BRN Discussion Ongoing

Moneytalks

Member
Had this been thrown up yet?


They have something new under wraps👍
 
  • Like
  • Thinking
  • Wow
Reactions: 14 users

itsol4605

Regular
Hi Bravo,

It seems that EdgeX are using Akida 1500(?) as the low power, low precision wake-up and, I'm guessing, Jetson for the full (software) classification? The 1500 does need an external processor for configuration etc., ie, no integrated ARM Cortex.

We know Nvidia has been working with Mercedes.

We know Mercedes is proposing to use software for sensor signal processing.

I reckon they will be using TeNNs/Akida 2 simulation software, presumably running on an Nvidia processor, so Nvidia should be familiar with Akida from their work with Mercedes. TeNNs light processor load and quasi-real-time performance make it feasible to use it in software format.

So, if Nvidia were to be interested in developing an Akida/Nvidia SoCC, I think it would be at the edge to start with, as with Mercedes ADAS processor. for example

But I don't know whether that would involve Sensor/SNN fusion or SNN/processor fusion, or a hybrid. Presumably they have had the processor/software version working for some time, and this may be the chosen near-term model while the technology continues to develop.

Of course, Akida SoC is updatable to the extent that the models can be upgraded using federated learning, somehting which PvdM foresaw a decade ago.
"... they will be using TeNNs/Akida 2 simulation software, presumably running on an Nvidia processor..."

Using 'TeNNs/Akida 2 simulation software' free of charge??
 
  • Like
Reactions: 7 users

Diogenese

Top 20
"... they will be using TeNNs/Akida 2 simulation software, presumably running on an Nvidia processor..."

Using 'TeNNs/Akida 2 simulation software' free of charge??
Just to put that in context, the quote was qualified by "I reckon", ie, it is an informed guess, not an established fact.

As to a software licence, Sean recently revealed there is a new algorithm product line to add to the IP. Again, I reckon commercial use of the simulation software would attract a licence fee for each copy of the software, just as any other commercial software, plus ongoing maintenance fees.
 
  • Like
  • Fire
  • Love
Reactions: 33 users
Wonder why they put us at the top of the list? Heheheh!



View attachment 69743




Neuromorphic Computing Market to Reach $20.4 Billion by 2031 By Top Research Firm​

2024-09-23
3D Technology


Onkar Patil

Guest Post By
Onkar PatilInformation Technology Markets2024-09-23
According to Persistence Market Research, the global neuromorphic computing market is projected to grow from USD 5.4 billion in 2024 to USD 20.4 billion by 2031, with a CAGR of 20.9%, fueled by advancements in hardware and applications in robotics, healthcare, and autonomous vehicles

Introduction: The Rise of Neuromorphic Computing
The global neuromorphic computing market is poised for significant growth, projected to expand from US$5.4 billion in 2024 to US$20.4 billion by 2031, achieving a robust CAGR of 20.9% during the forecast period. Key trends driving this growth include advancements in neuromorphic hardware and a shift beyond traditional AI applications into sectors like robotics, autonomous vehicles, and healthcare diagnostics.
The development of efficient neuromorphic algorithms for processing complex data patterns is also gaining momentum. Consumer electronics are expected to capture a substantial revenue share, with North America leading the market.
Historically, the market has grown at a CAGR of 16.7% from 2018 to 2023, underscoring its rapid evolution and expanding applications.
Understanding Neuromorphic Computing
Neuromorphic computing refers to the design of computer systems inspired by the structure and function of the human brain. Unlike traditional computing systems that rely on binary processing, neuromorphic systems use spiking neural networks to process data in a way that resembles human cognition.
This paradigm shift enables these systems to learn, adapt, and perform complex tasks with a high degree of efficiency.
The Components of Neuromorphic Systems
Neuromorphic systems typically consist of specialized hardware and software designed to emulate neural processes. Key components include:
  • Neurons and Synapses: Basic units of processing, mimicking the biological counterparts in the brain.
  • Spike-Timing Dependent Plasticity (STDP): A learning rule that adjusts the strength of connections based on the timing of neuron spikes.
  • Event-Driven Architecture: Processing is triggered by changes in the environment, allowing for real-time data processing with minimal power consumption.
Elevate your business strategy with comprehensive market data.

Request a sample report now:
www.persistencemarketresearch.com/samples/34726

Factors Driving Market Growth
Several factors are driving the growth of the neuromorphic computing market, each contributing to the technology's increasing adoption across various sectors.
Demand for Energy-Efficient Computing
As data centers and computing systems become increasingly energy-intensive, the need for energy-efficient alternatives is paramount. Neuromorphic computing's ability to perform complex computations with significantly lower power consumption compared to traditional systems makes it an attractive option for organizations looking to reduce their carbon footprint and operational costs.
Advances in Artificial Intelligence and Machine Learning
The rapid advancements in artificial intelligence (AI) and machine learning (ML) are creating a fertile ground for neuromorphic computing. These technologies require sophisticated algorithms capable of processing large amounts of data quickly and accurately.
Neuromorphic systems, with their inherent ability to learn and adapt, are uniquely positioned to enhance AI and ML applications, leading to greater efficiency and effectiveness.
Increasing Investment in Research and Development
The neuromorphic computing sector is witnessing significant investments from both public and private sectors. Governments and organizations are allocating funds to research and development initiatives aimed at exploring the full potential of neuromorphic architectures.
This influx of capital is driving innovation and accelerating the deployment of neuromorphic technologies across various industries.
Key Applications of Neuromorphic Computing
The potential applications of neuromorphic computing are vast and varied, spanning multiple sectors. Here are some of the key areas where this technology is making significant strides:
Robotics and Autonomous Systems
Neuromorphic computing plays a crucial role in enhancing the capabilities of robots and autonomous systems. By enabling machines to process sensory information in real-time, neuromorphic architectures improve decision-making and adaptability, making them more effective in dynamic environments.
Healthcare and Medical Diagnostics
In healthcare, neuromorphic computing is being utilized to enhance medical diagnostics and patient monitoring systems. By processing vast amounts of data from medical devices and imaging systems, neuromorphic technologies can identify patterns and anomalies more quickly, leading to improved patient outcomes and more efficient care delivery.
Smart Devices and the Internet of Things (IoT)
As the IoT continues to expand, the need for intelligent processing solutions becomes increasingly critical. Neuromorphic computing offers a powerful solution for smart devices, allowing them to learn from user interactions and environmental changes.
This capability enhances functionality and provides a more personalized experience for users.
Regional Insights: Where is the Growth Happening?
The neuromorphic computing market is not limited to a specific geographical region; instead, it is experiencing growth across the globe. However, certain regions are emerging as key players in this space.
North America: A Leader in Innovation
North America is at the forefront of neuromorphic computing innovation, driven by significant investment in research and development from both private companies and government agencies. The presence of leading tech companies and research institutions is fostering collaboration and accelerating advancements in neuromorphic technologies.
Europe: A Growing Hub for Research
Europe is also emerging as a crucial player in the neuromorphic computing market. With initiatives such as the Human Brain Project, European researchers are pushing the boundaries of what is possible with neuromorphic systems.
The region's focus on AI and machine learning is further propelling growth in this sector.
Asia-Pacific: The Next Frontier
The Asia-Pacific region is expected to witness substantial growth in the neuromorphic computing market. Countries like China and Japan are investing heavily in AI research and development, positioning themselves as leaders in adopting neuromorphic technologies.
The growing demand for advanced computing solutions in industries such as robotics and healthcare is driving this growth.
Challenges and Considerations
Despite the promising outlook for the neuromorphic computing market, several challenges need to be addressed.
Technical Complexity
The technical complexity of designing and implementing neuromorphic systems presents a significant hurdle for widespread adoption. Organizations may face challenges in integrating these systems with existing infrastructure, requiring substantial investment in training and development.
Standardization and Compatibility
The lack of standardization in neuromorphic architectures can hinder interoperability between different systems. Establishing industry standards is essential to facilitate collaboration and ensure compatibility among various neuromorphic technologies.
Ethical Considerations
As with any advanced technology, neuromorphic computing raises ethical considerations regarding privacy, security, and potential misuse. Addressing these concerns will be critical in building public trust and ensuring responsible deployment of neuromorphic systems.
Key Players:
  • BrainChip Holdings Ltd.
  • Intel Corporation
  • Qualcomm
  • SynSense AG
  • Samsung Electronics Co. Ltd
  • IBM Corporation
  • SK Hynix Inc.
  • General Vision Inc.
  • GrAI Matter Labs
  • Innatera Nanosystems
The Future of Neuromorphic Computing
Looking ahead, the future of neuromorphic computing appears bright. With advancements in hardware and software, combined with increasing investment in research and development, the potential for neuromorphic systems is vast.
As organizations continue to seek more efficient and intelligent solutions, the demand for neuromorphic computing is expected to surge.
Collaboration Between Academia and Industry
To realize the full potential of neuromorphic computing, collaboration between academia and industry will be vital. Researchers can drive innovation while industry partners can facilitate the practical application of these technologies, creating a symbiotic relationship that benefits both sectors.
Continued Investment and Research
Ongoing investment in neuromorphic research will be crucial for addressing the current challenges and unlocking new applications. As organizations recognize the potential benefits of neuromorphic systems, we can expect to see a significant increase in funding and resources dedicated to this field.
Conclusion: A Transformative Force in Computing
The neuromorphic computing market is on the brink of explosive growth, with projections indicating a market size of $20.4 billion by 2031. As this technology continues to evolve, its applications across various sectors will expand, driving innovation and transforming the way we process information.
Embracing neuromorphic computing will not only enhance efficiency but also pave the way for a more intelligent and adaptive future.


All of a sudden I am getting a very warm surge of blood pounding through my veins.
The more I think about it I get cold sweats

Is it about to blow jimmy????
 
  • Haha
  • Like
Reactions: 14 users

IloveLamp

Top 20
Last edited:
  • Like
  • Thinking
  • Wow
Reactions: 14 users
Steve Brightfields Presso from the recent AI Hardware & Edge AI Summit,

Hadn't noticed if posted but haven't read every post as been bit busy.

Link to Kiasco who posted it or I scrolled it below for quick reading.


BRN Presso Sept 24.jpg
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 81 users
Had this been thrown up yet?


They have something new under wraps👍
Or this........ Steve likes it!

 
  • Like
  • Thinking
Reactions: 10 users

Diogenese

Top 20
Steve Brightfields Presso from the recent AI Hardware & Edge AI Summit,

Hadn't noticed posted but haven't read every post as been bit busy.

Link to Kiasco who posted it or I scrolled it below for quick reading.


View attachment 69769
That is a very impressive presentation.

I particularly like the penultimate slide:

"New model algorithms in software".

This is a faster way to implementation.
 
  • Like
  • Love
  • Fire
Reactions: 41 users

Diogenese

Top 20
That is a very impressive presentation.

I particularly like the penultimate slide:

"New model algorithms in software".

This is a faster way to implementation.
... also "Akida Pico", surely this is for hearing aids.
 
  • Like
  • Fire
Reactions: 31 users
... also "Akida Pico", surely this is for hearing aids.
Was trying to find anything related to it.

Is it hearing?...got no idea but as someone like yourself would know, Pico is used in units of measurement, very small, but I also see it is an acronym also used in evidence based medicine...could something like this framework be used to guide creation of models for Akida 2.0 / Tenns?

Who knows where that came from in the presso?


Evidence Based Medicine: The PICO Framework​


Natural language questions typically do not contain the elements of clearly formulated question and can lead to difficulty when trying to find an answer.2,3 A modest investment of time to consider what you need to find out and construct a focused question will yield a more effective and efficient search for evidence, helping you to more quickly locate the best available evidence to inform your decision.

The PICO Framework​

The PICO framework is the most commonly used model for structuring clinical questions because it captures each key element required for a focused question. PICO stands for:
  • Patient or problem
  • Intervention or exposure
  • Comparison or control
  • Outcome(s)
 
  • Like
  • Fire
  • Love
Reactions: 20 users

Diogenese

Top 20
OOoo-oooH-ooh!

Obviously you think this means that there is a chance that they're incoproating OUR new model algorithms ???

I think I was the first to give this a ❤️

Hopefully that means I snuck in first for a more in depth description of why it COULD BE US??
I'd like to think that "THEY" are using our software, but who is "THEY"?

My list includes Valeo and Mercedes in their up-coming product releases. Prophesee is another likely user for their high definition DVS (Synsense being adopted for the el cheapo DVS). In fact, all the EAPs will already have been trying out Akida 2/TeNNs software.

What I'd like to know is, who took over the tape-out of Akida 2:

Intel with their 18A gate-all-around process,
Nvidia with their ADAS processor,
ARM, with whom we have a long-standing relationship,
Socionext,
TSMC,
TATA,
MegaChips ... ?

I think it has to be at that sort of level.
 
  • Like
  • Love
  • Fire
Reactions: 44 users

Diogenese

Top 20
Was trying to find anything related to it.

Is it hearing?...got no idea but as someone like yourself would know, Pico is used in units of measurement, very small, but I also see it is an acronym also used in evidence based medicine...could something like this framework be used to guide creation of models for Akida 2.0 / Tenns?

Who knows where that came from in the presso?


Evidence Based Medicine: The PICO Framework​


Natural language questions typically do not contain the elements of clearly formulated question and can lead to difficulty when trying to find an answer.2,3 A modest investment of time to consider what you need to find out and construct a focused question will yield a more effective and efficient search for evidence, helping you to more quickly locate the best available evidence to inform your decision.

The PICO Framework​

The PICO framework is the most commonly used model for structuring clinical questions because it captures each key element required for a focused question. PICO stands for:
  • Patient or problem
  • Intervention or exposure
  • Comparison or control
  • Outcome(s)
Hi FMF,

Being an engineer, I'm a literal sort of person. I took it to mean "very small", ie, something which could fit in the ear, or on a MCU that fits in the ear. The noise cancelling would be very useful for that. It reduces the processing MACs to less than one tenth compared with known systems, so it would require less processor capacity.
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 34 users
Hi FMF,

Being an engineer, I'm a literal sort of person. I took it to mean "very small", ie, something which could fit in the era, or on a MCU that fits in the ear. The noise cancelling would be very useful for that. It reduces the processing MACs to less than one tenth compared with known systems, so it would require less processor capacity.
Figured it might be the very small definition given the engineering background :)

The medical Pico framework did pique my interest though as something that could fit with NLP models or maybe not?
 
  • Like
  • Love
Reactions: 8 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Hi FMF,

Being an engineer, I'm a literal sort of person. I took it to mean "very small", ie, something which could fit in the ear, or on a MCU that fits in the ear. The noise cancelling would be very useful for that. It reduces the processing MACs to less than one tenth compared with known systems, so it would require less processor capacity.

Please let it be Cochlear Australia!

I love their catch phrase "Hear now. And always".

My partner has hearing issues and suffers terribly from tinnitus, so this is a subject that is extremely close to my heart.


Screenshot 2024-09-24 at 10.52.40 pm.png
 
  • Like
  • Love
  • Fire
Reactions: 35 users
Please let it be Cochlear Australia!

I love their catch phrase "Hear now. And always".

My partner has hearing issues and suffers terribly from tinnitus, so this is a subject that is extremely close to my heart.


View attachment 69775
Hearing aids, are an ever growing market, with the growth in popularity, of "Earbuds" among the masses.

I believe, there will be a much larger Future market, than there is currently.

I also have big hopes, that Cochlear, is a Future customer of ours 👍
 
  • Like
  • Thinking
  • Fire
Reactions: 17 users

Diogenese

Top 20
Please let it be Cochlear Australia!

I love their catch phrase "Hear now. And always".

My partner has hearing issues and suffers terribly from tinnitus, so this is a subject that is extremely close to my heart.


View attachment 69775
Sympathy to your partner - it must be literal torture.

I think I read somewhere a long while ago about noise-cancelling as a treatment for tinnitus. Now, if that is correct, each person could build their own noise-cancelling NN model. But the problem would be phase synchronization. To work, the treatment sound would need to be 180 degrees out of phase with the tinnitus and it would be difficult to maintain that synchronization so some feedback mechanism (PLL) would be requied. Perhaps that could be done by some biosensor, like those brain wave sensors, or maybe some simpler physiological reaction.

Nope, I didn't imagine it:
https://www.joinoto.com/articles/noise-cancelling-headphones-for-tinnitus
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 21 users

RobjHunt

Regular
  • Like
Reactions: 5 users
Please let it be Cochlear Australia!

I love their catch phrase "Hear now. And always".

My partner has hearing issues and suffers terribly from tinnitus, so this is a subject that is extremely close to my heart.


View attachment 69775
My wife calls it selective hearing.
 
  • Haha
  • Like
Reactions: 11 users

GStocks123

Regular
Mahesh from Google presenting on LLM>TinyML- He mentions 1-4bit quantisation (1bit, being the future)- A great match for Akida!

 
  • Like
  • Fire
Reactions: 10 users
Top Bottom