BRN Discussion Ongoing

Sirod69

bavarian girl ;-)
And Todd Vierra makes a point of describing OnSemi as their PARTNER.

To run a safety critical system of the type OnSemi describe and which Todd Vierra also alludes to would require significant power reserved for this purpose away from the driving wheels if running conventional Von Neumann compute which would require active cooling as some of these functions such as child detection need to run after the vehicle has been turned off across the full range of climatic conditions.

While there are other low powered neuromorphic processors they are not capable of running all the five senses plus radar, Lidar and ultrasonic and perform regression analysis and sensor fusion while being sensor and process agnostic and maintaining the cyber security for intelligent airbag deployment.

In safety critical systems providing redundancy is also a factor to consider and again comparing the AKIDA platform with the Nvidia Jetson series its compact small form and low weight makes it a winner.

My opinion only DYOR
Fact Finder
I just came across this article, but I don't know if you've already talked through it.

Do we know anything about I/ONX? Somehow I can't find much there, it's a small company and I can't find anything related to Brainchip.

The Hidden Trap of GPU-Based AI: The Von Neumann Bottleneck​

Dr. Eric Woodell

Mission-Critical Facilities Analyst and Auditor; Author of the book "Mission-Critical Facilities Management," Owner of Amerruss LLC

23. Januar 2024

.....,
nobody inside industry has worked at, much less seriously considered, challenging the Von Neumann architecture. There are attempts at quantum computing, where the environmental requirements are even more absurd than the Nvidia solutions... And then there is Neuromorphic computing.

Neuromorphic computing attempts to mimic how the organic brain functions, instead of the one-bit-at-a-time approach of the Von Neumann architecture. And this is where the real solution to viable AI lies.
....
I/ONX is a company that reached out to me for my input.

Their approach was to throw out the Von Neumann architecture and build a completely new instruction set for computer processors called Kore, which eliminates the time limitations imposed by the one-bit-at-a-time approach.
 
Last edited:
  • Like
  • Fire
Reactions: 3 users

Esq.111

Fascinatingly Intuitive.
  • Like
Reactions: 4 users

TopCat

Regular
Evening NickBRN ,

Thankyou , but the link dose not open, possibly only a problem at my end as not a LinkedIn subscriber.

Regards,
Esq.
IMG_3410.jpeg
IMG_3411.jpeg
 
  • Like
  • Love
  • Fire
Reactions: 67 users

Esq.111

Fascinatingly Intuitive.
Evening TopCat ,

Thankyou kindly good sir.

Regards,
Esq.
 
  • Like
Reactions: 8 users
Magnus “the master of foreplay”
I'm sure he will be dressed like this when he mentions AKIDA being used in their new cars:)

1706870285752.png
 
  • Haha
  • Like
Reactions: 12 users

Sirod69

bavarian girl ;-)
  • Haha
  • Like
Reactions: 5 users

MrRomper

Regular
  • Like
  • Fire
  • Love
Reactions: 31 users

rgupta

Regular
To make every device intelligent it should l
I'm sure he will be dressed like this when he mentions AKIDA being used in their new cars:)

View attachment 55781
Very important point to understand. Joined Intel programme in 2020 and other neurophonic programmed as well.
EQXX was displayed in 2021 and Mercedes told the world akida is 10 times better than any other available solution for keyword spotting.
So if you reason it out point is clear
 
  • Like
  • Fire
Reactions: 2 users

Sirod69

bavarian girl ;-)

AI in less than 100 mW! Power efficient tech at CES 2024​

From smart devices and wearables to mobile devices and cars, we power products used by 70% of the world's population. 🌐

To take a deep dive into what we do and why our partners choose to build #onArm, we invited Jeff Geerling to #CES2024 to speak with our ecosystem.

Follow along in his YouTube video as he uncovers the prevalence, versatility, and performance of Arm technology

 
  • Like
  • Thinking
  • Fire
Reactions: 18 users

Diogenese

Top 20
Just sittin down for dinner F&Chips with a brewski, and boom, first time I’ve seen a TV advert for Samsungs new phone GALAXY AI ! 👊🏼👊🏼

Are we powering this droid ?

Bring it 💥

SONIC OUT !
I still have Samsung in my "Competitors" folder.

This 2021 patent application for automatic translating phones does not use Akida. Of course, its performance would be greatly enhanced by Akida, but does Samsung know that?

US2023197059A1 ELECTRONIC DEVICE AND CONTROL METHOD THEREOF 20211015


1706874795039.png



[0093] The neural network model stored in the memory 130 may be a model based on a statistical machine translation (SMT) model or a model based on a neural machine translation (NMT). The neural network machine translation model (NMT) has an effect of outputting a natural and highly-quality translation by performing translation in units of whole sentences and phrases, rather than translating words individually.

To incorporate Akida, the whole circuit architecture shown would need to be redesigned from the ground up.
 
Last edited:
  • Like
  • Fire
  • Sad
Reactions: 16 users

Diogenese

Top 20


It's great that Marcus mentions "Hey Mercedes!" in the context of MB.OS because that means that, while MB.OS was being designed, they were well aware of Akida, so this increases the likelihood of Akida being compatible with MB.OS, or, to put it another way, there is an increased chance that MB.OS has been designed so that it is compatible with Akida among other technologies.

"In the ongoing development of the MBUX Virtual Assistant, it opens up wider freedoms for innovation than would be possible with an off-the-shelf solution from a third-party provider."
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 39 users

Esq.111

Fascinatingly Intuitive.
Could be a very productive event coming up at IFS.


View attachment 55630


View attachment 55631
Morning TopCat & Fellow Chippers ,

Just joining some dots and adding a possible sweetener.....

INTEL FOUNDRY PARTNERS , BRAINCHIP & SAM ALTMAN all in the same room.

Article on ChatGPT , CEO Sam Altman ( OpenAI ) & Arizona State University .

Arizona State University happens to be one of Brainchips technology training partners.

Drawing a long bow..... bit like Sam is stalking us, in a good way hopefully.

😃.


Regards ,
Esq.
 
  • Like
  • Love
  • Fire
Reactions: 55 users

Mt09

Regular

Attachments

  • IMG_5598.png
    IMG_5598.png
    261.7 KB · Views: 124
  • Like
  • Fire
Reactions: 17 users
When things turn for the better and weather that’s on Monday next week or in a years time and there’s movement in the share price what would be the least amount of shares you want to have in your portfolio?

Every day is one day closer to financial independence.
 
  • Like
  • Fire
Reactions: 14 users

TECH

Regular
Sorry I can’t find the full paper only the abstract


Neuromorphic Medical Image Analysis at the Edge: On-Edge training with the Akida Brainchip

Bråtman, Ebba​

KTH, School of Electrical Engineering and Computer Science (EECS).

Dow, Lucas​

KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Medicinsk bildanalys med neuromorfisk hårdvara : On-Edge-träning med Akida Brainchip (Swedish)

Abstract [en]​


Computed Tomography (CT) scans play a crucial role in medical imaging, allowing neuroscientists to identify intracranial pathologies such as haemorrhages and malignant tumours in the brain. This thesis explores the potential of deep learning models as an aid in intracranial pathology detection through medical imaging. By first creating a convolutional neural network model capable of identifying brain haemorrhage and then moving it onto the neuromorphic processor Akida AKD1000, it allowed the usage of Spiking Neural Networks and on-edge retraining capabilities. In a process called few-shot learning, the model was trained to also identify brain tumours with minimal additional samples. The research further investigated how the parameters used in the edge-learning influenced classification accuracy. It was shown that the parameter selection and interaction introduced a trade-off in regard to accuracy for the haemorrhage and tumour classification models, but an optimal constellation of parameters could be extracted. These results aim to serve as a foundation for future endeavours in image analysis using neuromorphic hardware, specifically within the domain of few-shot and on-edge learning. The integration of these models in the medical field has the potential to streamline the diagnosis of intracranial pathologies, enhancing accuracy and efficiency while unloading medical professionals.

There we go again....AKD 1000 doing us so proud !! "Too narrow in it's offerings" that comment still haunts me today.

I fully understand how new, more advanced iterations of Akida must be developed to drive our company forward in doing so, accommodating current and future customers requirements as we all grow, but as I have commented on many times now, please appreciate how AKD1000 was
a masterly achievement a few years ago.

As far as newer iterations are concerned, I think there is a little bit of confusion with regards AKD I AKD II AKD III up to AKD X...I did ask
Peter about this very thing in 2022/23 as to how he saw future iterations evolving over the next 7 year period, i.e. 2023 thru to 2030.

With regards reaching AGI by or around 2030, he said that it's possible in his opinion, but nothing is 100% certain, also that following the
earlier suggested path that appeared in an old slide showing AKD 1 1.5 thru to AKD X wasn't the plan in his mind, but I'll track down his
emailed reply to me before going any further, just in case I mix up his words and find myself in a spot of trouble, so to speak.

I'm hoping to hear some news late in 2024, early 2025 as to how AKD III is or has progressed, but lets not get too far ahead of ourselves,
we first need to achieve some solid traction reflected by ever increasing revenue streams created by both AKD 1 and AKD II....also it
would be nice to hear from our new guy in charge of sales, Steve Thorne on a company podcast, possibly too early but something during
the year would be nice in my opinion.

Regards to all.....Tech :coffee:(y)
 
  • Like
  • Love
  • Fire
Reactions: 38 users

cosors

👀
Is this already the MB NC special that we voted on or is there more to come? Maybe I have overlooked the link to the paper?
I mean, there were months to work it out. I don't want to grumble, I was just waiting for more insight. What was provided before for the wait until now was richer than this disclaimer. I think there should be more to come. I'd be grateful if someone could point me in the right direction.

____
Screenshot_2024-02-02-22-21-25-41_40deb401b9ffe8e1df2f1cc5ba480b12.jpg

Pressing on this for a PDF or page does not work for me.
 
Last edited:
  • Like
Reactions: 5 users

BrainShit

Regular
Hi All
In this world of instant gratification, three year election cycles, overnight multi millionaires and genuine time is ticking personal lifetime clocks the time it seems to be taking for Brainchip to become an overnight success can be frustrating.

It can also be hard to maintain perspective when every message around us is seemly negative. Interest rates, immigration numbers, cost of living, unemployment signals, national security, claims of genocide and on and on it goes 24/7 never stopping to take a breath even on the Australia Day public holiday weekend.

The following extracts are followed by the link to the full paper which is an interesting read but the point I am about to make is served by just these extracts.

The point is very simple.

This paper was published in 2021.

The ambition was lofty perhaps Science Fiction, the authors are eminent and located at prestigious places of research and employment.

The resources at their disposal huge in comparison with an Aussie company called Brainchip.

Yet Brainchip with the release of AKD1000, AKD1500 and AKIDA 2.0 are five years ahead and have achieved everyone of this groups lofty Science Fiction goals plus much more on a ridiculously small budget in comparison.

On top of which they have built out an amazing network of commercial partnerships hand in hand with their scientific and engineering achievements within that same limited budget.

If one divorces oneself from all the negativity there is much to praise about what Brainchip has achieved.

My opinion only DYOR
Fact Finder

“Autonomous Flying With Neuromorphic Sensing​

Patricia P. Parlevliet1*
newprofile_default_profileimage_new.jpg
Andrey Kanaev2 Chou P. Hung3 Andreas Schweiger4 Frederick D. Gregory5,6 Ryad Benosman7,8,9
newprofile_default_profileimage_new.jpg
Guido C. H. E. de Croon10 Yoram Gutfreund11 Chung-Chuan Lo12
newprofile_default_profileimage_new.jpg
Cynthia F. Moss13
  • 1Central Research and Technology, Airbus, Munich, Germany
  • 2U.S. Office of Naval Research Global, London, United Kingdom
  • 3United States Army Research Laboratory, Aberdeen Proving Ground, Maryland, MD, United States
  • 4Airbus Defence and Space GmbH, Manching, Germany
  • 5U.S. Army Research Laboratory, London, United Kingdom
  • 6Department of Bioengineering, Imperial College London, London, United Kingdom
  • 7Institut de la Vision, INSERM UMRI S 968, Paris, France
  • 8Biomedical Science Tower, University of Pittsburgh, Pittsburgh, PA, United States
  • 9Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, United States
  • 10Micro Air Vehicle Laboratory, Department of Control and Operations, Faculty of Aerospace Engineering, Delft University of Technology, Delft, Netherlands
  • 11The Neuroethological lab, Department of Neurobiology, The Rappaport Institute for Biomedical Research, Technion – Israel Institute of Technology, Haifa, Israel
  • 12Brain Research Center/Institute of Systems Neuroscience, National Tsing Hua University, Hsinchu, Taiwan
  • 13Laboratory of Comparative Neural Systems and Behavior, Department of Psychological and Brain Sciences, Neuroscience and Mechanical Engineering, Johns Hopkins University, Baltimore, MD, United States
Autonomous flight for large aircraft appears to be within our reach. However, launching autonomous systems for everyday missions still requires an immense interdisciplinary research effort supported by pointed policies and funding. We believe that concerted endeavors in the fields of neuroscience, mathematics, sensor physics, robotics, and computer science are needed to address remaining crucial scientific challenges. In this paper, we argue for a bio-inspired approach to solve autonomous flying challenges, outline the frontier of sensing, data processing, and flight control within a neuromorphic paradigm, and chart directions of research needed to achieve operational capabilities comparable to those we observe in nature. One central problem of neuromorphic computing is learning. In biological systems, learning is achieved by adaptive and relativistic information acquisition characterized by near-continuous information retrieval with variable rates and sparsity. This results in both energy and computational resource savings being an inspiration for autonomous systems. We consider pertinent features of insect, bat and bird flight behavior as examples to address various vital aspects of autonomous flight. Insects exhibit sophisticated flight dynamics with comparatively reduced complexity of the brain. They represent excellent objects for the study of navigation and flight control. Bats and birds enable more complex models of attention and point to the importance of active sensing for conducting more complex missions. The implementation of neuromorphic paradigms for autonomous flight will require fundamental changes in both traditional hardware and software. We provide recommendations for sensor hardware and processing algorithm development to enable energy efficient and computationally effective flight control………..”

“The long-term goal is hardware and software design and prototyping for interacting autonomous vehicles. Our
hardware and software design and prototyping for interacting autonomous vehicles. Our target is neuromorphic hardware that aims at mimicking the functions of neural cells in custom synthetic hardware that is analog, digital, and asynchronous in its nature of information processing and is vastly more energy-efficient and lighter than classical silicon circuitry.

It is expected that such a neuromorphic technology will disrupt existing solutions and be a key enabler for real-time processing of different sensor modalities by lower cost, lower energy consumption, lower weight, adaptable to changing missions, while providing enhanced and resilient performance and saving human lives.”

https://www.frontiersin.org/articles/10.3389/fnins.2021.672161/full
Speaking of neuromorphic sensing.... and detection.

- BrainChip Demonstrates Akida Vibrational Analysis Tactile Sensing
- BrainChip Demonstrates Taste Sensing with Akida
- BrainChip + Nviso Emotion Detection Demo
- BrainChip Demonstrates Drone Voice Keyword Spotting
- BrainChip Vibrational Analysis Tactile Sensing
- BrainChip Olfactory Analysis Technology
- BrainChip Object Detection and Classification
- BrainChip Facial Recognition Analysis Technology
- BrainChip Autonomous Learning Technology


BrainChip is set... industry will follow with applications an devices for sure.
Regular time to marked 2-4 years... for projects who starts now.
 
Last edited:
  • Like
  • Thinking
Reactions: 10 users
Top Bottom