Fox151
Regular
Sorry, are you lost? Can someone point this dude back to the crapper?
How have you escaped @zeebot's moderation for this long?
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
How have you escaped @zeebot's moderation for this long?
ndefries
Regular
laughing - can the beheading occur at a set time so i can watch
equanimous
Norse clairvoyant shapeshifter goddess
Seeing as Sony have partnered up with Prophesee I wander if the smart phone applications will apply here in near futureThanks for posting Jesse,
Holy Shit Balls that was a fantabolus podcast
Now bear with me this is all from my dodgy memory.
"we are very excited about collaboration with BrainChip, we are natural partners, before Brainchip they were facing integration problems, which was impacting sensor performance, so now combining Prophesee & Brainchip we are finishing the half story we were missing from the beginning, it is now complete, so now we can tell a full story to our customers.....WOW"
Three examples of use cases that Prophesee are currently working on & some I think he said they have been working on for the last 3 years are;
1. Industrial application - High speed fast accurate barcode detection on fast moving boxes
2. Automotive application - Event based camera state of the art object detection for sensors in cars to detect pedestrians or other objects in poor lighting & then for example applying the brakes
3. Mobile Application - Computational imaging for smart phone, our event based sensor will combine with regular frame based sensor to take best images, we capture moving object & we can help correct blurry images that would be taken with just a regular frame based sensor
This is what Prophesee thinks of Akida
And this is what BrainChip thinks about Prophesee
And this is what I think of our Partnership
Dang Son
Regular
BrainChip, Prophesee to deliver “neuromorphic” event-based vision systems for OEMs
Jun 24, 2022 | Abhishek JadhavCATEGORIES Edge Computing News | Hardware
BrainChip, a neuromorphic computing IP vendor, and Prophesee, an embedded neuromorphic vision systems vendor, have partnered to deliver advanced event-based vision systems with integrated low-power technology coupled with high AI performance.
The collaboration will enable enterprise customers to explore edge artificial intelligence use cases with neuromorphic vision systems. Neuromorphic systems function in a way not unlike how living brains function. As such, they are better for different tasks than one generally would feed to artificial-intelligence algorithms. The systems process individual real-world data samples immediately with low latency and power consumption.
Paris-based Prophesee has developed advanced neuromorphic vision systems through their patented sensor design and AI algorithms. Event-based vision systems are expected to take over the traditional frame-based approach to make machine vision more accessible and practical for developers.
“We have successfully ported the data from Prophesee’s neuromorphic-based camera sensor to process inference on Akida with high performance,” said Anil Mankar, co-founder and CDO of BrainChip. “This combination of machine vision sensors with Akida’s ability to process data with improved efficiency, precision and energy-efficient at the point of acquisition advances state-of-the-art AI enablement and offers manufacturers ready-to-implement solutions.”
What is an event-based vision?
The research to evaluate human vision capabilities have taken a big leap over the last couple of years. Existing research shows that humans can gather data from a scene that is changing at a rate of up to 1000 times a second. However, this information is encoded, which is likely impossible for fixed frame-rate cameras to observe using the typical 60 frames per second that high-quality cameras record.To change this paradigm, event-based sensing has garnered attention. Event-based vision systems rely on each pixel to sense significant change and reduce the recording of redundant data to save processing power, memory and other associated resources.
Basically, event-based vision systems are inspired by the way the human eye works; this miniature vision system enables efficient streaming of visual data for real-time analytics. This vision system has enabled enterprises and manufacturers to track high-speed moving objects, which is far from the capabilities of standard fixed frame-rate cameras. Neuromorphic vision system vendors are developing efficient and advanced machine learning algorithms to achieve higher temporal resolution and lower latency.
Prophesee is known for developing an event-based vision solutions ecosystem that comes with software and hardware integration to enable developers to build advanced used cases for a wide range of markets. Prophesee built 4-sensor generations, with the latest coming from the collaboration between Sony and Prophesee. The Metavision evaluation kit is designed for field testing conditions supported by an IMX636ES sensor inside a 30x30x36 mm box weighing 40 grams.
On the software side of the event-based vision ecosystem, Prophesee’s Metavision Intelligence Suite covers the whole development process from discovery to prototyping and end-application. The software suite provides 95 AI algorithms, 67 code samples and 11 ready-to-use applications. The open-source architecture gives the flexibility to “unlocking full interoperability between software and hardware devices.”
The partnership between BrainChip and Prophesee will give the market more commercially available neuromorphic vision systems for potential applications in autonomous vehicular systems, industrial automation, IoT, security, surveillance, retail automation, and AR/VR.
“By combining Prophesee’s Metavision solution with Akida-based IP, we are better able to deliver a complete high-performance and low-power solution to OEMs looking to leverage edge-based visual technologies as part of their product offerings,” said Luca Verre, CEO and co-founder of Prophesee.”
BrainChip recently announced a collaboration with Edge Impulse to address the growing demands for training AI workloads and inference deployments for large-scale edge AI applications. BrainChip also partnered with RISC-V founding member SiFive to work on deploying edge AI chips for optimized AI/ML compute at the edge.
BrainChip, Prophesee to deliver “neuromorphic” event-based vision systems for OEMs | Edge Industry Review
The collaboration will enable enterprise customers to explore edge artificial intelligence use cases with neuromorphic vision systems.
Dang Son
Regular
That's right FF, it was beautifully transcribed by me
Prophesee was so ahead of the game in tech that current (pre-BrainChip) tech was limiting their abilities to really shine & then all of a sudden a young sexy BrainChip walked through the door, Prophesee's eyes lit up & it was a match made in technology Heaven.
To me after listening to Luca, Prophesee will naturally choose BrainChip every single time it creates anything new, as why would they go forward & sell a half product to a customer when it can add BrainChip & sell a full better product to a customer, it's the "natural choice".
Buy Products | PROPHESEE
Experience Prophesee Metavision, with a range of Event-Based Vision products: event cameras, Evaluation Kits, Metavision sensors and Metavision software.
MDhere
Regular
Before 1000 is 500 n'est pas?
DingoBorat
Slim
Wouldn't it be easier, to just not reply to a random poster, who was posting a random comment, that wasn't even posed as a question?
Seems odd and Mercedes, haven't been shy about us recently..
Definitely curious..
H.E. Pennypacker
Regular
Moderate me for what exactly? It’s this mentality that has stopped great posters like Uiux posting here
Fact Finder
Top 20
Yes and yet it does not dominate the conversation here???
Why is this so???
My opinion only DYOR
FF
AKIDA BALLISTA
DingoBorat
Slim
Yes, if something better came along, they would.
There is no such thing as loyalty, when it comes to technology.
If BrainChip IP is already being incorporated though, it wouldn't be a sudden change..
(If this is even direct competition)
Last edited:
If you read his posts (not sure the platform) the guy (Francois) is looking at something in the context of some up-coming award where your secretary can nominate you. ie he is not looking at it on behalf of MB. He is not looking at a patent.
Quiltman
Regular
Thanks for posting Jesse,
Holy Shit Balls that was a fantabolus podcast
Now bear with me this is all from my dodgy memory.
"we are very excited about collaboration with BrainChip, we are natural partners, before Brainchip they were facing integration problems, which was impacting sensor performance, so now combining Prophesee & Brainchip we are finishing the half story we were missing from the beginning, it is now complete, so now we can tell a full story to our customers.....WOW"
Three examples of use cases that Prophesee are currently working on & some I think he said they have been working on for the last 3 years are;
1. Industrial application - High speed fast accurate barcode detection on fast moving boxes
2. Automotive application - Event based camera state of the art object detection for sensors in cars to detect pedestrians or other objects in poor lighting & then for example applying the brakes
3. Mobile Application - Computational imaging for smart phone, our event based sensor will combine with regular frame based sensor to take best images, we capture moving object & we can help correct blurry images that would be taken with just a regular frame based sensor
This is what Prophesee thinks of Akida
And this is what BrainChip thinks about Prophesee
And this is what I think of our Partnership
We have all seen the Prophesee partners page ....
We are integral to their solution moving forward ... hence, we will be integrated with their partners in delivering commercial solutions.
These guys & MegaChips ... why is the SP still under $1.00 .... won't be for long !
HopalongPetrovski
I'm Spartacus!
Uiux is free to post here, as are you.
As this is Zeeb0t's creation, He is the only one with the power to moderate anyone.
He has however asked us all to help him by pointing out possible infringements of his rules, which some do more zealously than other's,
as is they're bent.
Some individuals occasionally get over excited and begin to act as if they may dictate what other's post, or what is suitable, or what is politically correct according to some personal version of truth or morality held.
We are stronger as 1000 eye's when disparate and wide ranging views and opinions are able to be displayed as this can lead to interesting cross pollination and a strengthened overall viewpoint of our company from a multidisciplinary technical/corporate/ethical/financial/governance/research viewpoint. Just another anonymous opinion.
AKIDA BALLISTA
AKIDA'S EVERYWHERE
GLTAH
TheFunkMachine
seeds have the potential to become trees.
I read someone else alluding this to potentially be Synsense and not Akida. Have we explored that further? Does the synsense tech boast 100x power efficiency over GPUs ?
If this is Not Akida, then it is cause for concern, especially as we know Mercedes has boasted 5-10x power savings on their “hey Mercedes” applications.
In my opinion this has to be Akida as I have t heard of anyone else boasting these kind of results, but I don’t want to ignore potential competitors if there is any.
Fact Finder
Top 20
Hi @DingoBorat
There is a statement by Peter van der Made that AKIDA is 1,000 times more efficient than GPUs. Not sure where it is now but its out there somewhere to be found.
Prophesee has been looking for the event based processor to match the performance of their event based sensor and have now stated via this podcast and their CEO that AKIDA has provided the missing piece of their puzzle. Clearly not SynSense who runs around claiming all sorts of things about itself uninhibited by the ASX or SEC rules.
This fellow who not one of us ever mentioned before yesterday posts one random claim about an unidentified IP as being 100 more time efficient than a GPU and when asked if it is AKIDA says not that one.
Well the first thing to say is according to Peter van der Made AKIDA is 1,000 times more efficient so 10 times better than what is being described.
Second thing is that someone else I think @Cardpro posted other posts of this chap where he is saying Moores Law is not dead and conventional technology has a long way to go before it is dead.
Then @Bravo found and posted about a new clock technology that improves the performance of a GPU 100 times and references RISC-V technology as being made more efficient.
Having reflected on @Bravo 's posted information I am of the mind that this is what this poster was referencing however as SiFive adds AKIDA to its RISC-V all this new clock technology does is make more efficient the whole system which includes AKIDA it does not replace AKIDA.
So whether it is @Bravo 's discovery or whether it is AKIDA2.0 it in no way changes the importance of the Prophesee statements concerning why they are going forward with AKIDA in Mobile Phone vision systems, Industrial vision systems and Automotive vision systems.
Indeed all of the concerns that some have raised about AKIDA being dropped by Mercedes Benz for better technology are real except they are real for SynSense over at BMW where Prophesee has its foot in the door and on todays presentation the only solution they would be moving forward with is one where they are utilising AKIDA in vision systems for automotive.
If anything the Prophesee podcast should have everyone asking will this increase the use of AKIDA in Mercedes Benz as they will no doubt be introducing Mercedes Benz to what the combined AKIDA Prophesee vision sensor is capable of achieving for them.
Perhaps Brainchip is also over at Valeo introducing the Prophesee AKIDA Vision System for Valeo to consider as yet another automotive sensor technology to combine with its present offerings.
I have an enormous sense of frustration with the continuing discussion of one random engineer who makes claims about testing he has not even completed. For all we know this other technology if it is not AKIDA could be like Elon Musks Chip and needs 500 watts of power to achieve this 100 times improved performance.
My opinion only DYOR
FF
AKIDA BALLISTA
alwaysgreen
Top 20
In other news, how good is the share price action today!
ndefries
Regular
Almost getting upto where it was before 10M shorts taken out - that have not as yet been bought backIn other news, how good is the share price action today!
MDhere
Regular
"Hey fellow brners"
Let me make this clear - Hey Mercedes - is us. IMO the below uses Hey Mercedes and i agree its a hot word
Working with California-based artificial intelligence experts BrainChip, Mercedes-Benz engineers developed systems based on BrainChip’s Akida hardware and software. The example in the VISION EQXX is the “Hey Mercedes” hot-word detection. Structured along neuromorphic principles, it is five to ten times more efficient than conventional voice control.
This has come including the bold words, directly from https://group-media.mercedes-benz.com/
of course IMO
Let me make this clear - Hey Mercedes - is us. IMO the below uses Hey Mercedes and i agree its a hot word
Neuromorphic computing – a car that thinks like you
Another key efficiency feature of the VISION EQXX that takes its cue from nature is the way it thinks. It uses an innovative form of information processing called neuromorphic computing. The hardware runs so-called spiking neural networks. Information is coded in discrete spikes and energy is only consumed when a spike occurs, which reduces energy consumption by orders of magnitude.Working with California-based artificial intelligence experts BrainChip, Mercedes-Benz engineers developed systems based on BrainChip’s Akida hardware and software. The example in the VISION EQXX is the “Hey Mercedes” hot-word detection. Structured along neuromorphic principles, it is five to ten times more efficient than conventional voice control.
This has come including the bold words, directly from https://group-media.mercedes-benz.com/
of course IMO
buena suerte :-)
BOB Bank of Brainchip
BrainChip founder and CTO Peter van der Made presented at Stocks Down Under’s Semiconductor Conference on 30 November 2021.
So if you’re looking at our products, the Akida 1000 is the major product, which is the chip. The neural multiprocessor mimics…and I’ll look it up in the dictionary, it mimics neurobiological architecture present in the neural nervous system. So it doesn’t work like a processor that is applied in your laptop, it works like a mini-brain. It is very good at recognizing things, recognizing smells, recognizing images, recognizing tastes. We have done all these things as examples and made them available to the market. We also have an artificial retina image to spike converter. What the eye is doing, it takes images, converts those images into spikes that then the brain is processing. We do something very similar with our artificial retina image to spike converter.
The chip is up to 10 times more energy-efficient than any other edge AI processor. Except if you’re looking at very tiny things that can’t be really used for anything. But anything that isn’t the same class as the BrainChip Akida processor is using at least 10 times more energy here. And it’s up to a thousand times more energy-efficient than GPUs.
Bravo
If ARM was an arm, BRN would be its biceps💪!
Let's say for arguments sake that Francoise was talking about the new Esperanto chip. Do you think they could be a competitor or is there a possibility that we could be complementary to each other? I say this because of Esperanto's links with SiFive.
In another article by Sally Ward-Foxton it stated:
“BrainChip can run [AI] algorithms on their own, but when they move into a larger system, they will need a host processor,” Chris Jones, vice president, product at SiFive, told EE Times. “You could pick a host processor that does nothing but scheduling, or you could pick a host processor that actually contributes to the AI processing, and that’s where the SiFive Intelligence product comes in.”
In an SoC design for edge AI, the AI workload would typically be split between host processor, vector processor, and AI accelerator — some parts of edge workloads are better suited to general purpose compute rather than a dedicated AI accelerator, Jones said.
This 1,000-core RISC-V processor is generating buzz in the AI space
By Anthony Spadafora
published April 26, 2022
New AI chip hold promise for machine learning recommendation
(Image credit: Esperanto Technologies)
A new 1,000-core RISC-V processor from Esperanto Technologies (opens in new tab) is currently being evaluated by Samsung SDS and other ‘lead customers”.
According to a press release (opens in new tab) from the computer software company, its new ET-SoC-1 AI Inference Accelerator is undergoing initial evaluations by a number of firms ahead of its release.
Esperanto Technologies itself was founded back in 2014 by semiconductor industry veteran Dave Ditzel who has previously worked at both Sun Microsystems and Intel. The company is now led by President and CEO Art Swift who in addition to being the former CEO of Wave Computing also spent some time working at the RISC-V Foundation.
As part of its evaluation program, Samsung SDS (opens in new tab) and other potential customers will get a chance to obtain performance data after running a variety of off-the-shelf AI (opens in new tab) models using the ET-SoC-1 AI Inference Accelerator and so far the results have been quite impressive.
ET-SoC-1 AI Inference Accelerator
Esperanto’s ET-SoC-1 features 1,088 energy-efficient, 64-bit bit processor cores that utilize the RISC-V (opens in new tab) instruction set architecture which is quickly becoming a viable alternative to those of both x86 and ARM. The company’s new chip also includes four high-performance RISC-V cores along with 160m bytes of on-chip SRAM as well as interfaces for flash memory and external DRAM.What sets the ET-SoC-1 apart from similar chips is its speed together with its low-power requirements. While the chip can run any type of machine learning (opens in new tab) workload, Esperanto says that it excels at machine learning recommendation which is used by Meta, Amazon and other hyperscalers.
VP of AI at Samsung SDS, Dr. Patrick Bangert provided further insight on the experience the company’s data science team had when evaluating the ET-SoC-1, saying:
“Our data science team was very impressed with the initial evaluation of Esperanto’s AI acceleration solution. It was fast, performant and overall easy to use. In addition, the SoC demonstrated near-linear performance scaling across different configurations of AI compute clusters. This is a capability that is quite unique, and one we have yet to see consistently delivered by established companies offering alternative solutions to Esperanto.”
While Esperanto has given Samsung SDS and other potential customers a chance to test out its new AI chip (opens in new tab), we’ll have to wait and see if the evaluation was impressive enough for orders to start coming in.
This 1,000-core RISC-V processor is generating buzz in the AI space
New AI chip hold promise for machine learning recommendation
Similar threads
