BRN Discussion Ongoing

[Diogenese]

This table is a summary of partners and their field of activity from Brainhip's Partners page:

Partners - BrainChip

20230902
TECHNOLOGY PARTNERS
ARM	Next gen AI solutions
IFS	NN processor design
Prophesee	Event-based systems, DVS
SiFive	Integrated edge AI compute
ENABLEMENT PARTNERS
Ai Labs	Industrial monitoring and productivity
Edge Impulse	Expedite time-to-market for ML
Emotion3D	In-cabin image analysis
NVISO	Robotics and mobility devices
GMAC	Facial, vehicle, voice recognition in fast food drive-through
INTEGRATION PARTHERS
MegaChips	SNN ASICs
Teksun	Predictive maintenance, healthcare, security, surveillance
Lorser	Software Defined Radio
Quantum Ventura	cybersecurity
Tata Elxsi	medical, industrial

There seem to be several omissions, notably Valeo, Renesas, Socionext, but otherwise it corresponds quite well with the Joint Development partner list I posted a couple of days ago. The bonus is that the web page does provide the relevant fields of interest of each partner.
This is strong confirmation from the company as to with whom we are working and on what.

Most of the companies, ARM, Intel, Megachips and Teksun excepted have been described in terms of joint developments, so no up-front licence fee or royalties, but probably profit share.

 

[Cartagena]

1. Rob Telson likes this
2. 
   Sam Heidari 3rd+
   CEO Lumotive
   1d
   Follow
   
   After 8 years of hard work in fundamental R&D, we are proud to announce that our Beam Steering Technology is now available for mass deployment, solving one of the remaining fundamental challenges in Optics. Lumotive Launches the World's First Commercially-Available Optical Beam Steering Semiconductor
   …more
   
   

   Lumotive Launches the World's First Commercially-Available Optical Beam Steering Semiconductor​

   prnewswire.com​

   
   14213 Comments
   Like
   CommentShare
3. Rob Telson likes this
   
   Farzad Zarrinfar 3rd+
   Vice President of Sales for Major Accounts at Alphawave
   1d
   Follow
   
   We were thrilled to be a gold sponsor of Hot Chips 2023, where we showcased #AlphawaveSemi advanced product portfolio. Many of the industry’s biggest chip design firms were at the show, talking about their latest SoCs. It was a pleasure to see our customers exciting SoCs which were enabled with Alphawave IPs. Our #WaveMakers discussed how chiplet-powered high-speed connectivity silicon, featuring advanced interfaces like UCIe, HBM, PCIe and CXL, is driving transformative technologies. Hot chip designers were excited to interact with #Alphawave Semi representatives regarding their exciting applications such as #datacenter , #AI, #ML, #5g , #ssd , #automotive, generative AI & #opticalnetworking. We demonstrated our breakthrough innovations to our customers and the world, with our solutions such as #asic offering, IPs for #ethernet (1-112Gbps), #pcie Gen 4/5/6 CXL 3/2, #HBM 3/2, & #chiplets. I would like to thank customers ,partners, and prospects that visited our Alphawave Semi booth at Hot Chips 2023. Together, we are accelerating the connected world and the innovations beyond boundaries. #AlphawaveSemi #HotChips #2023 #Stanford #hardware #AI #AcceleratingTheConnectedWorld #chiplets #UCIe#semiconductor #asic
   …more
   • 

Exploring edge AI: Insights from Brainchip’s 2023 edge AI technology report​

Aug 9, 2023 | Larisa Redins
CATEGORIES Edge Applications | Edge Computing News | Market Research

The recently published 2023 Edge AI Technology Report delves into the present landscape of edge AI, showcasing its diverse applications in both the industrial and consumer realms.
The report, sponsored by Brainchip, Arduino, Arm, Edge Impulse and Sparkfun, explores the advantages of this technology and also sheds light on the challenges it faces. According to experts, edge AI is transforming multiple industries, such as industrial manufacturing, healthcare, consumer products, transportation, smart cities and smart homes.

The edge AI report explores how platforms such as TensorFlow Lite, PyTorch Mobile, OpenVino, Nvidia Jetson and others support edge AI development. It highlights critical hardware and software selection considerations, including integration and security, to ensure a smooth and secure implementation of edge AI.
TinyML is also featured prominently in the report, exploring its advantages, development tools and potential challenges. It delves into the role of TinyML in the products of the future.
The report also examines various edge AI algorithms, including classification, detection, segmentation and tracking algorithms. It further explores the harmonizing of these algorithms with hardware.
Sensing modalities, including vision-based, audio-based and environmental sensing, are also discussed alongside data collection methods. The report showcases how companies like Sparkfun are simplifying data logging, for example.
In a series of case studies, the report provides glimpses into the real-world applications of edge AI. Companies like ST, Sensory Inc and Pachama demonstrate how they’re transforming industries with edge AI technologies.
The report also addresses the challenges of edge AI, such as data management, integration, security, latency, scalability, cost and power consumption. It also suggests potential solutions to these issues.
Looking to the future, the report explores the potential impact of the emergence and growth of 5G/6G networks on edge AI. It foresees a growing significance of neuromorphic computing and event-based processing. Additionally, the report emphasizes the importance of data-efficient AI and in-memory computing for edge AI.

Previous Article:
Amsterdam to host annual IoT Tech Expo Europe this fall
Next Article:
Webinar: How to Secure IOT Edge Environments in Oil and Gas

Article Topics​

AI/ML | ARM | Brainchip | chip | edge AI | Edge Impulse | PyTorch |

 

[Diogenese]

1. Rob Telson likes this
2. 
   Sam Heidari 3rd+
   CEO Lumotive
   1d
   Follow
   
   After 8 years of hard work in fundamental R&D, we are proud to announce that our Beam Steering Technology is now available for mass deployment, solving one of the remaining fundamental challenges in Optics. Lumotive Launches the World's First Commercially-Available Optical Beam Steering Semiconductor
   …more
   
   

   Lumotive Launches the World's First Commercially-Available Optical Beam Steering Semiconductor​

   prnewswire.com​

   
   14213 Comments
   Like
   CommentShare
3. Rob Telson likes this
   
   Farzad Zarrinfar 3rd+
   Vice President of Sales for Major Accounts at Alphawave
   1d
   Follow
   
   We were thrilled to be a gold sponsor of Hot Chips 2023, where we showcased #AlphawaveSemi advanced product portfolio. Many of the industry’s biggest chip design firms were at the show, talking about their latest SoCs. It was a pleasure to see our customers exciting SoCs which were enabled with Alphawave IPs. Our #WaveMakers discussed how chiplet-powered high-speed connectivity silicon, featuring advanced interfaces like UCIe, HBM, PCIe and CXL, is driving transformative technologies. Hot chip designers were excited to interact with #Alphawave Semi representatives regarding their exciting applications such as #datacenter , #AI, #ML, #5g , #ssd , #automotive, generative AI & #opticalnetworking. We demonstrated our breakthrough innovations to our customers and the world, with our solutions such as #asic offering, IPs for #ethernet (1-112Gbps), #pcie Gen 4/5/6 CXL 3/2, #HBM 3/2, & #chiplets. I would like to thank customers ,partners, and prospects that visited our Alphawave Semi booth at Hot Chips 2023. Together, we are accelerating the connected world and the innovations beyond boundaries. #AlphawaveSemi #HotChips #2023 #Stanford #hardware #AI #AcceleratingTheConnectedWorld #chiplets #UCIe#semiconductor #asic
   …more
   • 

Lidar transmitter?

 

[Cartagena]

Lidar transmitter?

Could it involve Gen 2? Noticed RT liked the post. There must be a reason.

 

[SharesForBrekky]

Something to keep a look out for:

https://www.gizmochina.com/2023/08/30/nintendo-switch-2-gamescom/

"Moreover, according to the latest information, the Nintendo Switch 2 is expected to be revealed in 2024 and was secretly showcased at the Gamescom 2023."

"Now, it turns out that Nintendo secretly showcased the next-gen Switch hardware to select media and developers during Gamescom 2023.

If the rumors turn out to be true, we could soon hear an official announcement about new Nintendo Switch 2. This fits with previous leaks suggesting that Nintendo’s main partners have already received developer kits and plan to release games in the latter half of 2024."

 

[Rise from the ashes]

Evening Rise from the ashes,

Wow.... Well found.

I noticed this is a relatively old US government document... No doubt due to the sensitive nature..hence delayed for general / Civilian viewing.

I could be wrong, has happened, but I belive a past poster... Uiux.. found a fair bit of info down this ally.

One would think when ...if not already, AKIDA would splice extremely well into multiple levels of such hardware / software.

AKUDA BALLISTA.

Regards,
Esq.

Yes mate a bit old but I do have some recent documents but you'll have to take a long walk to the back of the farmhouse after reading jk
I'll have a rummage through his belongings he left behind and see if anything juicy is there and he does like to juice. I miss that guy's contributions.
Thanks to some of the narcissistic gaslighting posters he no longer posts here. But hey at least we still get to see burning bins and condescending posts instead of high valued posts.

 

[cosors]

View attachment 43629

Pioneering 5G OpenRAN Advancements with Accelerated Computing and NVIDIA Aerial – NVIDIA Technical Blog

developer.nvidia.com

View attachment 43630

Cortical Columns are

AKD-CC
or better
AK CC

 

[Rise from the ashes]

We need Brn to contact these people

The footage is not on the news program depicted here but it's a guy who follows these things around and definitely not smart at all as the guy on news interview states.
Runs with LLM DNN

Hilarious robot cases his house out.

 

[TheFunkMachine]

View attachment 43631

Published 6 hours ago

The Mercedes-Benz Concept CLA Class will make its debut at the event to give us an early look at a new family of models.

We'll need to wait until the show opens its doors to the press on Monday (Sept. 4), to see the Concept CLA Class from every angle, but a dark preview image released by the brand confirms the model looks nothing like the CLA that's currently in showrooms. It wears a futuristic-looking front end characterized by an oval grille, a light bar, and semi-circle-shaped LED accents with Mercedes-Benz star-like inserts.

Mercedes-Benz boss Ola Källenius confirmed the Concept CLA Class rides on a new architecture called MMA; the production-bound cars inspired by the design study will use this platform as well. Powertrain specifications haven't been released, but the company notes power comes from an "ultra-efficient" electric powertrain related to the system that powers the Vision EQXX concept unveiled in January 2022.

That's significant, because the Vision EQXX covered the 747 miles separating Stuttgart, Germany, and Silverstone, England, on one charge. It's a concept, bringing it to production as-is isn't feasible, but the lessons learned during the project will permeate MMA-based cars. "You need to improve every single area. Everything that has a weight needs to become lighter, everything that transfers energy needs to become more efficient, and everything that’s on the outside needs to be as aerodynamic as possible," Mercedes-Benz told me after I drove the car.

Interior photos haven't been released, but the Concept CLA Class will inaugurate a new operating system called MB.OS. We're curious to find out if the Vision EQXX, which featured a dashboard-wide screen and an elegantly minimalist interior, will also influence the cabin layout.

Stay tuned: More details about the Mercedes-Benz Concept CLA Class will emerge in the coming days. As for what's next, an unverified report from October 2022 claims the first EQXX-inspired, MMA-based car will land in showrooms in 2024 as a CLA-sized electric model.


.....

View attachment 43632

...
So

1. Akida technology is included in the EQXX concept car.
2. The Concept CLA class being unveiled next week is the first car to be launched using EQXX technology, including new operating system MB.OS
3. One can conclude that Akida technology will be in the concept CLA class.
4. First sales in 2024.

Well, next week could be very interesting indeed.
Out of the ASX200, but confirmed in the CLA class being launched in 2024

What, on earth, will the shorters do !!

i do really hope so! However, there is nothing in the article to conclude this to be the case other than they will use technology used in EQXX.

Crossing my fingers, toes and balls for some really good news next week, but according to the article I won’t be surprised that we are not included either.

 

[Nobody]

This table is a summary of partners and their field of activity from Brainhip's Partners page:

Partners - BrainChip

20230902
TECHNOLOGY PARTNERS
ARM	Next gen AI solutions
IFS	NN processor design
Prophesee	Event-based systems, DVS
SiFive	Integrated edge AI compute
ENABLEMENT PARTNERS
Ai Labs	Industrial monitoring and productivity
Edge Impulse	Expedite time-to-market for ML
Emotion3D	In-cabin image analysis
NVISO	Robotics and mobility devices
GMAC	Facial, vehicle, voice recognition in fast food drive-through
INTEGRATION PARTHERS
MegaChips	SNN ASICs
Teksun	Predictive maintenance, healthcare, security, surveillance
Lorser	Software Defined Radio
Quantum Ventura	cybersecurity
Tata Elxsi	medical, industrial

There seem to be several omissions, notably Valeo, Renesas, Socionext, but otherwise it corresponds quite well with the Joint Development partner list I posted a couple of days ago. The bonus is that the web page does provide the relevant fields of interest of each partner.
This is strong confirmation from the company as to with whom we are working and on what.

Most of the companies, ARM, Intel, Megachips and Teksun excepted have been described in terms of joint developments, so no up-front licence fee or royalties, but probably profit share.

*PARTHERS..

 

[Rise from the ashes]

i do really hope so! However, there is nothing in the article to conclude this to be the case other than they will use technology used in EQXX.

Crossing my fingers, toes and balls for some really good news next week, but according to the article I won’t be surprised that we are not included either.

According to the article I'd say we got a good chance of being mentioned imo.
Also anyone who contacts company regularly could you throw this question towards them.
Is Akida able to detect images that have been generated-photoshoped by Ai?

 

[IloveLamp]

News

www.intel.com

 

[IloveLamp]

Samsung announces a new oven that creates a timelapse video of your cooking

www.9news.com.au

 

[IloveLamp]

US military plans to thwart China with 1,000s of autonomous war drones

The US Deputy Secretary of Defense has officially kicked off the AI drone wars, announcing a radical "Replicator" plan to put many thousands of intelligent autonomous war drones into service within 18-24 months, to deter a Chinese invasion of Taiwan.

newatlas.com

 

[Quiltman]

i do really hope so! However, there is nothing in the article to conclude this to be the case other than they will use technology used in EQXX.

Crossing my fingers, toes and balls for some really good news next week, but according to the article I won’t be surprised that we are not included either.

Nothing is guaranteed.

Much like Tata Consultancy Services, Mercedes has been working on neuromorphic compute for over 5 years. BrainChip was invited to help implement the advantages of neuromorphic compute in their vehicles, not to understand it. Mercedes Benz would have been through an internal assessment process, and moved towards SNN architecture , then evaluated options on how to implement ( internal development, available commercial partners). My point being that they have been at it for a while.

I then reflect on this article from 6th Jan, 2022 .

Software-defined vehicles, software-based simulation and neural processors in EVs and connected cars, with a look at developments from General Motors, Mercedes-Benz and Blackberry.


The gist of the article is around how development times have improved enormously by using software simulation rather than building physical models. The VISION EQXX went from a white paper to a completed vehicle in only 18 months.

This means new, innovative concepts ( like neuromorphic compute ) that may have taken 5+ years to end up on the market in a vehicle should now only take 2 to 3 years.

This article, as we all know, went on to talk about Akida technology in the EQXX

.....

Neuromorphic computing for infotainment

This efficiency is not just being applied to enhancing range though. Mercedes-Benz also points out that its infotainment system uses neuromorphic computing to enable the car to take to “take its cue from the way nature thinks”.

Neuromorphic computing systems have the potential to radically reduce the energy needed to run the latest AI technologies in vehicles. (Image: Mercedes-Benz)

The hardware runs spiking neural networks, in which data is coded in discrete spikes and energy only consumed when a spike occurs, reducing energy consumption by orders of magnitude. In order to deliver this, the carmaker worked with BrainChip, developing the systems based on its Akida processor. In the VISION EQXX, this technology enables the “Hey Mercedes” hot-word detection five to ten times more efficiently than conventional voice control. Mercedes-Benz said although neuromorphic computing is still in its infancy, systems like these will be available on the market in just a few years. When applied on scale throughout a vehicle, they have the potential to radically reduce the energy needed to run the latest AI technologies.

......

So, in Jan 2022 Mercedes was stating " just a few years ".
Does market release of the new Concept CLS class in say, June 2024 ( don't know release dates ), 2.5 years from this statement, fit with all of the evidence above and constitute " a few years ". I'm guessing it does.
Still no guarantees of course, but the timelines seem to fit.

I also like the fact that Merc continue to add to it's Team AI Research group.
With a focus on, you guessed it, spiking neural networks.
So I hope, and expect, that the footprint of Akida within MB vehicles will continue to evolve and grow over later releases.

This job was advertised on 7th August.

As an employee of the Team AI Research , you are researching current trends in artificial intelligence such as GenAI, quantum AI or neuromorphic computing. We are intensively examining new artificial intelligence methods and working on them further in order to make them usable for our company together with our colleagues from the specialist departments. We strive to expand the limits of artificial intelligence and create customized innovative solutions for our customers. In our team, you can actively shape the future of technology.


These challenges await you:

• Applied research in the field of neuromorphic computing and spiking neural networks
• Development of innovative algorithms for automotive applications
• Implementation of neuromorphic algorithms for automotive applications
• Researching and transferring current neuromorphic computing trends for automotive applications with a special focus on ADAS

 

[Foxdog]

US military plans to thwart China with 1,000s of autonomous war drones

The US Deputy Secretary of Defense has officially kicked off the AI drone wars, announcing a radical "Replicator" plan to put many thousands of intelligent autonomous war drones into service within 18-24 months, to deter a Chinese invasion of Taiwan.

newatlas.com

'They'll be capable of swarming, or of operating completely solo where communications are difficult or impossible.'

So we've got connections with US DoD, we're the only commercial chip that can operate independent of the cloud. We're rad hardened for future space applications. If we're not involved in this initiative, who the hell is? Our management definitely can't disclose involvement here but watch the financials, this could be a company making contract.....if we're involved. This is happening quickly so some revenue should start to show soon. The next 4C is looking more and more interesting, imo.

 

[Rise from the ashes]

'They'll be capable of swarming, or of operating completely solo where communications are difficult or impossible.'

So we've got connections with US DoD, we're the only commercial chip that can operate independent of the cloud. We're rad hardened for future space applications. If we're not involved in this initiative, who the hell is? Our management definitely can't disclose involvement here but watch the financials, this could be a company making contract.....if we're involved. This is happening quickly so some revenue should start to show soon. The next 4C is looking more and more interesting, imo.

I wonder how they'll combat jamming from sdr''s
Also Ike I've mentioned before truly excited and concerned also about future sdr''s with Akida inside.

Dronesense: A LimeSDR Based Drone Detector and Jammer

Over on the LimeSDR CrowdSupply blog, Ogün Levent has submitted a short article about his 'Dronesense' project. Dronsense is a spectrum-scanning and jamming system based on the LimeSDR. The LimeSDR is a US$299 12-bit TX/RX capable SDR that can tune between 100 kHz – 3.8 GHz, with a maximum...

www.rtl-sdr.com

Also the military version contains software defined radio

DRONEKILLER®

disable drones operating on 7 frequency bands dronekiller is lethal up TO 1000 meters perfect gap filler in multiple links of the kill chain

www.ixiew.com

Anyone who can read English will be capable of doing very nefarious things with sdr''s
I just bought one for a nephew so he can learn a few things this one only has rx no tx so he can't transmit.

Anyone who relies on smart alarms, locks or whatever your much more secure with a rusty lock.

 

[jtardif999]

This table is a summary of partners and their field of activity from Brainhip's Partners page:

Partners - BrainChip

20230902
TECHNOLOGY PARTNERS
ARM	Next gen AI solutions
IFS	NN processor design
Prophesee	Event-based systems, DVS
SiFive	Integrated edge AI compute
ENABLEMENT PARTNERS
Ai Labs	Industrial monitoring and productivity
Edge Impulse	Expedite time-to-market for ML
Emotion3D	In-cabin image analysis
NVISO	Robotics and mobility devices
GMAC	Facial, vehicle, voice recognition in fast food drive-through
INTEGRATION PARTHERS
MegaChips	SNN ASICs
Teksun	Predictive maintenance, healthcare, security, surveillance
Lorser	Software Defined Radio
Quantum Ventura	cybersecurity
Tata Elxsi	medical, industrial

There seem to be several omissions, notably Valeo, Renesas, Socionext, but otherwise it corresponds quite well with the Joint Development partner list I posted a couple of days ago. The bonus is that the web page does provide the relevant fields of interest of each partner.
This is strong confirmation from the company as to with whom we are working and on what.

Most of the companies, ARM, Intel, Megachips and Teksun excepted have been described in terms of joint developments, so no up-front licence fee or royalties, but probably profit share.

Megachips paid an upfront licence fee though.

 

[Diogenese]

Could it involve Gen 2? Noticed RT liked the post. There must be a reason.

Hi Cartagena,

Short answer is "no'.

It's too early for Gen 2.

Also Akida would be used with a lidar receiver to examine the reflected light .

The Lumotive product is for the laser transmitter of the lidar system.

CORRECTION: Lumotive do use their beam steering in the receiver as well as the transmitter (#### see US2020371210A1 WAVEGUIDE-INTEGRATED TUNABLE LIQUID CRYSTAL METASURFACE DEVICE below ####), so theoretically Akida could be used in conjunction with Lumotivr's rceiver.


Here's a sampling of their 9 patents:

WO2021167657A2 LIDAR SYSTEMS BASED ON TUNABLE OPTICAL METASURFACES

An example optical transceiver system, such as a solid-state light detection and ranging (lidar) system, includes a tunable, optically reflective metasurface to selectively reflect incident optical radiation as transmit scan lines at transmit steering angles between a first steering angle and a second steering angle. In some embodiments, a feedback element, such as a volume Bragg grating element, may lock a laser to narrow the band of optical radiation. A receiver may include a tunable, optically reflective metasurface for receiver line-scanning or a two-dimensional array of detector elements forming a set of discrete receive scan lines. In embodiments incorporating a two-dimensional array of detector elements, receiver optics may direct optical radiation incident at each of a plurality of discrete receive steering angles to a unique subset of the discrete receive scan lines of detector elements.


US11567390B1 Coupling prisms for tunable optical metasurfaces

According to various embodiments, a solid-state light detection and ranging (LiDAR) transmitter includes a tunable optical metasurface to selectively steer incident optical radiation long an azimuth axis. In some embodiments, different subsets of lasers in an array of lasers are activated to generate optical radiation for incidence on the metasurface at different angles of incidence on an elevation axis for unsteered deflection by the metasurface at corresponding angles of elevation. In some embodiments, a prism is positioned relative to the tunable optical metasurface to deflect the optical radiation from the optical assembly by the optical radiation source for incidence on the metasurface at an angle of incidence that is between the first steering angle and the second steering angle, such that the optical radiation incident on the metasurface and the steered output optical radiation from the metasurface spatially overlap within the prism.

US10665953B1
Tunable liquid crystal metasurfaces

A tunable, optical metasurface can include an optically reflective surface to reflect optical radiation, such as infrared laser light. An array of optical resonant antennas may, for example, extend from or otherwise be positioned on the reflective surface with sub-wavelength spacings of, for example, less than one-half of a wavelength. Voltage-controlled liquid crystal may be positioned in the optical field region of each of the optical resonant antennas. A controller may apply a voltage differential bias pattern to the liquid crystal of optical resonant antennas, that may be arranged in tiled, interleaved, or randomly arranged subsets of optical resonant antennas to attain one-dimensional beam steering, two-dimensional beam steering, and/or spatial beam shaping.



US2020371210A1 WAVEGUIDE-INTEGRATED TUNABLE LIQUID CRYSTAL METASURFACE DEVICES


Optical receivers and transmitters can be used as stand-alone systems or combined together as a transceiver. Each of the receiver and transmitter may include an optically reflective steerable device, such as an optically reflective liquid crystal metasurface (LCM), to steer optical radiation to a target location. A transmit waveguide conveys optical radiation from a light source to the transmitter steerable device. A receive waveguide conveys received optical radiation reflected by the receiver optically steerable device to a sensor. In some embodiments, the transmit waveguide and the receive waveguide may be portions of the same planar waveguide. The receiver includes a holographic lens between the receiver LCM and the receive waveguide to pass through optical radiation received at a first range of incident angles and modify (e.g., collimate and/or spectrally filter) optical radiation reflected by the receiver LCM for conveyance by the receive waveguide to the sensor.

 

[Bravo]

ARTICLE 1 - Extract only - Date published 1 Sept 2023

ARTICLE 2 - Extract only - Date published 1 Sept 2023

ARTICLE 3 - Extract only - Date published 18 Jan 2022


Touting Vision EQXX as “a car that thinks like you,” Mercedes promises range of more than 1,000 km (about 620 miles) on a single charge.

“Working with California-based artificial intelligence experts BrainChip, Mercedes-Benz engineers developed systems based on BrainChip’s Akida hardware and software,” Mercedes noted in a statement describing the Vision EQXX. “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,” the carmaker claimed.



The Mercedes Vision EQXX uses neuromorphic computing to save power. (Source: Mercedes)

That represents validation of BrainChip’s technology by one of its early-access customers. BrainChip’s Akida chip accelerates spiking neural networks (SNNs) and convolutional neural networks (via conversion to SNNs). It is not limited to a particular application, and also run person detection, voice or face recognition SNNs, for example, that Mercedes could also explore.

“Although neuromorphic computing is still in its infancy, systems like these will be available on the market in just a few years,” Mercedes said. “When applied at scale throughout a vehicle, they have the potential to radically reduce the energy needed to run the latest AI technologies.”



Article 1 -

Mercedes-Benz Concept CLA Class EV Teased Ahead Of September 3 Debut

At IAA Mobility in Munich, Mercedes-Benz will debut an electric concept for its CLA Class. Here's a preview of what to expect.

insideevs.com

Article 2 - https://www.energyportal.eu/news/me...-currency-in-the-ev-market-by-reuters/227273/
Article 3 - https://www.eetimes.com/mercedes-applies-neuromorphic-computing-in-ev-concept-car/#