drop off point and outlines the most expedient route, Strube said.
She added that the algorithm can be adjusted to accommodate changes in a warehouse's workflow and forklift routes.
FAS' camera system would help forklift drivers move towards a pallet and secure it without damaging the warehouse's infrastructure or other pallets and items. The camera system would also have a backup feature to give drivers additional awareness as they move throughout the space in reverse.
To reduce the risk of forklift loads colliding with the top of doorframes, GTRI is also considering developing and installing sensors near doorways to alert drivers of imminent collisions.
"There are lots of different safety features that could be added to this project," Balakirsky said.
Additionally, GTRI seeks to further utilize RIFS to provide remote inspection and validation of inventory through virtual reality (VR) technology, where the warehouse maps and images would be created by autonomous robots.
RIFS has been incorporated into several other projects, including GTRI's Independent Research and Development (IRAD) of the Year winner for fiscal year 2022, which Strube leads. That project seeks to increase the situational awareness of troops on the ground.
Provided by Georgia Institute of Technology
ga
JK200SX
Regular
Thank you to @Diogenese and @BaconLover , that was what I was trying to get at.
I don't doubt the technology and do have faith in the Brainchip team. Whilst I'm sure that they have done their utmost due diligence, there is that 1% chance of something not going according to plan and was interested in understanding potential contingencies, such as speed tracking the AKD2000, etc..
I didn't ask the question lightly, in vain, or in any way to undermine any one else on the forum, or cast doubt in their mind about the technology - In my time as an Engineer in the automotive industry I've seen high profile projects go pear shaped. These weren't projects/products managed & developed by any of our teams in Australia. These were lead by dream teams out of Detroit, Frankfurt & Berlin, and yet they did at times managed to get it wrong. What was important was the subsequent recovery and how quickly they could get back on track.
(To the other poster, you were wrong, I'm only 4
).
D
Deleted member 118
Guest
And NASA have some of the best scientists and professors working on AI and I believe they have probably been working along side brainchip into getting this to taping out.I've said it before but once more for the dummies.....Peter and Anil would not have spent the time and money on taping it out if they weren't confident it was going to work...................
Shit did I just write something normal, I must be getting old.
Last edited by a moderator:
Xhosa12345
Regular
equanimous
Norse clairvoyant shapeshifter goddess
Gender reveal fail
alwaysgreen
Top 20
It's an.....orange! Congratulations you are having a fruit.
Also, I hate gender reveals. Such a self righteous act.
Similar threads
