BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Tothemoon24
Top 20
Why is dough another word for money? Because everyone kneads it.
… so very true , & we are on the Crust of making a shit load
Stable Genius
Regular
I took the bait @Fact Finder:
Edge AI Innovator Femtosense Brings Affordable, Off-the-Shelf Hearing Aids, Other Wearables Closer to Reality with First Silicon
Edge AI innovator Femtosense today announced the arrival and successful testing of its first silicon, substantiating the start-up’s assertions that it
www.businesswire.com
They’re talking about using neuromorphic AI but no company mentioned so fingers crossed they’re using the first and best commercially available NN!
Unfortunately not - they are using these guysI took the bait @Fact Finder:
Edge AI Innovator Femtosense Brings Affordable, Off-the-Shelf Hearing Aids, Other Wearables Closer to Reality with First Silicon
Edge AI innovator Femtosense today announced the arrival and successful testing of its first silicon, substantiating the start-up’s assertions that itwww.businesswire.com
They’re talking about using neuromorphic AI but no company mentioned so fingers crossed they’re using the first and best commercially available NN!
AI technology | imec
Artificial intelligence is about to get real: the technologies are mature and the applications are promising. Want to get on board? Imec is ready to assist you.
Yiyi Wang, Ph.D. on LinkedIn: Edge AI Innovator Femtosense Brings Affordable, Off-the-Shelf Hearing…
We are proud to partner with Femtosense to deliver the Edge AI chip!
davidfitz
Regular
Looks likes the Prophesee demo at The Venetian (beautiful hotel by the way) is popular with only a few meetings left for the first couple of days.
www.prophesee.ai
Book a Demo with the Prophesee Team
January 07 - 3:30 a.m., 7:30 a.m., 8 a.m. or 9 a.m.
Book a meeting | PROPHESEE
Book a meeting with our team to discover how Event-Based Vision will get your computer vision applications to the next level
Book a Demo with the Prophesee Team
January 06 - 7:30 a.m. or 9 a.m.
January 07 - 3:30 a.m., 7:30 a.m., 8 a.m. or 9 a.m.
equanimous
Norse clairvoyant shapeshifter goddess
I can see Dio shaking his head but im eager to hear his replyWhy is dough another word for money? Because everyone kneads it.
Fact Finder
Top 20
IMEC are not supplying the IP they helped produce the actual silicon.Unfortunately not - they are using these guys
AI technology | imec
Artificial intelligence is about to get real: the technologies are mature and the applications are promising. Want to get on board? Imec is ready to assist you.www.imec-int.com
Yiyi Wang, Ph.D. on LinkedIn: Edge AI Innovator Femtosense Brings Affordable, Off-the-Shelf Hearing…
We are proud to partner with Femtosense to deliver the Edge AI chip!www.linkedin.com
ARM is in the sights for the IP.
Also I am puzzled by the claim it is a result of 50 years of research when he looks barely 30 years. Even if he was an in vitro prodigy he is still over 19 years light on:
“Femtosense: Our Ultra-efficient AI Chip, Built with Arm Flexible Access
Sam Fok, co-founder and CEO of silicon startup Femtosense, explains how Arm Flexible Access for Startups enabled the development of a neuromorphic AI chip
Posted on 26th January 2021By Sam Fok, Co-founder and CEO, Femtosense
Artificial Intelligence (AI)Endpoint
Reading Time: 6 mins
One classical pathway to technology success runs from university research to commercial startup. It’s an exciting journey in which a small group of grad students takes a spark of innovation from research and kindles it into a technology that they hope will transform the world.
That journey has its challenges as the technology moves from the lab into the rigorous and sometimes unforgiving world of product development. And it’s a journey my co-founder, Alexander Neckar, and I embarked on two years ago out of Stanford.
Our startup, Femtosense, emerged from work we did in Stanford’s Electrical Engineering graduate program on a project called Braindrop—a mixed-signal neuromorphic system designed to be programmed at a high level of abstraction.
Neuromorphic systems are silicon versions of the neural systems found in neurobiology. It’s a growing field, offering a range of exciting possibilities such as sensory systems that rival human senses in real-time.
Over the past two years, we’ve nurtured our startup to develop the aspects of the technology with commercial potential. We’ve taken the original concept and built a neural network application-specific integrated circuit (ASIC) for the general application area of ultra-efficient AI. As a start, we want to enable ultra-power-efficient inference in embedded endpoint devices everywhere.
Why did we venture down this path? Datacenter technology is well-developed and has different technical challenges than edge technology. Further, consumers and market competition are pushing for edge and endpoint devices with ever-increasing capability. AI can and should be deployed at the endpoints when feasible to reduce latency, lower computing costs, and enhance security.
Area and power major considerations in neural networks
But designing such an ASIC (any ASIC really) is a unique challenge in today’s ultra-deep submicron world. For one thing, area and power considerations loom large. Neural networks are a different animal than classical signal processing. Designing an ASIC or system-on-chip (SoC) for neural networks presents a different challenge than, say, designing an efficient DSP or microcontroller.Neural networks have a lot of parameters, are quite memory intensive, and have a lot of potential for energetically expensive data motion. Of primary concern is the question of on-chip versus off-chip memory. Off-chip memory provides excellent density, allowing for bigger models, but accessing off-chip memory costs a lot of energy, which often puts such systems beyond the power budgets of the envisioned initial applications.
So, when you’re looking at ultra-power-efficient endpoint embedded solutions, you will want to put everything a single die, but then you will hit area and cost issues. This is where algorithm-hardware codesign comes into play; the two really must be done together.
You can’t just naively take an algorithm and map it down to a chip. It would cost too much energy or money or not just perform well. You have to think carefully about how to make that algorithm efficient. That’s the hardware and algorithm co-design challenge. We spend a lot of effort on the algorithm side to fit everything on-chip, and, once it’s on-chip, to map the algorithm onto the chip’s compute fabric.
As we design, we’re exploring many potential applications because we want to apply our technology as widely as possible. The market is not nearly as black-and-white as endpoint-and-cloud terminology suggests.
We see it as a continuum. It’s not like you’re either in datacenters or in tiny battery-powered devices. There are many nodes across the spectrum—everything from on-prem servers, to laptops, phones, smartwatches, earbuds, and even sensors out in the middle of nowhere with no power source could use more efficient neural network compute.
We want to deliver ultra-efficient compute. To us, this is our primary mission. When you’re in tough environments with tight requirements, that’s when you’re going to want to use our technology.
Arm Flexible Access for Startups gave us the design flexibility we needed
We’re a small team for now, so we need to focus on our strengths. There’s the core hardware accelerator, the software that goes with it, and the algorithms. Then, there’s technology to take that value and serve customers. This is where we’re very excited to be working with Arm and the Arm Flexible Access for Startups program.To integrate with customer designs, you need an interface to handle communications and off-load a bit of compute. This is not something we think about day-to-day in terms of our core engineering or IP. This is why it’s paramount to have a well-established, reliable partner like Arm to work with because you don’t have to reinvent everything or spend effort educating the market. Everyone knows Arm, and Arm is a well-known path to integration. Arm solves one of our biggest commercial challenges, and that’s why working with Arm is key.
One of the attractive elements of the Arm Flexible Access for Startups program is the ecosystem support. The ecosystem reduces barriers to adoption, which in turn drives innovation. When you’re planning projects, you need clear and accessible specifications and information about which products do what.
Making actionable information available upfront without huge outlays and with the ability to evaluate different IP and run experiments in the sandbox is huge for us. The program’s pricing models are much more aligned with how startups grow than traditional IP vending.
Standing at the beginning of the SoC integration path, we have an exciting journey ahead, and we’ll have more interesting perspectives the deeper we get into it. We have the initial design and are moving toward an ASIC implementation, making the Arm Flexible Access for Startups program an important tool to have.”
My opinion only DYOR
FF
AKIDA BALLISTA
PS: I suppose his Dad could have started the research before he was born and gave it to him when he was born.
Nearly had a heart attack....
Gates, Bezos invest in Aust 'brain chip'
Billionaires Bill Gates and Jeff Bezos have thrown their weight behind a potentially life-changing paralysis treatment that lets patients control computers with their minds.
Founded by Australian professors Tom Oxley and Nick Opie, New York-based Synchron announced on Friday it had closed a $110 million Series C funding round led by ARCH Venture Partners, with participation from Bezos Expeditions and Gates Frontier.
The product is a tiny device that can be implanted on blood vessels on the surface of the brain via the jugular vein.
Gates, Bezos invest in Aust 'brain chip'
Billionaires Bill Gates and Jeff Bezos have invested in an Australian brain-computer interface company in direct competition with Elon Musk start-up Neuralink.www.google.com
Hi Cardpro,
Thanks for posting this. I think Synchron has been mentioned a couple of times before but this is a timely reminder. There is a clear potential for using Akida in conjunction with this. It ties in nicely with my response to @Bravo's post about brain control of external devices and the brain spike sensor detecting apparently random spikes which N-of-M coding and the JAST rules (from Simon Thorpe's Spikenet company, now owned by BrainChip) can unscramble:
Here are some Synchron patents:
US2022369994A1 NEUROMONITORING DIAGNOSTIC SYSTEMS
A method of facilitating direct interaction between a distributed neural network of a brain of an individual and an external device, the method comprising:
generating a plurality of feedback data from the external device where the plurality of feedback data is related to an activity of the external device;
establishing a connection from the external device to a control unit coupled to the individual, where the control unit includes at a first neural implant previously positioned within a first cytoarchitecture region of the distributed neural network of the brain of the individual; and
transmitting the plurality of feedback data to the control unit, such that the control unit energizes the first neural implant to stimulate the first cytoarchitecture region of the brain, which produces an effect in the individual that is specific to the first cytoarchitecture region such that the individual is able to perceive the effect.
AU2020378095A1 Methods, systems, and apparatus for closed-loop neuromodulation
A method of treating epilepsy, comprising:
detecting, using a first electrode array, an electrophysiological signal of a subject, wherein the first electrode array is coupled to a first endovascular carrier implanted within the subject;
analyzing the electrophysiological signal using a neuromodulation unit implanted within the subject and electrically coupled to the first electrode array; and stimulating an intracorporeal target of the subject using a second electrode array in response to the electrophysiological signal detected, wherein the second electrode array is electrically coupled to the neuromodulation unit, and wherein the second electrode array is coupled to a second endovascular carrier implanted superior to a base of a skull of the subject.
AU2021246506A1 Systems and methods for controlling a device using detected changes in a neural-related signal
Systems and methods of controlling a device using detected changes in a neural-related signal of a subject are disclosed. In one embodiment, a method of controlling a device or software application comprises detecting a first change in a neural-related signal of a subject, detecting a second change in the neural-related signal, and transmitting an input command to the device upon or following the detection of the second change in the neural-related signal. The neural-related signal can be detected using a neural interface implanted within a brain of the subject.
Taproot
Regular
It's so great watching Tim Llewellyn frothing over Brainchip, his enthusiasm is infectious.Best advertising for us from NVISO..
NVISO and BrainChip make a #winningcombo! Get ready for a game-changing #neuromorphic demo at #CES2023.
Timothy Llewellynn on LinkedIn: NVISO BrainChip CES 2023
NVISO and BrainChip make a #winningcombo! Get ready for a game-changing event-based fully digital #neuromorphic demo at #CES2023. It has only been #9months…
It has only been #9months since we got our hands on the first commercial #neuromorphic silicon. Hence we are pretty excited to announce our partner BrainChip will be displaying our #optimised #neuro #SDK designed to power next-generation #automotive #drivermonitoring and #interiorsensing solutions using standard CMOS RGB/NIR sensors capable to run at #ultralowpower.
NVISO Neuro SDK running on Akida allows somecrazy stuff. What makes this great
We can run models at over 1000 FPS at ultra-low power (models run faster with 1/3 clock speed of a GPU). Think #PS5 #AR #VR type experiences in your car. #nocloud #battery
Leverage 2/4-bit quantized models that use just KBs of RAM, resulting in #massive #power and #cost #savings during production. Put models into the #tiniestofplaces running at #ultralowpower.
🎖 Fully compatible with #existing #RGB #NIR sensors, allowing for the reuse of #proven #sensor #technology and the elimination of the need to qualify new sensors. Now new training datasets - completely reuse existing data investments.
Our #unique #holistic #approach to detecting #complex #emotions maps exceptionally well to Akida’s ability to handle simultaneous multiplexing of models, something that traditional cloud, mobile, or GPU systems struggle with. Get #more #bang for your $.
Read our full press release here: https://bit.ly/3GcTKPG
Our software demo at CES will showcase #real #usescases of the power of our Neuro SDK when run on BrainChip Akida neuromorphic processor. If you are in the #automotive business of building #L3 automated cars Ola Kaellenius Benjamin Petz François Piednoel Magnus Östberg Frank Weber Peter Dr. Lehnert Mary Barra Valerie Brown Said Ben Shoham Oliver Hoffmann Neda Cvijetic Firas Lethaus Dr.-Ing. Mohsen Sefati James Kuffner and you don't have an end-to-end silicon to AI solution strategy - then you should haul yourself over to the Socionext US booth in Vehicle Tech and Advanced Mobility Zone in the Las Vegas Convention Center, North Hall, booth 10654 at #CES2023 and checkout the demo.
A huge thanks to the NVISO and BrainChip teams Miguel de Prado Luigi Bagnato Bogdan Lazar Abdelrahman Abubakr Colin Mason Anil Mankar Rob Telson Todd Vierra
Nikunj Kotecha Nandan Nayampally Richard Chevalier for all their hard work in getting this demo ready for CES 2023!
You can just tell that Akida is lighting up absolutely everything that he has been working so hard to achieve over the past 13 years.
He's so excited, that he barely seems to be able to contain himself
I can't help think that Luca Verre, ( Prophesee ), is feeling a little the same !
"Tim Llewellyn is President of Bonseyes AI Marketplace. Bonseyes is an open and expandable AI platform that intends to transform AI development from a cloud centric model, dominated by large internet companies, to an edge device centric model through a marketplace and an open AI platform. Tim Llewellyn is also CEO and co-founder of Nviso, a company that provides artificial intelligence solutions."
"Tim Llewellyn started nViso October 2009"
"Tim Llewellyn is CEO and Co-founder of nViso SA. Tim has 10 years’ experience in high-tech startups and is pioneering a truly scalable emotion recognition platform to help capture and analyze the emotional response and visual attention of consumers on a scale and level of detail not previously possible. Tim received his B.E. and M.E. (Hons) degrees in Electrical Engineering from the University of Canterbury, New Zealand in 1999 and 2001. Tim was a speaker at the ESOMAR 3D Digital Dimensions 2011 conference in Miami. Prior to founding nViso, Tim worked on ultralow power wearable devices as part of the Swatch Group. In Swatch, Tim helped build the first ultra-low power Smart Watches together with Microsoft, which turned out well ahead of its time."
Are we involved in it. If posted before apology
www.linkedin.com
Sony Depthsensing Solutions on LinkedIn: #demonstration #conceptcar #demonstration #sensors #interior #exterior…
Two days left before the #demonstration of our unique #conceptcar at CES 2023! 🔵 Contact Jan-Martin Juptner on LinkedIn to book your appointment. During the…
equanimous
Norse clairvoyant shapeshifter goddess
Prior to founding nViso, Tim worked on ultralow power wearable devices as part of the Swatch Group. In Swatch, Tim helped build the first ultra-low power Smart Watches together with Microsoft, which turned out well ahead of its time."
Worth repeating again. Pun intended also
Worth repeating again. Pun intended also
You won't get a rise out of me, but it did get a wry smile.
Jumpchooks
Regular
Yes well said dY22. I agree, grow peeps and let our Company's "Actions Speak Louder than Words".
Fact Finder
Top 20
Fullmoonfever
Top 20
These guys are apparently on the hunt
Chipmaker Infineon Ready to Spend Billions on Acquisitions - CEO
By Reuters
Dec. 28, 2022
MUNICH (Reuters) -Infineon is ready to spend several billion euros on the right takeover target as it searches for acquisitions to boost growth, Chief Executive Jochen Hanebeck said in an interview published on Wednesday.
The German chip maker is constantly "on the lookout" for suitable companies, Hanebeck told Frankfurter Allgemeine Zeitung (FAZ). "I see it in the range of up to a few billion (euros)."
The plans come at a time when demand for chips used in everything from smartphones to cars soars and supply chain bottlenecks lasting almost two years have plagued global industries from autos to healthcare and telecoms.
Infineon, which reported a 63% jump in segment profit to 3.4 billion euros ($3.6 billion) in the fiscal year that ended Sept. 30, has said it sees growth in particular in electromobility, autonomous driving, renewable energy, data centres, and the so-called internet of things.
The CEO would not comment on individual takeover candidates, according to the newspaper. He said the company could expand its portfolio in several fields, including power semiconductors, sensors, software and artificial intelligence.
It was quite conceivable that start-ups that are not sufficiently well financed, for example, would want to join a corporation, Hanebeck told FAZ.
Infineon had bought U.S. rivals Cypress Semiconductor for $10 billion and International Rectifier for $3 billion in 2019 and 2014, respectively, to expand in next-generation automobiles and Internet technologies.
To boost production capacity in Europe in a fiercely contested market, Brussels in February launched the so-called Chips Act, enabling 15 billion euros in additional public and private investment in the industry by 2030 on top of 30 billion euros of public investments already planned.
Infineon said last month it was planning a new 5 billion-euro factory in the eastern German city of Dresden.
Taiwan's TSMC is also in advanced talks about setting up its first European plant in Dresden, according to a media report.
Intel, on the other hand, has backed away from its original target of opening a chip factory in eastern Germany in the first half of 2023, according to another media report.
($1 = 0.9405 euros)
(Reporting by Kirsti Knolle, editing by John Revill, Maria Sheahan and Tomasz Janowski)
Copyright 2022 Thomson Reuters.
Getupthere
Regular
Top 10 Essential Tech Trends in 2023 Everyone Must be Ready For
Technology, be it in the form of AI or machine learning, it has made it extremely convenient for organizations to reduce costs, enhance customer experiences and increase profits. Here, we bring for you a list of top 10 essential tech trends in 2023 everyone must be ready for.
www.analyticsinsight.net
Artificial intelligence
It has been quite some time that artificial Intelligence has become popular. As a matter of fact, AI is constantly evolving, and newer applications for this emerging technology continue to spring upon the scene. Today, there are countless applications that rely on AI – image and speech recognition, navigation programs, voice assistants like Siri and Alexa, to name a few. No wonder, the coming years will see a lot more dependence on AI.Edge computing
These days, we can see millions of data points collecting user information from various sources such as social media, websites, emails, and web searches. This throws light on how exponentially the data collected is increasing. This is why old and traditional computing methods fall short. Well, edge computing to the rescue.
Taproot
Regular
nViso + TobiiPrior to founding nViso, Tim worked on ultralow power wearable devices as part of the Swatch Group. In Swatch, Tim helped build the first ultra-low power Smart Watches together with Microsoft, which turned out well ahead of its time."
Worth repeating again. Pun intended also
Tobii + Sony
Eye-tracking firm confirms Sony has licensed its tech for PSVR2 | VGC
Players will likely be able to control game elements using just eye movement…
www.videogameschronicle.com
Fact Finder
Top 20
Hi @Diogenese
On a serious note ‘La, la, la’ the following link for Femtosense is pointing me to a sparse Von Neumann mathematical approach improving performance but not revolutionising Ai the AKIDA way. Any ‘wisdomie’ thoughts:
Technology - FEMTOSENSE
femtosense.ai
Regards
FF
AKIDA BALLISTA
Fact Finder
Top 20
In this environment I wonder who would lend them the extra 95 billion???These guys are apparently on the hunt
Chipmaker Infineon Ready to Spend Billions on Acquisitions - CEO
By Reuters
Dec. 28, 2022
MUNICH (Reuters) -Infineon is ready to spend several billion euros on the right takeover target as it searches for acquisitions to boost growth, Chief Executive Jochen Hanebeck said in an interview published on Wednesday.
The German chip maker is constantly "on the lookout" for suitable companies, Hanebeck told Frankfurter Allgemeine Zeitung (FAZ). "I see it in the range of up to a few billion (euros)."
The plans come at a time when demand for chips used in everything from smartphones to cars soars and supply chain bottlenecks lasting almost two years have plagued global industries from autos to healthcare and telecoms.
Infineon, which reported a 63% jump in segment profit to 3.4 billion euros ($3.6 billion) in the fiscal year that ended Sept. 30, has said it sees growth in particular in electromobility, autonomous driving, renewable energy, data centres, and the so-called internet of things.
The CEO would not comment on individual takeover candidates, according to the newspaper. He said the company could expand its portfolio in several fields, including power semiconductors, sensors, software and artificial intelligence.
It was quite conceivable that start-ups that are not sufficiently well financed, for example, would want to join a corporation, Hanebeck told FAZ.
Infineon had bought U.S. rivals Cypress Semiconductor for $10 billion and International Rectifier for $3 billion in 2019 and 2014, respectively, to expand in next-generation automobiles and Internet technologies.
To boost production capacity in Europe in a fiercely contested market, Brussels in February launched the so-called Chips Act, enabling 15 billion euros in additional public and private investment in the industry by 2030 on top of 30 billion euros of public investments already planned.
Infineon said last month it was planning a new 5 billion-euro factory in the eastern German city of Dresden.
Taiwan's TSMC is also in advanced talks about setting up its first European plant in Dresden, according to a media report.
Intel, on the other hand, has backed away from its original target of opening a chip factory in eastern Germany in the first half of 2023, according to another media report.
($1 = 0.9405 euros)
(Reporting by Kirsti Knolle, editing by John Revill, Maria Sheahan and Tomasz Janowski)
Copyright 2022 Thomson Reuters.
Similar threads
