BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Fact Finder
Top 20
Yes so can we ensure no sales are made for less than $1.17 please.
Thank you.
Regards
FF
AKIDA BALLISTA
Learning
Learning to the Top 🕵♂️
Bravo
If ARM was an arm, BRN would be its biceps💪!
Behzad Benam
Sep 16
·
2 min read
Optimizing System Resources by Using Neuromorphic Computing
Neuromorphic systems will replace GPUs in the future
Spiking Neural Networks (SNN) are artificial neural networks based on biological knowledge to optimize the resources required to run machine learning algorithms. They are very similar to biological neural networks and the mechanism of brain operation.
The human brain has about 100 billion neurons and hundreds of trillions of connections. The fastest GPUs with the same network size require about half a gigawatt power. Therefore, we need to reduce the power consumption of machine learning algorithm execution, which is one of the barriers to realizing humanoid robot technology. Neuromorphic computing takes the human brain as a reference to optimize resources for machine learning algorithms.
Energy efficiency
Neuromorphic technology is more power efficient than GPU-based artificial neural networks. Energy consumption is a crucial issue for large networks. Neuromorphic computing aims to mimic our brain's low-power computing ability. Due to the low power consumption of neuromorphic hardware, measuring power consumption is challenging and requires a new strategy.Traditional computer architecture, known as von Neumann architecture, physically separated the system into memory units, central processing units, and other units. This separation causes power inefficiency and is a significant limitation for the future of computing systems. The human brain behaves differently because we know that memory and control units in our brain are not separate, and both are together.
Self-organizing and self-learning
Neuromorphic computing can solve uncertainties by learning new subjects like the human brain. Recently presented approaches in robotics can create new algorithms. The neuromorphic architecture is not as dependent on high-quality training data as deep neural networks.Execution performance
According to Moore's Law, the number of transistors in a microchip doubles every two years. Although Moore's Law is not entirely correct and the speed of doubling transistors has changed, based on new research, neuromorphic computing is a way to keep Moore's Law still true.
buena suerte :-)
BOB Bank of Brainchip
Some new chips from Sifive aimed at wearables and smart consumer devices
Fact Finder
Top 20
What do electrical engineers do?
Harness the Power of Electricity
Electrical engineers create, design and manage electricity to help power the world. They are problem-solvers who study and apply the physics and mathematics of electricity, electromagnetism and electronics to both large- and small-scale systems to process information and transmit energy. Electrical engineers work with all kinds of electronic devices which transform society, from the smallest pocket devices to large power stations and supercomputers.At UNSW School of Electrical Engineering and Telecommunications, we help our students learn through a combination of design and lab work. This mix of theory and practical application helps students visualise concepts and apply their ideas in real-life situations. Students learn to do what an electrical engineer does day-to-day: analyse and diagnose a problem and develop an innovative solution.
Electrical Engineering Industries
Electrical engineers mostly work with large-scale electrical systems such as motor control and power generation and transmission. They use a diverse range of technologies, from the lighting and wiring of buildings, to design of household appliances, telecommunication systems, electrical power stations and satellite communications. In the emerging field of microelectronics, electrical engineers design or develop electrical systems and circuits in computers and mobile devices.Graduates however aren’t just limited to these industries. Our degrees are structured in ways that encourage analytical thinking, help master time management and ensure students are technically proficient. Because of this, electrical engineers from UNSW are in high demand even in areas such as:
- Renewable energy
- Global Positioning System (GPS) technologies
- Mobile networking
- Banking
- Finance
- Arts
- Management
- Consulting”
They are clearly highly intelligent and capable of in-depth research in the above stated areas and would be tuned into a range of on line professional services where they could access all sorts of technical and scientific information that the lay person would not have access to.
Fact Finder a recognised technophobe and retired lawyer with no background in the sciences beyond high school only has access to what he finds on line and what Brainchip releases and of course to a brilliant retired consulting engineer @Diogenese.
You might think therefore that a brilliant electrical engineer of the type described above by the University of NSW could do a whole lot better by this group than simply stating “I don’t believe you” as a rebuttal argument to Fact Finder who is doing no more than parroting back what has been publicly stated by others similarly skilled in the art as the electrical engineer.
Now of course as Fact Finder has never been privy to an intellectual debate between electrical engineers skilled in the art of neuromorphic computing perhaps this is how it is done.
One states a theory and the other responds “I don’t believe you” and the other says “Ok I must be wrong” then they all go to the pub.
My error in this has been to cause Fact Finder to believe such arguments would be more like legal debates where one lawyer states a proposition put forward by the superior court and the other lawyer responds with a contrary position supported by another superior court. But of course this is the law and not science.
The thing that we all know is that on the Brainchip website there is free access to the Meta TF which allows you to explore the AKIDA technology revolution in the privacy of your own electrical engineering workshop and also direct questions to Brainchip engineers???
The other thing we all know is that though the AKD1000 chip was not available in 2019 the AKIDA IP was released to select early access customers from around July, 2019 and was being implemented in an FPGA for internal purposes.
We also know that laying around in Peter van der Made’s lab was Studio and Studio Accelerator both being earlier iterations of the AKIDA technology.
Though not skilled in the art I think it is reasonable to accept that Peter van der Made the inventor of the AKIDA technology had access to sufficient material to make statements about what his AKIDA technology could do.
So it might be thought that the blistering response from the electrical engineer that ‘na na’ he did not have AKD1000 in 2019 fails to live up to even cursory examination.
My opinion only DYOR
FF
AKIDA BALLISTA
Fact Finder
Top 20
Behzad Benam
Sep 16
·
2 min read
Optimizing System Resources by Using Neuromorphic Computing
Neuromorphic systems will replace GPUs in the future
Spiking Neural Networks (SNN) are artificial neural networks based on biological knowledge to optimize the resources required to run machine learning algorithms. They are very similar to biological neural networks and the mechanism of brain operation.
The human brain has about 100 billion neurons and hundreds of trillions of connections. The fastest GPUs with the same network size require about half a gigawatt power. Therefore, we need to reduce the power consumption of machine learning algorithm execution, which is one of the barriers to realizing humanoid robot technology. Neuromorphic computing takes the human brain as a reference to optimize resources for machine learning algorithms.
Energy efficiency
Neuromorphic technology is more power efficient than GPU-based artificial neural networks. Energy consumption is a crucial issue for large networks. Neuromorphic computing aims to mimic our brain's low-power computing ability. Due to the low power consumption of neuromorphic hardware, measuring power consumption is challenging and requires a new strategy.
Traditional computer architecture, known as von Neumann architecture, physically separated the system into memory units, central processing units, and other units. This separation causes power inefficiency and is a significant limitation for the future of computing systems. The human brain behaves differently because we know that memory and control units in our brain are not separate, and both are together.
Self-organizing and self-learning
Neuromorphic computing can solve uncertainties by learning new subjects like the human brain. Recently presented approaches in robotics can create new algorithms. The neuromorphic architecture is not as dependent on high-quality training data as deep neural networks.
Execution performance
According to Moore's Law, the number of transistors in a microchip doubles every two years. Although Moore's Law is not entirely correct and the speed of doubling transistors has changed, based on new research, neuromorphic computing is a way to keep Moore's Law still true.
View attachment 20952
WOW.
Peter van der Made may have been speaking the truth at the AGM in 2019 when he addressed shareholders.
WOW.
Maybe this is why an electrical engineer was not prepared to do his own research???
Wolves in sheep clothing???
My opinion only DYOR as @Bravo does many thanks.
FF
AKIDA BALLISTA
Bravo
If ARM was an arm, BRN would be its biceps💪!
Damo4
Regular
Wow!
Great find mate.
All I need now is BRN to enter orbit and I'll pull out just enough to buy one!
Dhm
Regular
Is anyone else tuned in to the Uni of Western Sydney Neurpmorphic Seminar? My past interaction with them led me to believe that they haven't used Akida, but that was over 3 months ago.
The event is being recorded so later on I will post a link for anyone to watch. I am working so the seminar is in the background. I have already fired a question to them:
The event is being recorded so later on I will post a link for anyone to watch. I am working so the seminar is in the background. I have already fired a question to them:
Fact Finder
Top 20
I have mentioned my memory before and how it plagues my life but was a valuable asset in my past careers.
Well that pesky memory thing is at play again and so in the interest of fairness and balance I thought I should give the final word to Milo:
“2. Akida is an AI chip and I think here he means that Akida can be used to process all the sensor data of the car. That doesn't mean Akida can outperform a GPU in areas the GPU's are good at. Do you think Akida can replace a GPU and able to handle the graphics you see in modern cars? Can Akida PCIe board replace a GPU and run modern games? If that were the case our Market cap won't be this by now.” - Milo
So fellow shareholders as Milo has stated AKIDA being able to replace GPUs the current market cap is no where near what it should be and Milo agrees with me that Brainchip is ridiculously oversold and under priced.
My opinion only DYOR
FF
AKIDA BALLISTA
Last edited:
Bravo
If ARM was an arm, BRN would be its biceps💪!
Interesting...
www.notebookcheck.net
Qualcomm Snapdragon Summit 2022 is officially set to start in mid-November 2022
The Snapdragon Summit is officially on, and will take place from its traditional Hawai'i setting in 2022. However, it will also be livestreamed, starting with its Day 1 keynote. The event is widely projected to introduce the new top-end 8 Gen 2 mobile processor, although Qualcomm asserts that it...
Dhm
Regular
The reply was as I expected......no. The manner of the presenters verbal response led me to believe that they are unsure of our suite of products and disruption. The presentation showed a rocket launch whereby the word Prophesee was shown as a camera system. I will win no friends by repeatedly bombarding them with further Brainchip questions.
@Fact Finder perhaps you might want to send the link to TD when it is published later on. He may want to offer the university some info about how ahead of the field we are.
Dhm
Regular
https://uws.zoom.us/j/87065262335?pwd=Yzc5cEtUbFpGYStWZzdrZk54UndoUT09
The seminar is being recorded so I will publish a link later.
Boab
I wish I could paint like Vincent
Am now back up to my 20% threshold. Like a Stingray stealing my crab bait I was able to hoover up another 43,000 shares.
Hi dhm,
UWS get a guernsey in Prophesee's Community page:
https://www.prophesee.ai/prophesee-inventors-community/
If memory serves, UWS had a camera aboard a recent NASA launch, but the data was transmitted to earth for processing.
https://www.prophesee.ai/space-situational-awareness-event-based-vision
WORLD FIRST NEUROMORPHIC INSPIRED MOBILE TELESCOPE OBSERVATORY FOR HIGH PERFORMANCE SPACE SITUATIONAL AWARENESS
The growing reliance on satellites has led to an increased risk in collisions between space objects. Accurate detection and tracking of satellites has become crucial.
Astrosite, a world first neuromorphic-inspired mobile telescope observatory developed by the International Centre for Neuromorphic Systems (ICNS) at Western Sydney University is using Event-Based sensing as a more efficient and low-power alternative for Space Situational Awareness.
The Astrosite is a mobile observatory that uses Event-Based Vision in a new telescope system. This allows the system to only collect information when something changes in its field of view – i.e. when a satellite or other object is detected.
This results in far less data being processed than taking a series of snapshots. The high dynamic range that Prophesee’s Metavision Event-Based Vision sensor delivers allows for observation of space even during the daytime.
Western Sydney University has established the International Centre for Neuromorphic Systems (ICNS) – the only dedicated neuromorphic laboratory in Australia – as a home and global hub for leading researchers and students in this increasingly important field. The work of ICNS encompasses all three essential components of data-based decision-making systems, as their vision is to perform world-leading research to develop neuromorphic sensors, algorithms, and processors, and apply them to solve problems in modern society.
I suppose WA is not really part of Australia?
alwaysgreen
Top 20
Douglas Fairbairn on LinkedIn: Quadric’s New Chimera GPNPU Processor IP Blends NPU and DSP into New…
Big announcement from one of our AI IP partners!
Looks to be CNN, not SNN. Not us?
Also, nobody from Brainchip has "liked" it yet.
Last edited:
Similar threads
