Hmmm but Rob don’t like it 🫡
Hmmm but Rob don’t like it 🫡
Magnus Östberg on LinkedIn: #ai #neuromorphiccomputing #leadincarsoftware | 19 comments
I received many great questions from the community in response to my recent post on neuromorphic computing, so I’ll jump right in and answer a few. How does a… | 19 comments on LinkedInwww.linkedin.com
View attachment 58928
I received many great questions from the community in response to my recent post on neuromorphic computing, so I’ll jump right in and answer a few.
How does a more powerful processor increase energy efficiency?
#AI is already used in advanced driving assistance systems (ADAS) and infotainment, and the complex calculations are currently performed on traditional CPUs, GPUs and NPUs, which are not energy efficient. #Neuromorphiccomputing requires for the same tasks less energy. As the number of AI functions continue to increase, the increased computing efficiency of neuromorphic hardware will require less energy in comparison to legacy hardware. Reduced energy usage will also increase vehicle range and improve sustainability.
When can I experience neuromorphic computing?
Widespread use of neuromorphic computing will depend on many factors. The technology requires new programming and algorithms, so it will not immediately replace traditional processors. One key factor for us is that automotive-grade chips must meet extremely strict reliability requirements. However, we are already actively working to drive development and we are committed to being the first to use this technology in the automotive industry.
If you haven’t read the article yet, check it out here https://lnkd.in/epnUc5Sy. Be sure to ask more questions so we can keep the conversation going.
Neuromorphic computing? We’ve got that.
Because it’s still nascent technology, I am frequently asked to describe #neuromorphic computing. It is a paradigm shift for how we perform computations in machine learning (#ML) and artificial intelligence (AI), which process massive amounts of data requiring tons of fast memory.
Currently available processor architecture separates data calculations from system memory, which is inefficient. The biological inspiration for neural networks is the human brain, where computing and memory are combined, and data processing uses neurons to communicate through electrical signals and chemical processes known as neurotransmitters.
In neuromorphic computing, those human neurons and synapses are modelled in circuits and communication is event-driven, with information coded in spikes, mimicking the processing fundamentals of the brain. Those spikes propagate through a Spiking Neural Network of artificial neurons and synapses to predict results. Information processing is measured by spike rate or spike time instead of the number of calculations. Thus, neuromorphic chips are more energy efficient and have lower latency than conventional CPUs and GPUs. That means much faster computation using considerably less power.
However, this change in data processing also requires new software algorithms specifically designed to work with neuromorphic hardware. Existing algorithms can only partially leverage the many benefits of neural technology. Thanks to Valerij, Alexander, Christina in the Innovations & Future Technology area and the rest of our team for tackling this huge project!
𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀
Neuromorphic computing reduces the power required for advanced AI computation, which is useful in applications where energy is limited, like electric vehicles. However, we still need automotive-grade chips with neuromorphic technology before this technology becomes common in cars.
We at Mercedes-Benz AG are currently working on novel algorithms that take advantage of neuromorphic computing to improve the energy efficiency and performance of our cars. Our primary goals are to extend vehicle range, make safety systems react faster, and increase the number of #AI functions possible. In 2020, we already joined the #Intel Neuromorphic Research Community and since then we are continuously expanding our collaborations with other research partners and universities to ensure our software and hardware solutions continue to lead the industry.
It's an exciting time to be in the world of automotive technology. Please share any questions and comments below.
No comment to a number of posters...they weren't my words, the dark web conjures up all sorts of information, unless Brainchip and SiFive
make a joint statement it's purely speculation, do you believe everything you read over the internet, I honestly can't say it's fact or not.
Only thing I can say with any certainty is that our 1st quarter finishes in 13 business days, then we wait to see how the company has been performing when the 4C is released in late April 2024.
Have a good day...Tech.
hey - not sure why you are not letting this go. SiFive are a partner and they offer Akida in their chips as an option. They clearly recommend it but it may not be desirable in all sales. Ultimately it is the customer that decides this no Sifive. We have been successfully incorporated into their chip design and hopefully their work with NASA includes us given they have been testing Akida for many years now.I originally asked for a link???
If they aren’t your words, then provide the link.
I wish.. but he also saysHi @Stable Genius,
It's funny when you think that NVIDIA and Mercedes only just announced in January this year their partnership in building the world's most advanced software defined vehicles.
Now we have Magnus Ostberg (Cheif Software Officer Mercedes) confirming that "traditional CPUs, GPUs and NPUs, which are not energy efficient". Additionally he states "We are already actively working to drive development and we are committed to being the first to use this technology in the automotive industry."
And in this Reuters article(link below) in Septmeber 2023 Ola Kaellenius (CEO Mercedes) had this to say.
View attachment 58959
These statements confirm in my mind that we will be incorporated into NVIDIA's Drive Thor which is going to be launched towards the end of this year.
I wonder if we'll get any further reveals at NVIDIA's 2024 GTC Conference on 18 March?
https://www.reuters.com/business/au...iciency-is-new-currency-ev-market-2023-09-01/
Magnus Östberg on LinkedIn: #ai #neuromorphiccomputing #leadincarsoftware | 19 comments
I received many great questions from the community in response to my recent post on neuromorphic computing, so I’ll jump right in and answer a few. How does a… | 19 comments on LinkedInwww.linkedin.com
View attachment 58928
I received many great questions from the community in response to my recent post on neuromorphic computing, so I’ll jump right in and answer a few.
How does a more powerful processor increase energy efficiency?
#AI is already used in advanced driving assistance systems (ADAS) and infotainment, and the complex calculations are currently performed on traditional CPUs, GPUs and NPUs, which are not energy efficient. #Neuromorphiccomputing requires for the same tasks less energy. As the number of AI functions continue to increase, the increased computing efficiency of neuromorphic hardware will require less energy in comparison to legacy hardware. Reduced energy usage will also increase vehicle range and improve sustainability.
When can I experience neuromorphic computing?
Widespread use of neuromorphic computing will depend on many factors. The technology requires new programming and algorithms, so it will not immediately replace traditional processors. One key factor for us is that automotive-grade chips must meet extremely strict reliability requirements. However, we are already actively working to drive development and we are committed to being the first to use this technology in the automotive industry.
If you haven’t read the article yet, check it out here https://lnkd.in/epnUc5Sy. Be sure to ask more questions so we can keep the conversation going.
Neuromorphic computing? We’ve got that.
Because it’s still nascent technology, I am frequently asked to describe #neuromorphic computing. It is a paradigm shift for how we perform computations in machine learning (#ML) and artificial intelligence (AI), which process massive amounts of data requiring tons of fast memory.
Currently available processor architecture separates data calculations from system memory, which is inefficient. The biological inspiration for neural networks is the human brain, where computing and memory are combined, and data processing uses neurons to communicate through electrical signals and chemical processes known as neurotransmitters.
In neuromorphic computing, those human neurons and synapses are modelled in circuits and communication is event-driven, with information coded in spikes, mimicking the processing fundamentals of the brain. Those spikes propagate through a Spiking Neural Network of artificial neurons and synapses to predict results. Information processing is measured by spike rate or spike time instead of the number of calculations. Thus, neuromorphic chips are more energy efficient and have lower latency than conventional CPUs and GPUs. That means much faster computation using considerably less power.
However, this change in data processing also requires new software algorithms specifically designed to work with neuromorphic hardware. Existing algorithms can only partially leverage the many benefits of neural technology. Thanks to Valerij, Alexander, Christina in the Innovations & Future Technology area and the rest of our team for tackling this huge project!
𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀
Neuromorphic computing reduces the power required for advanced AI computation, which is useful in applications where energy is limited, like electric vehicles. However, we still need automotive-grade chips with neuromorphic technology before this technology becomes common in cars.
We at Mercedes-Benz AG are currently working on novel algorithms that take advantage of neuromorphic computing to improve the energy efficiency and performance of our cars. Our primary goals are to extend vehicle range, make safety systems react faster, and increase the number of #AI functions possible. In 2020, we already joined the #Intel Neuromorphic Research Community and since then we are continuously expanding our collaborations with other research partners and universities to ensure our software and hardware solutions continue to lead the industry.
It's an exciting time to be in the world of automotive technology. Please share any questions and comments below.
Here it is!I originally asked for a link???
If they aren’t your words, then provide the link.
Hi 7fur7,I wish.. but he also says
“Widespread use of neuromorphic computing will depend on many factors. The technology requires new programming and algorithms, so it will not immediately replace traditional processors”
I think for the long term holders of us, this will be interesting. But I don’t expect end of the year. The technology behind this is too complicated. And we need urgent a certification for using such a sensitive area like car security etc ! Let’s say 2025/2026
Hi 7fur7,
I think it is clear that Mercedes cannot use Nvidia on its own in an EV (ICE is another matter). The alternative is to use Akida as a neuromorphic accelerator to do the heavy lifting in processing the sensor signals, and run with the Nvidia control software responding to Akida outputs. Akida IP could be included with the Nvidia processor in a single SoC (unlikely as we have not heard about the licence) or they could be separate chips.
Then again, Mercedes would want Akida 2, and this could add to the delay ...
PS: I'm just trying to think of ways they can do it now!
Yes sure. That's not what I'm doubting! I'm just talking about the timeframe! One tends to forget the necessary certifications required for such sensitive applications that are safety-critical. As long as they don't have such certificates... or whoever registers them. You can't integrate them into production-ready products. One thing is to research and try out what is possible. And the other is to have a finished product.Hi 7fur7,
I think it is clear that Mercedes cannot use Nvidia on its own in an EV (ICE is another matter). The alternative is to use Akida as a neuromorphic accelerator to do the heavy lifting in processing the sensor signals, and run with the Nvidia control software responding to Akida outputs. Akida IP could be included with the Nvidia processor in a single SoC (unlikely as we have not heard about the licence) or they could be separate chips.
Then again, Mercedes would want Akida 2, and this could add to the delay ...
PS: I'm just trying to think of ways they can do it now!
‘Widespread use’ can mean general adoption. Merc are an early adopter as BRN have always stated. Early adopters like Valeo and Mercedes Benz get the jump on the market. They would have a target date in mind for releasing the integrated Akida IP. Personally I think @Bravo could be close to the money regarding the potential for Akida’s integration into Thaw but that would depend on getting the right certification done and who knows how long that could take?I wish.. but he also says
“Widespread use of neuromorphic computing will depend on many factors. The technology requires new programming and algorithms, so it will not immediately replace traditional processors”
I think for the long term holders of us, this will be interesting. But I don’t expect end of the year. The technology behind this is too complicated. And we need urgent a certification for using such a sensitive area like car security etc ! Let’s say 2025/2026
Interestingly, poseidon and akida are both greek words..........NVIDIA Drive Thor uses updated ARM Poseidon AE cores and AKIDA is compatible with Arm's product families. Just a thought bubble.
View attachment 58985
This part of an article dated September 2022 caught my eye.
View attachment 58986
My feeling is that a company that goes to all the trouble to create their own OS will want to own their own chip. ie We should expect M-B to announce the license deal with us at the time they announce that we are the third chip partner.Hi 7fur7,
I think it is clear that Mercedes cannot use Nvidia on its own in an EV (ICE is another matter). The alternative is to use Akida as a neuromorphic accelerator to do the heavy lifting in processing the sensor signals, and run with the Nvidia control software responding to Akida outputs. Akida IP could be included with the Nvidia processor in a single SoC (unlikely as we have not heard about the licence) or they could be separate chips.
Then again, Mercedes would want Akida 2, and this could add to the delay ...
PS: I'm just trying to think of ways they can do it now!
That would imply a trident - so who's gooseberry?Interestingly, poseidon and akida are both greek words..........
Are we about to see a godly tidal wave of spikes?
I'd like to think so
Thank me for that.
Reason.
I'm going with Fact Finder back to hot crapper.
And when I go, so do my posts. (all 250+ of them)
Yes. We've discussed certification in detail a long time ago.In the automotive sector, similar standards apply as in other safety-critical industries, but there are also specific requirements that must be considered. The most important certifications and standards include:
ISO 26262: This standard is specifically for the functional safety of electrical and electronic systems in road vehicles. ASIL Classification: According to ISO 26262, systems and components are classified according to their Automotive Safety Integrity Level (ASIL) to assess the risk of hazards and take appropriate risk reduction measures. IATF 16949: This standard defines requirements for a quality management system for the automotive industry and also considers aspects of product safety. ISO 9001: A quality management system that sets out general requirements for quality management practices and is relevant to the automotive industry. Cybersecurity: With the increasing connectivity of vehicles and the introduction of autonomous driving, cybersecurity in the automotive sector is also becoming increasingly important. Standards such as ISO/SAE 21434 and UN-R155 may be relevant here.
These certifications and standards are important to ensure that AI chips and systems in the automotive sector operate safely and reliably.
All I want to say is, there are more factors if you want to implement a new technology into a car etc. you need certifications