BRN Discussion Ongoing

Diogenese said:

Don't encourage her.

Click to expand...

@Diogenese , Your right, we have gone this long not hearing her.

keyeat said:

Armand Ruiz on LinkedIn: This new chip turns AI upside down. IBM NorthPole is the hardware… | 61 comments

This new chip turns AI upside down. IBM NorthPole is the hardware breakthrough that supercharges AI. IBM's NorthPole overcomes key tradeoffs… | 61 comments on LinkedIn

www.linkedin.com

Click to expand...

This is the last sentence of that post. Sounds great but............
Kudos to the brilliant team from IBM Research for leading this development. We can't wait to make this technology available to our customers.

IloveLamp said:

Why Qualcomm AI Orchestrator is the key to next generation AI experiences | Qualcomm

Discover how Qualcomm AI Orchestrator enhances on-device AI with personalized, multimodal support, improving privacy and responsiveness.

www.qualcomm.com

View attachment 70343

Click to expand...

Diogenese said:

Don't encourage her.

Click to expand...

OOooooohh! That sounds encouraging @IloveLamp!

For a millisecond I thought this was going to be it and be the icing on my cake. But then I remembered it was an announcement from
BRN

Food4 thought said:

Brainchip really need to release a good news story on asx to have and capture the good news stories in the media or we will be going backwards again
Down down the s p is down

Click to expand...

I think you need more food for your thoughts…

keyeat said:

Armand Ruiz on LinkedIn: This new chip turns AI upside down. IBM NorthPole is the hardware… | 61 comments

This new chip turns AI upside down. IBM NorthPole is the hardware breakthrough that supercharges AI. IBM's NorthPole overcomes key tradeoffs… | 61 comments on LinkedIn

www.linkedin.com

Click to expand...

IBM have several patent applications for hybrid (Frankenstein) analog/digital NNs.

They must have found way of solving the manufacturing and operational variability of memristors. I guess the problem is manageable with single bit weights/activations.

US2024202275A1 ASSIGNING DNN WEIGHTS TO A 3D CROSSBAR ARRAY 20221220





US2024185057A1 HYBRID ANALOG SYSTEM FOR TRANSFER LEARNING 20221205

Good afternoon,

What I find rather interesting, if that's the right word is in the attached link below, that's primarily focused on us,
Brainchip's latest offering AKIDA PICO, how does Mike Davies (Intel) get quoted, as if he's the spiking neural network guru in
an article about us....can you reference any recent Intel articles where key Brainchip staff (Peter or Anil) get asked to comment
within a competitors new product article....maybe I'm just moaning out loud, but I'm pretty sure our CTO would never be drawn
into comment on other companies news articles....just saying......


Tech

TECH said:

Good afternoon,

What I find rather interesting, if that's the right word is in the attached link below, that's primarily focused on us,
Brainchip's latest offering AKIDA PICO, how does Mike Davies (Intel) get quoted, as if he's the spiking neural network guru in
an article about us....can you reference any recent Intel articles where key Brainchip staff (Peter or Anil) get asked to comment
within a competitors new product article....maybe I'm just moaning out loud, but I'm pretty sure our CTO would never be drawn
into comment on other companies news articles....just saying......

Brain-like Computers Tackle the Extreme Edge

Start-up BrainChip announces a new chip design for a milliwatt-level AI inference

spectrum.ieee.org

Tech

Click to expand...

Yeah, but what can you do, if you want to get an independent industry view on a new product and the best option for that, is a Company with a research chip?..

We are basically at the top of the Neuromorphic Hill.

That's not reflected yet, in the way we want, but the fact that we are often mentioned, after Intel and IBM (with other startups "sometimes" mentioned after) says a lot, when the size of the respective Companies is considered..

How AI and Accelerated Computing Drive Energy Efficiency​

AI and accelerated computing are transforming industries by driving energy efficiency and offering innovative solutions to global sustainability challenges, as Joshua Parker explains on NVIDIA’s AI Podcast.


October 3, 2024 by Kristen Yee



Share

AI isn’t just about building smarter machines. It’s about building a greener world.
From optimizing energy use to reducing emissions, artificial intelligence and accelerated computing are helping industries tackle some of the world’s toughest environmental challenges.
As Joshua Parker, NVIDIA’s Senior Director of Corporate Sustainability, explains on the latest edition of NVIDIA’s AI Podcast, these technologies are powering a new era of energy efficiency.

Can AI Help Reduce Energy Consumption?​

Yes. And it’s doing it in ways that might surprise you.
AI systems themselves use energy—sure—but the big story is how AI and accelerated computing are helping other systems save energy.
Take data centers, for instance.

The AI Podcast · NVIDIA’s Josh Parker on How AI and Accelerated Computing Drive Sustainability – Ep. 233
They’re the backbone of AI, housing the powerful systems that crunch the data needed for AI to work.
Globally, data centers account for about 2% of total energy consumption, and AI-specific centers represent only a tiny fraction of that, Parker explains.
Despite this, AI’s real superpower lies in its ability to optimize.
How? By using accelerated computing platforms that combine GPUs and CPUs.
GPUs (Graphics Processing Units) are designed to handle complex computations quickly and efficiently.
In fact, these systems can be up to 20 times more energy-efficient than traditional CPU-only systems, Parker notes.
That’s not just good for tech companies—it’s good for the environment, too.

What is Accelerated Computing?​

At its core, accelerated computing is about doing more with less.
It involves using specialized hardware—like GPUs—to perform tasks faster and with less energy.
This isn’t just theoretical. Over the last eight years, AI systems running on accelerated computing platforms have become 45,000 times more energy-efficient, Parker said.
That’s a staggering leap in performance, driven by improvements in both hardware and software.
So why does this matter? It matters because, as AI becomes more widespread, the demand for computing power grows.
Accelerated computing helps companies scale their AI operations without consuming massive amounts of energy. This energy efficiency is key to AI’s ability to tackle some of today’s biggest sustainability challenges.

AI in Action: Tackling Climate Change​

AI isn’t just saving energy—it’s helping to fight climate change.
For instance, AI-enhanced weather forecasting is becoming more accurate, allowing industries and governments to prepare for climate-related events like hurricanes or floods, Parker explains.
The better we can predict these events, the better we can prepare for them, which means fewer resources wasted and less damage done.
Another key area is the rise of digital twins—virtual models of physical environments.
These AI-powered simulations allow companies to optimize energy consumption in real-time, without having to make costly changes in the physical world.
In one case, using a digital twin helped a company achieve a 10% reduction in energy use, Parker said. That may sound small, but scale it across industries and the impact is huge.
AI is also playing a crucial role in developing new materials for renewable energy technologies like solar panels and electric vehicles, accelerating the transition to clean energy.

Can AI Make Data Centers More Sustainable?​

Here’s the thing: AI needs data centers to operate, and as AI grows, so does the demand for computing power. But data centers don’t have to be energy hogs.
In fact, they can be part of the sustainability solution.
One major innovation is direct-to-chip liquid cooling. This technology allows data centers to cool their systems much more efficiently than traditional air conditioning methods, which are often energy-intensive.
By cooling directly at the chip level, this method saves energy, helping data centers stay cool without guzzling power, Parker explains.
As AI scales up, the future of data centers will depend on designing for energy efficiency from the ground up. That means integrating renewable energy, using energy storage solutions, and continuing to innovate with cooling technologies.
The goal is to create green data centers that can meet the world’s growing demand for compute power without increasing their carbon footprint, Parker says.

The Role of AI in Building a Sustainable Future​

AI is not just a tool for optimizing systems—it’s a driver of sustainable innovation. From improving the efficiency of energy grids to enhancing supply chain logistics, AI is leading the charge in reducing waste and emissions.
Let’s look at energy grids. AI can monitor and adjust energy distribution in real-time, ensuring that resources are allocated where they’re needed most, reducing waste.
This is particularly important as the world moves toward renewable energy, which can be less predictable than traditional sources like coal or natural gas, Parker said.
AI is also helping industries reduce their carbon footprints. By optimizing routes and predicting demand more accurately, AI can cut down on fuel use and emissions in logistics and transportation sectors.
Looking to the future, AI’s role in promoting sustainability is only going to grow.
As technologies become more energy-efficient and AI applications expand, we can expect AI to play a crucial role in helping industries meet their sustainability goals, Parker said.
It’s not just about making AI greener—it’s about using AI to make the world greener.
AI and accelerated computing are reshaping how we think about energy and sustainability.
With their ability to optimize processes, reduce energy waste, and drive innovations in clean technology, these technologies are essential tools for creating a sustainable future.
As Parker explains on NVIDIA’s AI Podcast, AI’s potential to save energy and combat climate change is vast—and we’re only just beginning to tap into it.

How AI and Accelerated Computing Drive Energy Efficiency

AI isn’t just about building smarter machines. It’s about building a greener world. From optimizing energy use to reducing emissions, artificial intelligence and accelerated computing are helping industries tackle some of the world’s toughest environmental challenges. As Joshua Parker, NVIDIA’s...

blogs.nvidia.com

IloveLamp said:

Vasyl Chumachenko, PhD on LinkedIn: #akida #neuromorphicchip #research #development #projectreview #ai #ml…

Akida neuromorphic chips – my honest opinion after finishing an R&D project focused on this technology 🧬 Our AI Consulting team at Data Science UA is proud…

www.linkedin.com

View attachment 70348 View attachment 70349

Click to expand...

Everyone who worked with akida have the same opinion but still so long to get market acceptance.

TECH said:

Good afternoon,

What I find rather interesting, if that's the right word is in the attached link below, that's primarily focused on us,
Brainchip's latest offering AKIDA PICO, how does Mike Davies (Intel) get quoted, as if he's the spiking neural network guru in
an article about us....can you reference any recent Intel articles where key Brainchip staff (Peter or Anil) get asked to comment
within a competitors new product article....maybe I'm just moaning out loud, but I'm pretty sure our CTO would never be drawn
into comment on other companies news articles....just saying......

Brain-like Computers Tackle the Extreme Edge

Start-up BrainChip announces a new chip design for a milliwatt-level AI inference

spectrum.ieee.org

Tech

Click to expand...

I would say Mike Davies quotes in this article have been copied and pasted from another article regarding loihi
and have nothing at all to do with Akida.
Love to be wrong but.

TECH said:

Good afternoon,

What I find rather interesting, if that's the right word is in the attached link below, that's primarily focused on us,
Brainchip's latest offering AKIDA PICO, how does Mike Davies (Intel) get quoted, as if he's the spiking neural network guru in
an article about us....can you reference any recent Intel articles where key Brainchip staff (Peter or Anil) get asked to comment
within a competitors new product article....maybe I'm just moaning out loud, but I'm pretty sure our CTO would never be drawn
into comment on other companies news articles....just saying......

Brain-like Computers Tackle the Extreme Edge

Start-up BrainChip announces a new chip design for a milliwatt-level AI inference

spectrum.ieee.org

Tech

Click to expand...

I highly doubt the author asked for that quote in relation to the article for Akida Pico.

The quote from Davies would be in relation to an entirely separate conversation. The author is repurposing it for this article. It's lazy journalism, happens all the time.

Would luv to buy this bloke a beer






Many small and even huge companies have not yet heard of BrainChip Akida and therefore do not yet know the enormous potential that Akida has.

Even companies like Microsoft are still stuck with outdated and power-hungry technology that uses graphics processors to realize artificial intelligence.
The outdated method used there to realize intelligence has nothing to do with the enormous performance of biological brains.

Even crazier:
Microsoft is currently trying to get approval to restart a decommissioned nuclear power plant. The nuclear power plant will only be used to power outdated, power-hungry AI technology.

It is time for large companies to also get involved with modern technologies.

BrainChip Akida is contemporary and future-oriented.

It requires only a tiny amount of electricity to awaken the enormous power of neuromorphic intelligence.

Soon Akida will serve people in everyday devices and indispensable helpers.

A hearing aid that detects and amplifies the human voice in real time from a mix of noise and human voices.

This is something people who rely on hearing aids have been hoping for for ages - now the technology is here, and it's all cloud-free.

cosors said:

I can take your words to mean that there is nothing for you to celebrate about the German reunification and it was today just a free day for you.

Click to expand...

Oh, I celebrated it when it happened, but this is so long ago now, that it is now just a normal free day to most people. By the way, yes, it was a day to celebrate, but it also brought along many costly years to follow for those from the West of paying high extra monthly taxes. So it is understandable that the East celebrates it more than the West.

Edge AI also flagged by Tata Elxsi Transportation as a key tech for vehicle interaction.

Technologies Revolutionising Vehicle Interaction​

Several technologies are set to revolutionise the way we interact with our vehicles. Edge AI, for instance, allows for real-time processing of data within the vehicle, reducing the need for cloud-based computation and enabling faster response times. This is particularly useful for applications like voice-activated controls and real-time diagnostics.

GStocks123 said:

This recently published article is worth the read. Quite a few experiments completed with Akida, Loihi 2 & DynappCNN. Akida appears to outperform on most.

Detection of Fast-Moving Objects with Neuromorphic Hardware

Click to expand...

Gazzafish said:

New article comparing Akida to Loihi2. the entire article is worth the read as it. Compares power usage and speed across both platforms

Detection of Fast-Moving Objects with Neuromorphic Hardware

Extract :-
For Loihi2, we did not have direct access to an edge device, but only through a virtual machine provided by Intel via the Intel Neuromorphic Research Community8. With this Loihi2 setup, the time per forward pass is with 1458.57ms two orders of magnitude slower than the other devices. This is mainly due to inefficient communication between the virtual machine and the Loihi2 chip, which is a consequence of our current implementation not being well optimized in this regard. Note that the inference time on the GPU is longer than on all neuromorphic edge devices, however, the good hardware integration of the GPU shows its advantage.

Click to expand...

A video going along with that paper was uploaded to YouTube yesterday:



Both paper and video relate to another paper and video published by the same Uni Tübingen authors earlier this year. At a cursory glance, at least the videos (posted about six months apart) appear to be VERY similar:

https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-416900





Now compare the slides to those in the video uploaded October 3:








In fact, when I just tried to cursorily compare the new paper to the March 15 paper that @Fullmoonfever had linked at the time (https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-416313), I discovered that the link he had posted then now connects directly to this new paper, published on September 16, so it seems to be an updated version of the previous paper.

I did notice the addition of another co-author, though: Sebastian Otte, who used to be a PhD student and postdoc at Uni Tübingen (2013-2023) and became Professor at Uni Lübeck’s Institute for Robotics and Cognitive Systems just over a year ago, where he heads the Adaptive AI research group.




To put the results that our competitors’ neuromorphic offerings fared worse in the benchmarking tests alongside Akida somewhat into perspective:
In all fairness, it should be highlighted that Akida’s superiority was at least partly due to the fact that AKD1000 is available as a PCIe Board, whereas SynSense’s DynapCNN was connected to the PC via USB and - as the excerpt Gazzafish already posted shows - the researchers did not have direct access to a Loihi 2 edge device, but merely through a virtual machine provided by Intel via their Neuromorphic Research Cloud. The benchmarking would obviously yield better comparable results if the actual hardware used were of a similar form factor:

“Our results show that the better a neuromorphic edge device is connected to the main compute unit, e.g., as a PCIe card, the better the overall run-time.”


Anyway, Akida undoubtedly impressed the researchers, and as a result they are considering further experiments: “(…) future work could involve evaluating the system with an additional Akida PCIe card.”

---

In an earlier post (https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-426404), I had already mentioned that the paper’s first author, Andreas Ziegler, who is doing a PhD in robotics and computer vision at Uni Tübingen, has meanwhile completed his internship at Sony AI in Switzerland (that - as we know - partially funded the paper’s research):




Fun fact: One of his co-authors, Karl Vetter, however, is no longer with Uni Tübingen’s Cognitive Systems Lab, but has since moved to France, where he has been working as a research engineer for…

Neurobus for the past three months!
It’s a small world, isn’t it?!

For those worry warts, if there are any in this forum Sean and Tony (chairman) are well aware of holder concerns about the time it is taking to complete deals.
Sean addressed from the 34 minute point of the AGM the time it takes to do deals and why he is optimistic and confident.
If you want a 'lift' have a look and listen.
These issues were also addressed later in Question time.

More great exposure this time from the well respected Toms Hardware , seems to be some more detail amongst this read